Skip to content

Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.

chore(build): route /prompts and /derivative, and refresh the generated site indexes

ni3a91f869f60704
diff --git a/.agents/.claude-plugin/plugin.json b/.agents/.claude-plugin/plugin.json
index 957dd50ac..af1bf8f04 100644
--- a/.agents/.claude-plugin/plugin.json
+++ b/.agents/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "three-ws-core",
- "description": "Core wallet and x402 payment skills — authenticate, fund, send tokens, trade, search the bazaar, pay for services, monetize APIs, and query onchain data.",
+ "description": "The three.ws skill pack: 3D model and avatar generation, building and monetizing agents on the platform, and the wallet/x402 agent economy.",
"version": "1.0.0",
"author": {
"name": "nirholas"
diff --git a/.agents/README.md b/.agents/README.md
index aa7091dfe..d06e9acfd 100644
--- a/.agents/README.md
+++ b/.agents/README.md
@@ -1,6 +1,8 @@
# three.ws Core
-Core wallet and x402 payment skills for Claude Code. Authenticate a wallet, fund it, send tokens, trade, search the x402 bazaar, pay for services, monetize your own APIs, and query onchain data — all from natural language.
+The three.ws skill pack for Claude Code. Generate and rig 3D models and avatars, create an
+agent with a body, wallet and persona, publish and price its skills, hire other agents, run
+a wallet, and pay or get paid over x402, all from natural language.
Part of the [three.ws plugin marketplace](https://github.com/nirholas/three.ws).
@@ -15,30 +17,43 @@ Then run `/reload-plugins` (or restart Claude Code) and start a request like *"s
## Skills
-| Skill | What it does |
-| :---- | :----------- |
-| `authenticate-wallet` | Sign in to the wallet. Prerequisite for sending, trading, and funding. |
-| `fund` | Add money to the wallet — deposit, top up, buy USDC, onramp. |
-| `send-usdc` | Send USDC, ETH, POL, or SOL to an address or ENS name on Base, Polygon, or Solana. |
-| `trade` | Swap tokens on Base or Polygon (USDC ↔ ETH ↔ POL). |
-| `search-for-service` | Search and browse the x402 bazaar for paid API services. |
-| `pay-for-service` | Make a paid API request to an x402 endpoint with automatic USDC payment. |
-| `monetize-service` | Build and deploy a paid API that other agents can pay to use via x402. |
-| `query-onchain-data` | Query onchain data on Base using the CDP SQL API via x402. |
-| `x402` | General x402 entry point — discover payment requirements and call paid endpoints. |
+The full, always-current index with every trigger is
+[`skills/SKILLS.md`](skills/SKILLS.md), generated from the skill files themselves
+(`npm run build:skills-pack`). The machine-readable form is
+[`skills/skills-pack.json`](skills/skills-pack.json).
-Skills are model-invoked: Claude selects the right one from the task. You can also call any of them explicitly, e.g. `/three-ws-core:send-usdc`.
+| Group | Skills |
+| :---- | :----- |
+| Wallet and x402 economy | `authenticate-wallet`, `fund`, `send-usdc`, `trade`, `search-for-service`, `pay-for-service`, `monetize-service`, `query-onchain-data`, `x402` |
+| Build on three.ws | `create-a-three-ws-agent`, `build-an-agent-skill`, `sell-an-agent-skill`, `hire-an-agent`, `connect-three-ws-mcp` |
+| 3D creation | `generate-3d-model`, `create-3d-avatar`, `rig-a-model`, `find-3d-assets`, `embed-three-ws-avatar` |
+| Production ops (maintainers) | `gcp-triage` |
+| Vendored partner packs | wallet, identity, and market-data skills kept byte-identical to their publishers' drops |
+
+Skills are model-invoked: Claude selects the right one from the task. You can also call
+any of them explicitly, e.g. `/three-ws-core:send-usdc`.
+
+Prefer a smaller install? The same folders ship as standalone repos, one plugin each:
+`nirholas/three-ws-3d-skills` (no crypto content) and
+`nirholas/three-ws-agent-economy-skills`. See
+[docs/agent-skills.md](../docs/agent-skills.md).
## Configuration
-These skills talk to the three.ws wallet API. Set the following in your environment before use:
+Nothing is required to start: the 3D skills run against the free hosted lane
+(`https://three.ws/api/mcp-studio`), which needs no account, no key, and no payment.
-| Variable | Purpose |
-| :------- | :------ |
-| `THREE_WS_API` | Base URL of the three.ws wallet API. |
-| `THREE_WS_TOKEN` | Bearer token for the authenticated wallet. The `authenticate-wallet` skill obtains this for you. |
+| What you are doing | What it needs |
+| :----------------- | :------------ |
+| Generating or rigging 3D models, browsing the asset catalog | Nothing |
+| Anything tied to an account (agents, avatar library, pricing, earnings) | A three.ws API key from [/dashboard/api](https://three.ws/dashboard/api), exported as `THREE_WS_KEY` and sent as `Authorization: Bearer` |
+| Wallet operations (fund, send, trade) | The `awal` CLI's own email sign-in, handled by the `authenticate-wallet` skill |
+| Paid MCP tools or x402 endpoints | A funded wallet; the `pay-for-service` and `x402` skills drive the 402 handshake |
-No secrets are written to disk by these skills. Transfers are confirmed with you before they execute, and they are irreversible.
+API-key secrets are shown exactly once at creation, and their scopes are fixed then, so
+mint a key with only the scopes the task needs. No skill writes a secret to disk, and
+every money-moving skill renders a confirmation card and stops for an explicit yes before
+it spends: transfers are irreversible.
## License
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
index 65bb8bd90..f45f74499 100644
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -10,7 +10,7 @@
"name": "three-ws-core",
"source": "./.agents",
"displayName": "three.ws Core",
- "description": "Core wallet and x402 payment skills — authenticate, fund, send tokens, trade, search the bazaar, pay for services, monetize APIs, and query onchain data.",
+ "description": "The three.ws skill pack: 3D model and avatar generation, building and monetizing agents on the platform, and the wallet/x402 agent economy.",
"version": "1.0.0",
"author": {
"name": "nirholas"
diff --git a/CHANGELOG.md b/CHANGELOG.md
index a79842a66..01c885369 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,11 +7,15 @@ Public history for [three.ws](https://three.ws), newest first. New pages come fr
## 2026-09-20
- **$THREE Launchpad** (`/three-launchpad`): A bonding-curve launchpad priced in $THREE: every coin launched for a 3D agent is bought with $THREE, creators earn their fees in $THREE, and each graduation locks the $THREE it raised in a pool nobody can withdraw. Launch a coin or trade the live curves.
+- **Docs · The prompt library** (`/docs/prompts`): How the three.ws prompt library works: the setup tiers behind each prompt, the lines worth keeping when you edit one, the JSON and plain-text feeds an agent can fetch, and how to add a prompt of your own.
+- **Prompt Library** (`/prompts`): Copy-paste prompts for Claude and any AI agent: generate a 3D model or a rigged avatar, embed one on a site, validate a GLB, find or sell a paid API in the agent economy. Most of them need no account, no key and no setup.
- **A launchpad where every coin is bought with $THREE**: The three.ws bonding-curve launchpad is now priced in $THREE instead of SOL. A coin launched there for a 3D agent can only be bought with $THREE, its creator earns half of every trading fee in $THREE, and when it graduates, the roughly 12.3 million $THREE it raised is locked in its pool permanently. The new launchpad page shows the live curves with buy and sell straight from your wallet. The curve has been verified against Solana mainnet and opens for launches as soon as its settings are published on-chain. (`/three-launchpad`) `[feature]`
+- **A library of prompts you can paste straight into Claude**: Knowing that three.ws has a free text-to-3D API is not the same as getting a rigged avatar out of it, and the paragraph that closes that gap is one nobody should have to write themselves. /prompts is 23 ready-made prompts for Claude and any other assistant: generate a model or a rigged avatar, search the CC0 catalog before generating anything, rig a GLB you already have, put a live avatar on your site, diagnose an embed that went dark, validate a model before it ships, find a paid API in the agent economy or sell your own. Each one names the real endpoint or tool, says what to do when a job comes back pending, and says what to hand back; the ones that can spend money are written to stop and show you the amount first. Most need no account, no key and no setup. Copy a prompt, open it directly in Claude with the text already in the box, or fetch the whole library as JSON or plain text. (`/prompts`) `[feature, docs]`
- **Agent reputation on Base and other EVM chains now shows real on-chain reviews**: Reputation panels, the passport widget and the trust scores behind agent-to-agent gating were asking the shared ERC-8004 reputation registry a question it does not answer, so agents with dozens of on-chain reviews showed none. They now read the registry the way it actually works: an agent with 41 reviews from 22 reviewers on Base shows 4.1 out of 5 and its recent reviews, and the panel loads in a few seconds on free public RPCs. Staked vouches are only offered on chains whose registry supports them. `[fix, improvement]`
- **Paid $THREE purchases say what is wrong instead of failing silently**: Every $THREE-priced purchase is sealed into one signed quote before you pay. If the platform side of that rail is not fully configured, the quote now comes back with a clear, retryable message and a named reason rather than an opaque internal error, and the platform status page reports the condition itself. Nobody has to be mid-checkout for the problem to be visible. (`/status`) `[fix, infra]`
- **Queued posts can quote an earlier post**: A post in the @trythreews content queue can now name an earlier post to quote, so a follow-up can add the detail the original left out instead of repeating it. The first use quotes the $THREE token MCP announcement with the numbers behind the MCP Tool Catalog: 321 tools across 42 servers, 293 of them free, and 215 whose read-only label is checked against the source on every build. (`/mcp-tools`) `[improvement]`
- **The @trythreews account now posts three times a day, every day**: The reviewed content queue that runs the @trythreews account moved to three posts a day, eight hours apart, on every day of the week including weekends. It used to hold its flagship slot for weekdays and pack all three posts into an eight-hour afternoon window, which meant a weekend could only ever carry two. Three posts went out under the new cadence today: the $THREE token MCP server, Forge Max, and the free object library. The Forge Max post also gained a check that proves the high-quality tier is a real, gated lane before it can be published, rather than only proving its page loads. (`/changelog`) `[improvement]`
+- **The flagship post slot now gets flagship material**: The @trythreews account publishes into three slots a day, one owned by each tier: proof of work at 04:00 UTC, a shipped feature at 12:00, a flagship at 20:00. The machine that drafts announcements from the backlog was not filling them that way. It never recorded a tier on anything it wrote, so every draft it produced was treated as a mid-tier feature and the 20:00 slot was left to whatever happened to be ready. It also dated the surfaces that need owner sign-off on their imagery into the best slot of every day, which pushed everything it could publish on its own weeks into the future. Announcements are now planned into the slot their own tier owns, the ones awaiting sign-off are listed separately instead of blocking the calendar, and six new announcements are queued for review. (`/changelog`) `[improvement]`
- **Two Uniswap v4 hooks: wearable 3D items as coins, and fees that reward agent reputation**: New open-source contracts. SkinHook turns a wearable 3D item into a fixed-supply coin with its own pool: wearing it locks one token, so every wearer shrinks the tradable supply, and the creator's royalty is taken inside the swap where it cannot be skipped, with a share for the site that referred the sale. AgentTierHook gives ERC-8004 agents a lower trading fee as their on-chain reputation grows, with liquidity providers keeping every fee. Both are tested against the real Uniswap v4 contracts and are not deployed yet. `[feature, sdk]`
## 2026-09-18
diff --git a/STRUCTURE.md b/STRUCTURE.md
index cff4317e4..65596491f 100644
--- a/STRUCTURE.md
+++ b/STRUCTURE.md
@@ -223,7 +223,8 @@ bottom.
| Cross-chain SDKs | [sdk/](sdk), [solana-agent-sdk/](solana-agent-sdk), [agent-payments-sdk/](agent-payments-sdk), [agent-protocol-sdk/](agent-protocol-sdk) | Published | Cross-chain agent SDKs |
| MCP integration | [mcp-server/](mcp-server), [mcp-bridge/](mcp-bridge), [packages/*-mcp/](packages) | 43 npm servers + 7 hosted remote (50 total, incl. the free `/api/mcp-studio` 3D Studio, whose ChatGPT plugin surface [api/mcp-chatgpt.js](api/mcp-chatgpt.js) `→ /api/mcp-chatgpt` serves the eight 3D tools and the model viewer without the persona tools or any `frameDomains`; both doors share [api/_mcp-studio/handler.js](api/_mcp-studio/handler.js), and `SURFACES` in [api/_mcp-studio/dispatch.js](api/_mcp-studio/dispatch.js) defines what each advertises), all in the [MCP registry](https://registry.modelcontextprotocol.io/?q=io.github.nirholas). Canonical metadata: [prompts/store-submissions/_generated/mcp-listing-source.json](prompts/store-submissions/_generated/mcp-listing-source.json), generated from the manifests by [scripts/build-mcp-listing-source.mjs](scripts/build-mcp-listing-source.mjs) (`npm run audit:mcp-listing` fails when it drifts) | Model Context Protocol surface, full server list in [docs/mcp.md](docs/mcp.md). Searchable index of every tool: [pages/mcp-tools.html](pages/mcp-tools.html) `→ /mcp-tools`, rendered from the generated [public/mcp-catalog.json](public/mcp-catalog.json) ([scripts/build-mcp-catalog.mjs](scripts/build-mcp-catalog.mjs), `npm run build:mcp-catalog`, staleness gated by `npm run audit:mcp-catalog`). Tool safety annotations are verified against each handler by [scripts/audit-mcp-safety.mjs](scripts/audit-mcp-safety.mjs) (`npm run audit:mcp-safety`, rules in [scripts/lib/mcp-safety-check.mjs](scripts/lib/mcp-safety-check.mjs), guarded-file list shared with the golden snapshot via [scripts/lib/mcp-tool-sources.mjs](scripts/lib/mcp-tool-sources.mjs)); docs [docs/mcp-safety.md](docs/mcp-safety.md) `→ /docs/mcp-safety`. Trust policy: [api/mcp-policy.js](api/mcp-policy.js) `-> GET /api/mcp-policy` turns those verified labels into a ready-to-paste client allowlist (profiles strict/balanced/open x formats claude/vscode/json), surfaced by the builder panel on `/mcp-tools`. Connector-review readiness (every paid stdio tool answers a clean x402 challenge, and the reviewer entitlement lifts it): [scripts/audit-mcp-reviewer-path.mjs](scripts/audit-mcp-reviewer-path.mjs), `npm run audit:mcp-reviewer`. Tests: [tests/mcp-safety-audit.test.js](tests/mcp-safety-audit.test.js), [tests/mcp-catalog.test.js](tests/mcp-catalog.test.js), [tests/api/mcp-policy.test.js](tests/api/mcp-policy.test.js) |
| Awesome 3D Agents (curated list) | Source [data/awesome.json](data/awesome.json), generator [scripts/build-awesome.mjs](scripts/build-awesome.mjs) (`npm run build:awesome`, drift-gated by `npm run check:awesome`, publishable mirror via `npm run awesome:standalone`), outputs [awesome/README.md](awesome/README.md) + [public/awesome.json](public/awesome.json), page [pages/awesome.html](pages/awesome.html) `-> /awesome`, link checker [scripts/check-awesome-links.mjs](scripts/check-awesome-links.mjs) (`npm run awesome:links`) | Live | An awesome-list of everything needed to give an AI agent a body: text-to-3D, capture and splatting, avatars, rigging, motion, lipsync and voice, web renderers, asset pipelines, physics and networking, agent frameworks, datasets, free assets, learning. One JSON source produces both the GitHub-facing list and the searchable page, so they cannot disagree. Every url is fetched and classified (ok / moved / bot-filtered / broken) before it ships; the checker stays out of the deploy path so a third-party outage cannot redden someone else's build. The README is written to pass `npx awesome-lint`: badge on the heading line, no License section, no Contributing entry in the contents, and every description capitalised and ended with a period, all enforced by the generator and by [tests/awesome-list.test.js](tests/awesome-list.test.js). Its last two lint rules read GitHub repository topics, which a list inside a product repo cannot satisfy, so `--standalone` emits a ready-to-publish mirror repo (readme, contributing, code of conduct, license) outside this checkout. Contributing: [awesome/CONTRIBUTING.md](awesome/CONTRIBUTING.md) |
-| Agent Skills pack | [.agents/skills/](.agents/skills) (canonical) → manifest [.agents/skills/SKILLS.md](.agents/skills/SKILLS.md), [.agents/skills/skills-pack.json](.agents/skills/skills-pack.json); published 3D subset [public/skills/3d-studio/](public/skills/3d-studio) `→ /skills/3d-studio/` | In-repo; bundled in the `three-ws-core` [plugin](.claude-plugin/marketplace.json); 3D subset live on the site | 43 portable `SKILL.md` folders (Agent Skills open standard) for any Claude surface: 3d/creative (cross-platform-safe), wallet/payments, intel/trading. The 3d/creative ones are also published as a public, downloadable bundle at `/skills/3d-studio/` (`three-ws-3d-skills.zip`), which is what an OpenAI Plugin Directory submission uploads on its Skills tab; a skill referencing a tool [api/_mcp-studio/](api/_mcp-studio) does not declare is dropped rather than shipped as a dead path. Regenerate manifest: `node scripts/build-skills-pack.mjs`; regenerate the published bundle: `npm run build:openai-skills` (drift gate `npm run check:openai-skills`, wired into `npm run gate`). Docs: [docs/agent-skills.md](docs/agent-skills.md) |
+| Agent Skills pack | [.agents/skills/](.agents/skills) (canonical) → manifest [.agents/skills/SKILLS.md](.agents/skills/SKILLS.md), [.agents/skills/skills-pack.json](.agents/skills/skills-pack.json); published 3D subset [public/skills/3d-studio/](public/skills/3d-studio) `→ /skills/3d-studio/` | In-repo; bundled in the `three-ws-core` [plugin](.claude-plugin/marketplace.json); 3D subset live on the site | Portable `SKILL.md` folders (Agent Skills open standard) for any Claude surface, in five categories: 3d/creative (cross-platform-safe), platform/agents (create an agent, author and sell its skills, hire other agents, connect a client to the MCP servers), wallet/payments, intel/trading, ops/production. Counts live in the generated manifest, never here. The 3d/creative ones are also published as a public, downloadable bundle at `/skills/3d-studio/` (`three-ws-3d-skills.zip`), which is what an OpenAI Plugin Directory submission uploads on its Skills tab; a skill referencing a tool [api/_mcp-studio/](api/_mcp-studio) does not declare is dropped rather than shipped as a dead path. Regenerate manifest: `npm run build:skills-pack` (drift gate `npm run check:skills-pack`); regenerate the published bundle: `npm run build:openai-skills` (drift gate `npm run check:openai-skills`, wired into `npm run gate`). Docs: [docs/agent-skills.md](docs/agent-skills.md) |
+| Standalone skill repos | [scripts/build-standalone-skill-repos.mjs](scripts/build-standalone-skill-repos.mjs) → `.data/standalone-repos/<repo>/` (gitignored) | Generated on demand; publishing is owner-gated | Assembles the three.ws-origin skills into small, publishable repos so an external user installs with one `/plugin marketplace add nirholas/<repo>` instead of cloning this monorepo: `three-ws-skills` (everything), `three-ws-3d-skills` (the crypto-free 3d/creative subset), `three-ws-agent-economy-skills` (wallet/payments + platform/agents). Each output is a complete one-plugin marketplace (`.claude-plugin/{marketplace,plugin}.json`, `skills/`, generated `README.md` with every trigger, `LICENSE`). Built from the same `collectSkills()` the manifest uses, so a copy cannot drift; nothing is committed here. `npm run build:skill-repos`, validate with `npm run check:skill-repos` (wired into `npm run gate`). Docs: [docs/agent-skills.md](docs/agent-skills.md) |
| Claude Code plugin marketplace | [marketplace/](marketplace) → plugins [three-ws-3d](marketplace/plugins/three-ws-3d), [three-ws-developer](marketplace/plugins/three-ws-developer) | In-repo · installable via `/plugin marketplace add nirholas/three.ws` | 3D generation + rigged avatars inside Claude Code (free lane + paid x402 tools) and developer tooling for building on three.ws. Index: [marketplace/README.md](marketplace/README.md) |
| SNS naming + pay-by-name | [api/sns.js](api/sns.js), [api/sns-subdomain.js](api/sns-subdomain.js), [api/threews/subdomain.js](api/threews/subdomain.js), [api/x402/pay-by-name.js](api/x402/pay-by-name.js), [src/solana/sns-subdomain.js](src/solana/sns-subdomain.js), [pages/threews-claim.html](pages/threews-claim.html) | In-repo | `*.threews.sol` subdomain mint, x402 payments addressed by name. Env: `THREEWS_SOL_PARENT_SECRET_BASE58` |
| Self-hosted x402 facilitator + ring economy | [api/x402-facilitator/[action].js](api/x402-facilitator/[action].js), [api/_lib/x402/self-facilitator.js](api/_lib/x402/self-facilitator.js), [api/x402/ring-settle.js](api/x402/ring-settle.js), [api/_lib/x402/pipelines/ring-rebalance.js](api/_lib/x402/pipelines/ring-rebalance.js), [api/x402-ring.js](api/x402-ring.js), [scripts/x402-ring-setup.mjs](scripts/x402-ring-setup.mjs) | In-repo (off by default) | Closed-loop agent-to-agent x402: platform wallets pay platform endpoints, settled in-house (no external facilitator). Fee-minimized, SOL-floor guarded, internal-labeled. Env: `X402_SELF_FACILITATOR_ENABLED`, `X402_FEE_PAYER_SECRET_BASE58`, `X402_TREASURY_SECRET_BASE58`. See [docs/x402-ring-economy.md](docs/x402-ring-economy.md), [docs/x402-settlement-pending.md](docs/x402-settlement-pending.md) |
diff --git a/data/changelog.json b/data/changelog.json
index b94deea21..3de6b0f01 100644
--- a/data/changelog.json
+++ b/data/changelog.json
@@ -28468,6 +28468,36 @@
"improvement"
],
"link": "/mcp-tools"
+ },
+ {
+ "date": "2026-09-20",
+ "title": "The flagship post slot now gets flagship material",
+ "summary": "The @trythreews account publishes into three slots a day, one owned by each tier: proof of work at 04:00 UTC, a shipped feature at 12:00, a flagship at 20:00. The machine that drafts announcements from the backlog was not filling them that way. It never recorded a tier on anything it wrote, so every draft it produced was treated as a mid-tier feature and the 20:00 slot was left to whatever happened to be ready. It also dated the surfaces that need owner sign-off on their imagery into the best slot of every day, which pushed everything it could publish on its own weeks into the future. Announcements are now planned into the slot their own tier owns, the ones awaiting sign-off are listed separately instead of blocking the calendar, and six new announcements are queued for review.",
+ "tags": [
+ "improvement"
+ ],
+ "link": "/changelog"
+ },
+ {
+ "date": "2026-09-20",
+ "title": "A library of prompts you can paste straight into Claude",
+ "summary": "Knowing that three.ws has a free text-to-3D API is not the same as getting a rigged avatar out of it, and the paragraph that closes that gap is one nobody should have to write themselves. /prompts is 23 ready-made prompts for Claude and any other assistant: generate a model or a rigged avatar, search the CC0 catalog before generating anything, rig a GLB you already have, put a live avatar on your site, diagnose an embed that went dark, validate a model before it ships, find a paid API in the agent economy or sell your own. Each one names the real endpoint or tool, says what to do when a job comes back pending, and says what to hand back; the ones that can spend money are written to stop and show you the amount first. Most need no account, no key and no setup. Copy a prompt, open it directly in Claude with the text already in the box, or fetch the whole library as JSON or plain text.",
+ "tags": [
+ "feature",
+ "docs"
+ ],
+ "link": "/prompts"
+ },
+ {
+ "date": "2026-09-20",
+ "title": "Five new skills teach any Claude to build on three.ws, and three standalone repos to install them from",
+ "summary": "Until now the skills we hand out taught Claude the 3D lanes and the wallet, and stopped at the platform itself: nothing explained how to create an agent, give it a capability, put a price on it, or hire someone else's. Five new skills cover exactly that, each written against the real endpoints with the real request bodies and the real failure responses: create an agent (body, custodial Solana wallet, persona, live page), author a four-file in-app skill bundle and test it, publish and price a skill per call in $THREE with metered free trials, hire another agent under per-call and daily spend caps, and connect Claude Code, Claude Desktop or any MCP client to the hosted servers starting with the free one. The pack is also published as three small standalone repos, so installing it no longer means cloning a 60-directory monorepo: everything, the crypto-free 3D subset, or the agent-economy set. The repos are generated from the same folders the platform ships, so a copy can never drift from the original.",
+ "tags": [
+ "feature",
+ "sdk",
+ "docs"
+ ],
+ "link": "/docs/agent-skills"
}
]
}
diff --git a/docs/agent-skills.md b/docs/agent-skills.md
index e7e501f86..767d2104c 100644
--- a/docs/agent-skills.md
+++ b/docs/agent-skills.md
@@ -27,6 +27,7 @@ Three categories:
| Category | Skills | Notes |
| --- | --- | --- |
| **3d/creative** | `find-3d-assets`, `generate-3d-model`, `create-3d-avatar`, `rig-a-model` | Text→GLB on the free lane, one-call rigged avatars, auto-rigging. **Cross-platform-safe**: zero coin/wallet/payment content, so this subset is reusable on non-Claude tracks (OpenAI, etc.). |
+| **platform/agents** | `create-a-three-ws-agent`, `build-an-agent-skill`, `sell-an-agent-skill`, `hire-an-agent`, `connect-three-ws-mcp` | Building ON three.ws: create an agent with a body, wallet and persona; author an in-app skill bundle; publish and price it in $THREE; hire another agent; wire a client to the MCP servers. Written against the public REST + MCP surfaces, so they work from any Claude surface. |
| **wallet/payments** | `authenticate-wallet`, `fund`, `send-usdc`, `trade`, `search-for-service`, `pay-for-service`, `monetize-service`, `query-onchain-data`, `x402`, `metamask-agent-*`, okx wallet/identity set | The x402 agent-economy set. Never bundle these on non-crypto tracks. |
| **intel/trading** | okx dex/defi market-data and execution set | Vendored partner skills (byte-identical to the vendor drop; categorized only in the pack manifest). |
@@ -86,7 +87,9 @@ option / skills directory the SDK exposes.
- **Self-contained**: a skill folder must work when copied out of this repo — no
relative imports into app internals.
- After adding or editing a skill, regenerate the manifest:
- `node scripts/build-skills-pack.mjs` (CI-style check: `--check`).
+ `npm run build:skills-pack` (CI-style check: `npm run check:skills-pack`, wired into
+ `npm run gate`). Category prose lives in one `CATEGORY_DESCRIPTIONS` map in that
+ script, so a new category cannot be counted while its description is missing.
### d) Downloaded from three.ws, no clone
@@ -128,6 +131,36 @@ bundle with no edit to the builder.
Published Markdown follows the repo's dash rule; the canonical files under
`.agents/skills/` are never rewritten.
+## The platform skills
+
+The set that turns a Claude session into a three.ws build surface. Each one is written
+against the public API (bearer key from
+[/dashboard/api](https://three.ws/dashboard/api)) and names the exact endpoint, body
+schema, and failure envelope, so the model does not have to guess.
+
+- **`create-a-three-ws-agent`**: forge a body, save it with
+ `POST /api/avatars/from-forge`, create the identity with `POST /api/agents` (the
+ custodial Solana wallet is minted in that request), then set the persona with
+ `PUT /api/agents/:id`. Returns the live `/agents/:id` page. Includes the
+ `409 identity_conflict` path, which is the integrity gate refusing a look-alike
+ identity rather than a bug to retry.
+- **`build-an-agent-skill`**: author the four-file in-app bundle
+ (`manifest.json` + `SKILL.md` + `tools.json` + `handlers.js`), the `ctx.*` handler
+ context, the Web Worker sandbox limits, the trust policy, and how to install and test
+ the bundle. Its worked example calls a real public API end to end.
+- **`sell-an-agent-skill`**: publish to the catalog (`POST /api/skills`), price per call,
+ price an agent's skill in $THREE (`PUT /api/monetization/prices`), metered trials and
+ pay-what-you-want (`PUT /api/agents/:id/skills-pricing`), the 250 bps author split, and
+ where the money lands.
+- **`hire-an-agent`**: the demand side. Browse `/api/agents/economy?view=offers`, take a
+ metered trial, buy over Solana Pay, or let one agent hire another with
+ `POST /api/agents/a2a-hire` under per-call and daily spend caps. Carries the mandatory
+ spend-confirmation card.
+- **`connect-three-ws-mcp`**: wire Claude Code, Claude Desktop, the Agent SDK, or any
+ JSON-RPC client to the hosted MCP servers, starting from the free one that needs no
+ account. Reads the live server directory at `/.well-known/mcp.json` rather than
+ trusting a hardcoded list.
+
## The 3D-creation skills
The platform's signature set, safe to reuse anywhere:
@@ -151,6 +184,43 @@ The three generation skills run free against the hosted studio endpoint
`https://three.ws/api/mcp-studio` (JSON-RPC `tools/call`), documented with runnable
`curl` examples inside each skill.
+## Standalone repos (install without cloning this one)
+
+Cloning a 60-directory monorepo to get a skill folder is a bad first experience, so the
+packs are also published as small standalone repos, each a complete Claude Code plugin
+marketplace of one plugin:
+
+| Repo | Contents | Who it is for |
+| --- | --- | --- |
+| `nirholas/three-ws-skills` | Every three.ws-origin skill (3D, platform, wallet/x402) | Anyone who wants the whole platform in one install |
+| `nirholas/three-ws-3d-skills` | The `3d/creative` cross-platform-safe subset | 3D users who want no wallet or payment content at all |
+| `nirholas/three-ws-agent-economy-skills` | `wallet/payments` + `platform/agents` | Builders monetizing agents and paying for services |
+
+```
+/plugin marketplace add nirholas/three-ws-3d-skills
+/plugin install three-ws-3d@three-ws-3d
+```
+
+**They are generated, never hand-maintained.** `npm run build:skill-repos` assembles each
+one into `.data/standalone-repos/<repo>/` (gitignored) straight from `.agents/skills/`,
+using the same `collectSkills()` the pack manifest uses, and writes the
+`.claude-plugin/marketplace.json`, `.claude-plugin/plugin.json`, `skills/`, a generated
+`README.md` with every trigger, the Apache-2.0 `LICENSE`, and a `.gitignore`. Because the
+copies are built on demand and never committed here, they cannot drift from the canonical
+folders.
+
+`npm run check:skill-repos` validates the repo specs against the pack without writing
+anything (it fails if a selector stops matching any skill, or a selected skill has no
+`SKILL.md`) and is wired into `npm run gate`, alongside `npm run check:skills-pack` which
+fails when `SKILLS.md` / `skills-pack.json` are stale.
+
+Vendored partner skills are deliberately excluded from every standalone repo: they belong
+to their publishers, and the `ops/production` skill is for maintainers of this repo rather
+than platform users.
+
+Publishing is owner-gated. The build prints the exact `git init` plus `gh repo create`
+command per repo when it finishes; nothing is pushed automatically.
+
## Related
- [STRUCTURE.md](../STRUCTURE.md) — where every surface lives
diff --git a/package.json b/package.json
index 55a3946a6..ad34d372f 100644
--- a/package.json
+++ b/package.json
@@ -160,6 +160,8 @@
"check:docs-search": "node scripts/build-docs-search-index.mjs --check",
"build:globe-geometry": "node scripts/build-globe-geometry.mjs",
"build:pages": "node scripts/build-page-index.mjs",
+ "build:prompt-library": "node scripts/build-prompt-library.mjs",
+ "check:prompt-library": "node scripts/build-prompt-library.mjs --check",
"hood:universe": "node scripts/build-hood-portfolios-universe.mjs --verbose",
"ship": "node packages/shipfeed/bin/shipfeed.mjs --local --changelog data/changelog.json --site https://three.ws",
"build:guards": "node scripts/build-guards.mjs",
@@ -238,7 +240,7 @@
"audit:route-shadowing": "node scripts/audit-route-shadowing.mjs",
"audit:handlers": "node scripts/audit-empty-handlers.mjs",
"audit:x402-catalog": "node scripts/audit-x402-catalog.mjs",
- "gate": "npm run check:conflicts && npm run check:claude && npm run check:vendored && npm run check:model-viewer && npm run check:gcloudignore && npm run check:fetch-timeouts && npm run check:tdz-bootstrap && npm run check:event && npm run check:cron-syntax && npm run check:home-matrix && npm run check:studio-openapi && npm run test:gate && npm run test:gate-3d && npm run audit:mcp && npm run audit:mcp-golden && npm run audit:mcp-safety && npm run audit:mcp-catalog && npm run audit:mcp-listing && npm run audit:routes && npm run audit:handlers && npm run audit:pages && npm run audit:links && npm run check:awesome && npm run audit:docs && npm run check:docs-freshness && npm run audit:upstreams && npm run check:tutorials && npm run audit:hidden-guard && npm run audit:inline-handlers && npm run audit:x402-catalog && npm run audit:tokens && npm run audit:states && npm run audit:motion-tokens && npm run audit:guards && npm run audit:tour-atlas && npm run check:ios-icons && npm run check:macos-icon && npm run check:apple-widget && npm run check:windows-widget && npm run check:announce && npm run i18n:home && npm run check:skills-seed && npm run check:openai-skills && npm run check:openai-fields && npm run audit:motion && npm run audit:tour-global && npm run check:doc-media && npm run check:images && npm run audit:route-shadowing",
+ "gate": "npm run check:conflicts && npm run check:claude && npm run check:vendored && npm run check:model-viewer && npm run check:gcloudignore && npm run check:fetch-timeouts && npm run check:tdz-bootstrap && npm run check:event && npm run check:cron-syntax && npm run check:home-matrix && npm run check:studio-openapi && npm run test:gate && npm run test:gate-3d && npm run audit:mcp && npm run audit:mcp-golden && npm run audit:mcp-safety && npm run audit:mcp-catalog && npm run audit:mcp-listing && npm run audit:routes && npm run audit:handlers && npm run audit:pages && npm run audit:links && npm run check:awesome && npm run check:prompt-library && npm run audit:docs && npm run check:docs-freshness && npm run audit:upstreams && npm run check:tutorials && npm run audit:hidden-guard && npm run audit:inline-handlers && npm run audit:x402-catalog && npm run audit:tokens && npm run audit:states && npm run audit:motion-tokens && npm run audit:guards && npm run audit:tour-atlas && npm run check:ios-icons && npm run check:macos-icon && npm run check:apple-widget && npm run check:windows-widget && npm run check:announce && npm run i18n:home && npm run check:skills-seed && npm run check:openai-skills && npm run check:skills-pack && npm run check:skill-repos && npm run check:openai-fields && npm run audit:motion && npm run audit:tour-global && npm run check:doc-media && npm run check:images && npm run audit:route-shadowing",
"test:gate-3d": "vitest run tests/glb-canonicalize.test.js tests/animation-retarget.test.js tests/animation-retarget-rest-pollution.test.js tests/viewer-framing.test.js",
"audit:mcp-golden": "node scripts/audit-mcp-golden.mjs",
"audit:mcp-safety": "node scripts/audit-mcp-safety.mjs",
@@ -293,7 +295,7 @@
"triage:gcp:deep": "node scripts/gcp-triage.mjs --deep --since 6h",
"snapshot": "node scripts/page-snapshot.mjs",
"build:news": "node scripts/build-news.mjs",
- "prebuild": "node scripts/copy-three-decoders.mjs && node scripts/copy-voice-models.mjs && (node scripts/build-news.mjs & node scripts/build-skill-metadata.mjs & node scripts/build-local-skill-packs.mjs & node scripts/build-discovery-cards.mjs & node scripts/build-guards.mjs & node scripts/build-atlas-index.mjs & node scripts/build-mcp-catalog.mjs & node scripts/build-awesome.mjs & npm run build:examples & npm run build:docs-search & npm run build:club-assets & npm run build:walk-environments & wait) && node scripts/inject-blog-seo.mjs --write && node scripts/inject-hidden-guard.mjs --write && node scripts/i18n-annotate.mjs --apply --pages=\"public/news/*.html\" && (node scripts/build-page-index.mjs && node scripts/audit-page-index.mjs --strict && node scripts/audit-empty-handlers.mjs && node scripts/audit-hidden-guard.mjs) && node scripts/inject-seo-meta.mjs --write && node scripts/inject-theme-boot.mjs --write",
+ "prebuild": "node scripts/copy-three-decoders.mjs && node scripts/copy-voice-models.mjs && (node scripts/build-news.mjs & node scripts/build-skill-metadata.mjs & node scripts/build-local-skill-packs.mjs & node scripts/build-discovery-cards.mjs & node scripts/build-guards.mjs & node scripts/build-atlas-index.mjs & node scripts/build-mcp-catalog.mjs & node scripts/build-awesome.mjs & node scripts/build-prompt-library.mjs & npm run build:examples & npm run build:docs-search & npm run build:club-assets & npm run build:walk-environments & wait) && node scripts/inject-blog-seo.mjs --write && node scripts/inject-hidden-guard.mjs --write && node scripts/i18n-annotate.mjs --apply --pages=\"public/news/*.html\" && (node scripts/build-page-index.mjs && node scripts/audit-page-index.mjs --strict && node scripts/audit-empty-handlers.mjs && node scripts/audit-hidden-guard.mjs) && node scripts/inject-seo-meta.mjs --write && node scripts/inject-theme-boot.mjs --write",
"seo:meta": "node scripts/inject-blog-seo.mjs --write && node scripts/build-page-index.mjs && node scripts/inject-seo-meta.mjs --write",
"build": "NODE_OPTIONS='--no-deprecation --max-old-space-size=6144' vite build && node scripts/strip-sw-from-embeds.mjs && node scripts/inject-tour-boot.mjs && node scripts/inject-atlas.mjs && node scripts/inject-inline-behaviors.mjs",
"build:wasm": "node scripts/build-wasm.mjs",
@@ -444,6 +446,10 @@
"seed:skills": "node scripts/seed-skills.js",
"build:openai-skills": "node scripts/build-openai-skills-bundle.mjs",
"check:openai-skills": "node scripts/build-openai-skills-bundle.mjs --check",
+ "build:skills-pack": "node scripts/build-skills-pack.mjs",
+ "check:skills-pack": "node scripts/build-skills-pack.mjs --check",
+ "build:skill-repos": "node scripts/build-standalone-skill-repos.mjs",
+ "check:skill-repos": "node scripts/build-standalone-skill-repos.mjs --check",
"build:openai-fields": "node scripts/build-openai-portal-fields.mjs",
"check:openai-fields": "node scripts/build-openai-portal-fields.mjs --check",
"build:skills-seed": "node scripts/build-skills-seed.mjs",
diff --git a/public/changelog-recent.json b/public/changelog-recent.json
index 01a0d5cc2..3357092cc 100644
--- a/public/changelog-recent.json
+++ b/public/changelog-recent.json
@@ -1,11 +1,11 @@
{
- "generated_at": "2026-09-20T05:24:40.698Z",
+ "generated_at": "2026-09-20T06:01:19.979Z",
"generated_by": "scripts/build-page-index.mjs from data/pages.json + data/changelog.json",
"site": {
"name": "three.ws",
"url": "https://three.ws"
},
- "total": 3718,
+ "total": 3722,
"complete": false,
"full_feed": "/changelog.json",
"entries": [
@@ -19,6 +19,26 @@
"launch"
]
},
+ {
+ "date": "2026-09-20",
+ "type": "launch",
+ "title": "Docs · The prompt library",
+ "summary": "How the three.ws prompt library works: the setup tiers behind each prompt, the lines worth keeping when you edit one, the JSON and plain-text feeds an agent can fetch, and how to add a prompt of your own.",
+ "link": "/docs/prompts",
+ "tags": [
+ "launch"
+ ]
+ },
+ {
+ "date": "2026-09-20",
+ "type": "launch",
+ "title": "Prompt Library",
+ "summary": "Copy-paste prompts for Claude and any AI agent: generate a 3D model or a rigged avatar, embed one on a site, validate a GLB, find or sell a paid API in the agent economy. Most of them need no account, no key and no setup.",
+ "link": "/prompts",
+ "tags": [
+ "launch"
+ ]
+ },
{
"date": "2026-09-20",
"type": "update",
@@ -29,6 +49,17 @@
"feature"
]
},
+ {
+ "date": "2026-09-20",
+ "type": "update",
+ "title": "A library of prompts you can paste straight into Claude",
+ "summary": "Knowing that three.ws has a free text-to-3D API is not the same as getting a rigged avatar out of it, and the paragraph that closes that gap is one nobody should have to write themselves. /prompts is 23 ready-made prompts for Claude and any other assistant: generate a model or a rigged avatar, search the CC0 catalog before generating anything, rig a GLB you already have, put a live avatar on your site, diagnose an embed that went dark, validate a model before it ships, find a paid API in the agent economy or sell your own. Each one names the real endpoint or tool, says what to do when a job comes back pending, and says what to hand back; the ones that can spend money are written to stop and show you the amount first. Most need no account, no key and no setup. Copy a prompt, open it directly in Claude with the text already in the box, or fetch the whole library as JSON or plain text.",
+ "link": "/prompts",
+ "tags": [
+ "feature",
+ "docs"
+ ]
+ },
{
"date": "2026-09-20",
"type": "update",
@@ -71,6 +102,16 @@
"improvement"
]
},
+ {
+ "date": "2026-09-20",
+ "type": "update",
+ "title": "The flagship post slot now gets flagship material",
+ "summary": "The @trythreews account publishes into three slots a day, one owned by each tier: proof of work at 04:00 UTC, a shipped feature at 12:00, a flagship at 20:00. The machine that drafts announcements from the backlog was not filling them that way. It never recorded a tier on anything it wrote, so every draft it produced was treated as a mid-tier feature and the 20:00 slot was left to whatever happened to be ready. It also dated the surfaces that need owner sign-off on their imagery into the best slot of every day, which pushed everything it could publish on its own weeks into the future. Announcements are now planned into the slot their own tier owns, the ones awaiting sign-off are listed separately instead of blocking the calendar, and six new announcements are queued for review.",
+ "link": "/changelog",
+ "tags": [
+ "improvement"
+ ]
+ },
{
"date": "2026-09-20",
"type": "update",
@@ -1573,49 +1614,6 @@
"tags": [
"improvement"
]
- },
- {
- "date": "2026-09-08",
- "type": "update",
- "title": "A GPU waking up now says so, instead of looking like a stuck progress bar",
- "summary": "Some of our 3D engines release their graphics card when nobody is using them, so the first request of a quiet spell has to boot one back up before any sculpting starts. That wait is normal and it ends, but several surfaces showed nothing but a spinning step while it happened, which reads as a hang. Now every place you can watch a model being built names it: the homepage forge, the Studio, the in-world item forge on /play, and the tools other apps drive us through all say a GPU is waking, how much of the boot is left, and that your job is already accepted and starts the second the worker answers. Every number comes from the generator itself, so nothing is a guessed timer. Two related fixes came out of it: the elapsed counter on /forge now reports how long your job has really been running rather than how long the tab has been open, so reopening the page mid-build no longer restarts the clock at zero; and the countdown now uses each engine's real boot budget instead of an estimate. The keep-warm schedule that holds those engines open during busy hours was also missing our highest-quality lane, which has the longest boot of the fleet.",
- "link": "/forge",
- "tags": [
- "improvement",
- "fix"
- ]
- },
- {
- "date": "2026-09-08",
- "type": "update",
- "title": "A live globe of what is happening on Earth, and every layer says how far back it can really see",
- "summary": "There is a new page at /globe: a 3D globe carrying eleven layers of open data at once. Armed conflict, mobilizations and sanctions are read out of the world news stream and placed where they happened; earthquakes, volcanoes and wildfires come from the USGS and NASA; cyclones, floods and drought from the UN and European Commission disaster system; national internet blackouts from Georgia Tech's outage project; and economic contraction from World Bank figures. Under all of it sits the geography that gives the rest meaning: overseas military bases, nuclear sites, and the nine maritime chokepoints world trade passes through, each one scored by how much armed activity the live feed puts within reach of it. Drag the globe or press F to flatten it into a map, click any point to read what it is and open the source it came from, and search the feed for a place or an actor. The whole view lives in the link, so the exact globe you are looking at is one you can send to someone. Two things it will not do: it will not quietly show you an hour of data under a label that says a week, because every layer prints the window it actually covered, and it will not go blank when a source goes down, because a layer that cannot be reached says so and the other ten keep working. Nothing here needs an account or an API key, and the same data is one call away at /api/globe/intel.",
- "link": "/globe",
- "tags": [
- "feature"
- ]
- },
- {
- "date": "2026-09-08",
- "type": "update",
- "title": "Agent Galaxy no longer strands you when the star map cannot be built",
- "summary": "When the embedding service behind the 3D agent map is unreachable, the page showed a sentence of explanation and nothing to click. It now offers the same agents as a browsable list plus a link to how the map is built. The keyboard experience was rebuilt too: every control on the page has a visible focus ring, and the search box and Money-Cam button drop out of the tab order while an overlay covers the map, so you can no longer tab into a search that has nothing to search. An agent card's Chat button now opens that agent's chat panel instead of repeating the View agent link.",
- "link": "/galaxy",
- "tags": [
- "fix",
- "improvement"
- ]
- },
- {
- "date": "2026-09-08",
- "type": "update",
- "title": "Agent Launches: the Tip button on every launch card actually works now",
- "summary": "Each card on the launches feed carries the launching agent's wallet, and the whole-card link to the coin profile was sitting on top of it: every tap on Tip, and every attempt to preview the wallet, opened the coin page instead. The wallet now sits above that link, so tipping and the wallet preview both work, on the feed and everywhere else the wallet badge appears. Keyboard and screen-reader use got the same pass: the Mainnet/Devnet switch responds to the arrow keys and says which feed it controls, the graduation bars announce which coin they belong to and how far along it is, the wallet's trust score and balance no longer read as unlabelled boxes while they load, and a page that found nothing on devnet now offers a button back to mainnet instead of only telling you to switch.",
- "link": "/launches",
- "tags": [
- "fix",
- "improvement"
- ]
}
]
}
diff --git a/public/changelog.json b/public/changelog.json
index 1c700b2dc..d01aed833 100644
--- a/public/changelog.json
+++ b/public/changelog.json
@@ -1,5 +1,5 @@
{
- "generated_at": "2026-09-20T05:24:40.658Z",
+ "generated_at": "2026-09-20T06:01:19.896Z",
"generated_by": "scripts/build-page-index.mjs from data/pages.json + data/changelog.json",
"site": {
"name": "three.ws",
@@ -16,6 +16,26 @@
"launch"
]
},
+ {
+ "date": "2026-09-20",
+ "type": "launch",
+ "title": "Docs · The prompt library",
+ "summary": "How the three.ws prompt library works: the setup tiers behind each prompt, the lines worth keeping when you edit one, the JSON and plain-text feeds an agent can fetch, and how to add a prompt of your own.",
+ "link": "/docs/prompts",
+ "tags": [
+ "launch"
+ ]
+ },
+ {
+ "date": "2026-09-20",
+ "type": "launch",
+ "title": "Prompt Library",
+ "summary": "Copy-paste prompts for Claude and any AI agent: generate a 3D model or a rigged avatar, embed one on a site, validate a GLB, find or sell a paid API in the agent economy. Most of them need no account, no key and no setup.",
+ "link": "/prompts",
+ "tags": [
+ "launch"
+ ]
+ },
{
"date": "2026-09-20",
"type": "update",
@@ -26,6 +46,17 @@
"feature"
]
},
+ {
+ "date": "2026-09-20",
+ "type": "update",
+ "title": "A library of prompts you can paste straight into Claude",
+ "summary": "Knowing that three.ws has a free text-to-3D API is not the same as getting a rigged avatar out of it, and the paragraph that closes that gap is one nobody should have to write themselves. /prompts is 23 ready-made prompts for Claude and any other assistant: generate a model or a rigged avatar, search the CC0 catalog before generating anything, rig a GLB you already have, put a live avatar on your site, diagnose an embed that went dark, validate a model before it ships, find a paid API in the agent economy or sell your own. Each one names the real endpoint or tool, says what to do when a job comes back pending, and says what to hand back; the ones that can spend money are written to stop and show you the amount first. Most need no account, no key and no setup. Copy a prompt, open it directly in Claude with the text already in the box, or fetch the whole library as JSON or plain text.",
+ "link": "/prompts",
+ "tags": [
+ "feature",
+ "docs"
+ ]
+ },
{
"date": "2026-09-20",
"type": "update",
@@ -68,6 +99,16 @@
"improvement"
]
},
+ {
+ "date": "2026-09-20",
+ "type": "update",
+ "title": "The flagship post slot now gets flagship material",
+ "summary": "The @trythreews account publishes into three slots a day, one owned by each tier: proof of work at 04:00 UTC, a shipped feature at 12:00, a flagship at 20:00. The machine that drafts announcements from the backlog was not filling them that way. It never recorded a tier on anything it wrote, so every draft it produced was treated as a mid-tier feature and the 20:00 slot was left to whatever happened to be ready. It also dated the surfaces that need owner sign-off on their imagery into the best slot of every day, which pushed everything it could publish on its own weeks into the future. Announcements are now planned into the slot their own tier owns, the ones awaiting sign-off are listed separately instead of blocking the calendar, and six new announcements are queued for review.",
+ "link": "/changelog",
+ "tags": [
+ "improvement"
+ ]
+ },
{
"date": "2026-09-20",
"type": "update",
diff --git a/public/changelog.xml b/public/changelog.xml
index 12e3e6742..aec647dc9 100644
--- a/public/changelog.xml
+++ b/public/changelog.xml
@@ -14,6 +14,22 @@
<category>launch</category>
<description>A bonding-curve launchpad priced in $THREE: every coin launched for a 3D agent is bought with $THREE, creators earn their fees in $THREE, and each graduation locks the $THREE it raised in a pool nobody can withdraw. Launch a coin or trade the live curves.</description>
</item>
+ <item>
+ <title>Docs · The prompt library</title>
+ <link>https://three.ws/docs/prompts</link>
+ <guid isPermaLink="false">2026-09-20:Docs · The prompt library</guid>
+ <pubDate>Sun, 20 Sep 2026 12:00:00 GMT</pubDate>
+ <category>launch</category>
+ <description>How the three.ws prompt library works: the setup tiers behind each prompt, the lines worth keeping when you edit one, the JSON and plain-text feeds an agent can fetch, and how to add a prompt of your own.</description>
+ </item>
+ <item>
+ <title>Prompt Library</title>
+ <link>https://three.ws/prompts</link>
+ <guid isPermaLink="false">2026-09-20:Prompt Library</guid>
+ <pubDate>Sun, 20 Sep 2026 12:00:00 GMT</pubDate>
+ <category>launch</category>
+ <description>Copy-paste prompts for Claude and any AI agent: generate a 3D model or a rigged avatar, embed one on a site, validate a GLB, find or sell a paid API in the agent economy. Most of them need no account, no key and no setup.</description>
+ </item>
<item>
<title>A launchpad where every coin is bought with $THREE</title>
<link>https://three.ws/three-launchpad</link>
@@ -22,6 +38,14 @@
<category>feature</category>
<description>The three.ws bonding-curve launchpad is now priced in $THREE instead of SOL. A coin launched there for a 3D agent can only be bought with $THREE, its creator earns half of every trading fee in $THREE, and when it graduates, the roughly 12.3 million $THREE it raised is locked in its pool permanently. The new launchpad page shows the live curves with buy and sell straight from your wallet. The curve has been verified against Solana mainnet and opens for launches as soon as its settings are published on-chain.</description>
</item>
+ <item>
+ <title>A library of prompts you can paste straight into Claude</title>
+ <link>https://three.ws/prompts</link>
+ <guid isPermaLink="false">2026-09-20:A library of prompts you can paste straight into Claude</guid>
+ <pubDate>Sun, 20 Sep 2026 12:00:00 GMT</pubDate>
+ <category>feature</category>
+ <description>Knowing that three.ws has a free text-to-3D API is not the same as getting a rigged avatar out of it, and the paragraph that closes that gap is one nobody should have to write themselves. /prompts is 23 ready-made prompts for Claude and any other assistant: generate a model or a rigged avatar, search the CC0 catalog before generating anything, rig a GLB you already have, put a live avatar on your site, diagnose an embed that went dark, validate a model before it ships, find a paid API in the agent economy or sell your own. Each one names the real endpoint or tool, says what to do when a job comes back pending, and says what to hand back; the ones that can spend money are written to stop and show you the amount first. Most need no account, no key and no setup. Copy a prompt, open it directly in Claude with the text already in the box, or fetch the whole library as JSON or plain text.</description>
+ </item>
<item>
<title>Agent reputation on Base and other EVM chains now shows real on-chain reviews</title>
<link>https://three.ws/changelog</link>
@@ -54,6 +78,14 @@
<category>improvement</category>
<description>The reviewed content queue that runs the @trythreews account moved to three posts a day, eight hours apart, on every day of the week including weekends. It used to hold its flagship slot for weekdays and pack all three posts into an eight-hour afternoon window, which meant a weekend could only ever carry two. Three posts went out under the new cadence today: the $THREE token MCP server, Forge Max, and the free object library. The Forge Max post also gained a check that proves the high-quality tier is a real, gated lane before it can be published, rather than only proving its page loads.</description>
</item>
+ <item>
+ <title>The flagship post slot now gets flagship material</title>
+ <link>https://three.ws/changelog</link>
+ <guid isPermaLink="false">2026-09-20:The flagship post slot now gets flagship material</guid>
+ <pubDate>Sun, 20 Sep 2026 12:00:00 GMT</pubDate>
+ <category>improvement</category>
+ <description>The @trythreews account publishes into three slots a day, one owned by each tier: proof of work at 04:00 UTC, a shipped feature at 12:00, a flagship at 20:00. The machine that drafts announcements from the backlog was not filling them that way. It never recorded a tier on anything it wrote, so every draft it produced was treated as a mid-tier feature and the 20:00 slot was left to whatever happened to be ready. It also dated the surfaces that need owner sign-off on their imagery into the best slot of every day, which pushed everything it could publish on its own weeks into the future. Announcements are now planned into the slot their own tier owns, the ones awaiting sign-off are listed separately instead of blocking the calendar, and six new announcements are queued for review.</description>
+ </item>
<item>
<title>Two Uniswap v4 hooks: wearable 3D items as coins, and fees that reward agent reputation</title>
<link>https://three.ws/changelog</link>
diff --git a/public/features.json b/public/features.json
index 40c8ac04d..e20301a51 100644
--- a/public/features.json
+++ b/public/features.json
@@ -1,5 +1,5 @@
{
- "generated_at": "2026-09-20T05:24:40.639Z",
+ "generated_at": "2026-09-20T06:01:19.858Z",
"generated_by": "scripts/build-page-index.mjs from data/pages.json",
"site": {
"name": "three.ws",
@@ -653,6 +653,16 @@
"tags": [],
"showcase": false
},
+ {
+ "path": "/prompts",
+ "title": "Prompt Library",
+ "description": "Copy-paste prompts for Claude and any AI agent: generate a 3D model or a rigged avatar, embed one on a site, validate a GLB, find or sell a paid API in the agent economy. Most of them need no account, no key and no setup.",
+ "added": "2026-09-20",
+ "auth": null,
+ "indexable": true,
+ "tags": [],
+ "showcase": true
+ },
{
"path": "/start",
"title": "Get Started",
@@ -4788,6 +4798,16 @@
"tags": [],
"showcase": false
},
+ {
+ "path": "/docs/prompts",
+ "title": "Docs · The prompt library",
+ "description": "How the three.ws prompt library works: the setup tiers behind each prompt, the lines worth keeping when you edit one, the JSON and plain-text feeds an agent can fetch, and how to add a prompt of your own.",
+ "added": "2026-09-20",
+ "auth": null,
+ "indexable": true,
+ "tags": [],
+ "showcase": false
+ },
{
"path": "/docs/mcp-studio",
"title": "Docs · 3D Studio MCP (free)",
diff --git a/public/llms-full.txt b/public/llms-full.txt
index 68a0199c5..41b654c61 100644
--- a/public/llms-full.txt
+++ b/public/llms-full.txt
@@ -402,6 +402,12 @@ URL: https://three.ws/agora
A watchable 3D world where AI agent and human citizens live, work, and earn $THREE. Walk the square, inspect any citizen's passport, and watch the economy come alive.
+### Prompt Library
+
+URL: https://three.ws/prompts
+
+Copy-paste prompts for Claude and any AI agent: generate a 3D model or a rigged avatar, embed one on a site, validate a GLB, find or sell a paid API in the agent economy. Most of them need no account, no key and no setup.
+
### Get Started
URL: https://three.ws/start
@@ -2920,6 +2926,12 @@ URL: https://three.ws/docs/vscode
The VS Code extension that renders .glb and .gltf files in an editor tab, reports on them, generates and rigs new models on the free lane, and writes a pinned <agent-3d> embed.
+### Docs · The prompt library
+
+URL: https://three.ws/docs/prompts
+
+How the three.ws prompt library works: the setup tiers behind each prompt, the lines worth keeping when you edit one, the JSON and plain-text feeds an agent can fetch, and how to add a prompt of your own.
+
### Docs · 3D Studio MCP (free)
URL: https://three.ws/docs/mcp-studio
diff --git a/public/llms.txt b/public/llms.txt
index 97c6b900f..8d2d9ef68 100644
--- a/public/llms.txt
+++ b/public/llms.txt
@@ -93,6 +93,7 @@ Create and customize an agent.
- [Assistant widget](https://three.ws/assistant): Put a 3D avatar assistant on any website with one script tag. A floating launcher opens a real animated avatar, against your page, a color, or a gradient, with a chatbot mode (free models or your own Groq/OpenRouter key) and a speak mode where the avatar says whatever you type out loud in a speech bubble.
- [Embed Doctor](https://three.ws/embed-doctor): Find out why your 3D agent embed is not showing up. Paste your page URL and we load it in a real browser, watch the embed try to boot, and name the exact line to change: a Content-Security-Policy that dropped the runtime, a container with no height, a private agent id, WebGL turned off. Works on a snippet too, before you deploy it.
- [Agora: the Commons](https://three.ws/agora): A watchable 3D world where AI agent and human citizens live, work, and earn $THREE. Walk the square, inspect any citizen's passport, and watch the economy come alive.
+- [Prompt Library](https://three.ws/prompts): Copy-paste prompts for Claude and any AI agent: generate a 3D model or a rigged avatar, embed one on a site, validate a GLB, find or sell a paid API in the agent economy. Most of them need no account, no key and no setup.
- [Create](https://three.ws/create): The front door for everything you can create on three.ws: build an AI agent, make a 3D avatar (from a photo, from scratch, from a text prompt, or a file), generate a standalone 3D model, or launch a token world.
- [Agent Genome: breed two agents](https://three.ws/genome): Breed two AI agents into a provably-inherited offspring. The child inherits a recombination of both parents' brain, voice, body, and on-chain skill licenses: each breeding event seed-recorded so the lineage is re-derivable and forgery-detectable, with a verifiable family tree on every parent and child.
- [Instant Agent Genesis](https://three.ws/genesis): A prompt or a selfie becomes a rigged 3D AI agent with its own custodial Solana + EVM wallet and a verifiable on-chain identity: in under a minute, owned by you.
@@ -502,6 +503,7 @@ Docs, tutorials, and reference.
- [Docs · MCP](https://three.ws/docs/mcp): Expose your agent as an MCP server for Claude, ChatGPT, and other clients.
- [Docs · Solana Memo Media MCP](https://three.ws/docs/mcp-solana-memo-media): Decode validated image data embedded in Solana Memo transactions and return safe inline MCP images with provenance.
- [Docs · three.ws in VS Code](https://three.ws/docs/vscode): The VS Code extension that renders .glb and .gltf files in an editor tab, reports on them, generates and rigs new models on the free lane, and writes a pinned <agent-3d> embed.
+- [Docs · The prompt library](https://three.ws/docs/prompts): How the three.ws prompt library works: the setup tiers behind each prompt, the lines worth keeping when you edit one, the JSON and plain-text feeds an agent can fetch, and how to add a prompt of your own.
- [Docs · 3D Studio MCP (free)](https://three.ws/docs/mcp-studio): The free, no-auth MCP server behind the ChatGPT 3D Studio app: text and image to 3D, rigged avatars, conversational refinement, and living agent personas.
- [Docs · AR in ChatGPT](https://three.ws/docs/chatgpt-ar): How a sentence typed into ChatGPT becomes a 3D model standing in your room: the free generation lane, the arUrl contract, the device-aware AR launcher, living avatars, and link unfurls.
- [Docs · Scenes MCP](https://three.ws/docs/mcp-scenes): Speak a placed 3D diorama into being from one sentence, then browse the gallery.
diff --git a/public/nav-data.js b/public/nav-data.js
index 91ba93453..96798b87a 100644
--- a/public/nav-data.js
+++ b/public/nav-data.js
@@ -750,6 +750,11 @@ export const NAV_GROUPS = [
{ title: 'Tutorials', href: '/tutorials', desc: 'Step-by-step guides' },
{ title: 'Examples', href: '/examples', desc: 'Runnable copy-paste code' },
{ title: 'Cookbook', href: '/cookbook', desc: 'Recipes you download and run' },
+ {
+ title: 'Prompt Library',
+ href: '/prompts',
+ desc: 'Prompts you paste into Claude to build with three.ws',
+ },
{
title: 'Awesome 3D Agents',
href: '/awesome',
diff --git a/public/sitemap/index.html b/public/sitemap/index.html
index 507feae87..c5dc2ad97 100644
--- a/public/sitemap/index.html
+++ b/public/sitemap/index.html
@@ -96,7 +96,7 @@
<main class="sm-wrap">
<div class="sm-hero">
<h1>Sitemap</h1>
- <p>All 943 pages on three.ws, grouped by purpose. Looking for the machine-readable versions?</p>
+ <p>All 945 pages on three.ws, grouped by purpose. Looking for the machine-readable versions?</p>
<div class="sm-formats">
<a href="/sitemap.xml"><code>sitemap.xml</code> · for search engines</a>
<a href="/llms.txt"><code>llms.txt</code> · for AI agents</a>
@@ -108,7 +108,7 @@
</div>
<div class="sm-filter">
<svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" aria-hidden="true"><circle cx="11" cy="11" r="7"/><path d="m21 21-4.3-4.3"/></svg>
- <input id="sm-filter-input" type="search" placeholder="Filter 943 pages by name, path, or description…" aria-label="Filter pages" autocomplete="off" spellcheck="false" />
+ <input id="sm-filter-input" type="search" placeholder="Filter 945 pages by name, path, or description…" aria-label="Filter pages" autocomplete="off" spellcheck="false" />
<kbd id="sm-filter-kbd" aria-hidden="true">/</kbd>
</div>
<p class="sm-filter-count" role="status" aria-live="polite"><span id="sm-filter-count"></span><span id="sm-filter-hint" aria-hidden="true"></span></p>
@@ -116,6 +116,14 @@
<h2 id="sm-new-title">Newest<a class="sm-new-more" href="/changelog">full changelog &rarr;</a></h2>
<p class="sm-section-desc">The 9 most recently launched pages, straight to the live surface.</p>
<ul class="sm-list">
+ <li>
+ <a href="/prompts">
+ <span class="sm-new-date">Sep 20, 2026</span>
+ <span class="sm-title">Prompt Library</span>
+ <span class="sm-path">/prompts</span>
+ <span class="sm-desc">Copy-paste prompts for Claude and any AI agent: generate a 3D model or a rigged avatar, embed one on a site, validate a GLB, find or sell a paid API in the agent economy. Most of them need no account, no key and no setup.</span>
+ </a>
+ </li>
<li>
<a href="/three-launchpad">
<span class="sm-new-date">Sep 20, 2026</span>
@@ -124,6 +132,14 @@
<span class="sm-desc">A bonding-curve launchpad priced in $THREE: every coin launched for a 3D agent is bought with $THREE, creators earn their fees in $THREE, and each graduation locks the $THREE it raised in a pool nobody can withdraw. Launch a coin or trade the live curves.</span>
</a>
</li>
+ <li>
+ <a href="/docs/prompts">
+ <span class="sm-new-date">Sep 20, 2026</span>
+ <span class="sm-title">Docs · The prompt library</span>
+ <span class="sm-path">/docs/prompts</span>
+ <span class="sm-desc">How the three.ws prompt library works: the setup tiers behind each prompt, the lines worth keeping when you edit one, the JSON and plain-text feeds an agent can fetch, and how to add a prompt of your own.</span>
+ </a>
+ </li>
<li>
<a href="/docs/doc-freshness">
<span class="sm-new-date">Sep 17, 2026</span>
@@ -172,22 +188,6 @@
<span class="sm-desc">How three.ws/launch launches a pump.fun coin for a 3D agent: agent-linked metadata, the 1% dev-buy fee, v0 lookup-table and Solana transaction v1 formats, claiming creator rewards on three.ws, and the API behind it.</span>
</a>
</li>
- <li>
- <a href="/contributors">
- <span class="sm-new-date">Sep 15, 2026</span>
- <span class="sm-title">Contributors</span>
- <span class="sm-path">/contributors</span>
- <span class="sm-desc">A living thank-you to the developers, issue reporters, and community members improving the open-source three.ws platform.</span>
- </a>
- </li>
- <li>
- <a href="/atomic">
- <span class="sm-new-date">Sep 15, 2026</span>
- <span class="sm-title">Atomic - Solana V1 Inspector</span>
- <span class="sm-path">/atomic</span>
- <span class="sm-desc">A live Solana Transaction V1 observatory and pre-sign inspector. Paste a mainnet signature or base64 wire transaction to see exact bytes, resource caps, compute use, and sponsor safety.</span>
- </a>
- </li>
</ul>
</section>
<nav class="sm-toc" aria-label="Sections">
@@ -634,7 +634,7 @@
<section class="sm-section" id="build">
<header>
- <h2>Build<span class="sm-count" data-count>78</span></h2>
+ <h2>Build<span class="sm-count" data-count>79</span></h2>
<p class="sm-section-desc">Create and customize an agent.</p>
</header>
<ul class="sm-list">
@@ -659,6 +659,13 @@
<span class="sm-desc">A watchable 3D world where AI agent and human citizens live, work, and earn $THREE. Walk the square, inspect any citizen's passport, and watch the economy come alive.</span>
</a>
</li>
+ <li>
+ <a href="/prompts">
+ <span class="sm-title">Prompt Library</span>
+ <span class="sm-path">/prompts</span>
+ <span class="sm-desc">Copy-paste prompts for Claude and any AI agent: generate a 3D model or a rigged avatar, embed one on a site, validate a GLB, find or sell a paid API in the agent economy. Most of them need no account, no key and no setup.</span>
+ </a>
+ </li>
<li>
<a href="/start">
<span class="sm-title">Get Started<span class="sm-badge sm-badge-internal">internal</span></span>
@@ -2590,7 +2597,7 @@
<section class="sm-section" id="learn">
<header>
- <h2>Learn<span class="sm-count" data-count>436</span></h2>
+ <h2>Learn<span class="sm-count" data-count>437</span></h2>
<p class="sm-section-desc">Docs, tutorials, and reference.</p>
</header>
<ul class="sm-list">
@@ -3574,6 +3581,13 @@
<span class="sm-desc">The VS Code extension that renders .glb and .gltf files in an editor tab, reports on them, generates and rigs new models on the free lane, and writes a pinned &lt;agent-3d&gt; embed.</span>
</a>
</li>
+ <li>
+ <a href="/docs/prompts">
+ <span class="sm-title">Docs · The prompt library</span>
+ <span class="sm-path">/docs/prompts</span>
+ <span class="sm-desc">How the three.ws prompt library works: the setup tiers behind each prompt, the lines worth keeping when you edit one, the JSON and plain-text feeds an agent can fetch, and how to add a prompt of your own.</span>
+ </a>
+ </li>
<li>
<a href="/docs/mcp-studio">
<span class="sm-title">Docs · 3D Studio MCP (free)</span>
diff --git a/vercel.json b/vercel.json
index f6dacf2a7..f7aea978a 100644
--- a/vercel.json
+++ b/vercel.json
@@ -1362,6 +1362,10 @@
"src": "/hacks/?",
"dest": "/hacks.html"
},
+ {
+ "src": "/derivative/([a-z0-9_-]{1,60})/([A-Za-z0-9._:~-]{1,48})/?",
+ "dest": "/derivative.html"
+ },
{
"src": "/exchange/([a-z0-9_-]{1,60})/?",
"dest": "/exchange.html"
@@ -5749,6 +5753,10 @@
"src": "/awesome",
"dest": "/awesome.html"
},
+ {
+ "src": "/prompts",
+ "dest": "/prompts.html"
+ },
{
"src": "/awesome/",
"dest": "/awesome.html"
diff --git a/vite.config.js b/vite.config.js
index f641baaa4..cc0bfe296 100644
--- a/vite.config.js
+++ b/vite.config.js
@@ -670,6 +670,7 @@ const appConfig = {
'agent-identities': resolve(__dirname, 'pages/agent-identities.html'),
'mcp-tools': resolve(__dirname, 'pages/mcp-tools.html'),
awesome: resolve(__dirname, 'pages/awesome.html'),
+ prompts: resolve(__dirname, 'pages/prompts.html'),
'render-lab': resolve(__dirname, 'pages/render-lab.html'),
holo: resolve(__dirname, 'pages/holo.html'),
bundles: resolve(__dirname, 'pages/bundles.html'),
@@ -882,6 +883,7 @@ const appConfig = {
categories: resolve(__dirname, 'pages/categories.html'),
exchanges: resolve(__dirname, 'pages/exchanges.html'),
derivatives: resolve(__dirname, 'pages/derivatives.html'),
+ derivative: resolve(__dirname, 'pages/derivative.html'),
converter: resolve(__dirname, 'pages/converter.html'),
defi: resolve(__dirname, 'pages/defi.html'),
chains: resolve(__dirname, 'pages/chains.html'),
@@ -1443,6 +1445,8 @@ const appConfig = {
'/agent-identities/': resolve(root, 'pages/agent-identities.html'),
'/awesome': resolve(root, 'pages/awesome.html'),
'/awesome/': resolve(root, 'pages/awesome.html'),
+ '/prompts': resolve(root, 'pages/prompts.html'),
+ '/prompts/': resolve(root, 'pages/prompts.html'),
// Production routes /app to the Next viewer and leaves app.html
// reachable only at /app-classic (vercel.json). Dev has to mirror
// that, or every /app change gets exercised against the wrong page.
@@ -2379,6 +2383,14 @@ const appConfig = {
// matching api/vanity/drops.js's id format)
else if (!filePath && /^\/drop\/[0-9a-f]{24}\/?$/.test(path))
filePath = resolve(root, 'pages/drop.html');
+ // /derivative/:venue/:symbol → one perpetual contract. The symbol
+ // segment carries the venue's own symbol with any '/' folded to
+ // '~' (see src/shared/derivative-slug.js). Mirrors vercel.json.
+ else if (
+ !filePath &&
+ /^\/derivative\/[a-z0-9_-]{1,60}\/[A-Za-z0-9._:~-]{1,48}\/?$/i.test(path)
+ )
+ filePath = resolve(root, 'pages/derivative.html');
// /exchange/:id → exchange detail page (CoinGecko exchange slug)
else if (!filePath && /^\/exchange\/[a-z0-9_-]{1,60}\/?$/i.test(path))
filePath = resolve(root, 'pages/exchange.html');