Garry's Opinionated OpenClaw/Hermes Agent Brain
TypeScript
name: skill-creator version: 1.0.0 description: | Create new skills following the GBrain conformance standard. Generates SKILL.md with frontmatter, Contract, Phases, Output Format, and Anti-Patterns. Checks MECE against existing skills. Updates manifest and resolver. triggers: - "create a skill" - "new skill" - "improve this skill" tools: - search - list_pages mutating: true when_to_use: "Use when the user asks: "create a skill", "new skill", "improve this skill"."
Skill Creator
Contract
This skill guarantees:
- New skill follows conformance standard (frontmatter + required sections)
- MECE check: no overlap with existing skills' triggers
- Manifest.json updated
- RESOLVER.md updated with routing entry
- Skill passes conformance tests (
bun test test/skills-conformance.test.ts) andbun run check:skill-health(no drift from the CLI, SKILL.md within 16 KB, description within 1 KB) - Improving a skill follows the update ladder (CONTRIBUTING.md, "Changing a skill"): fix it below the skill first, then edit the existing line instead of appending
Phases
- Identify the gap. What capability is missing? What user intent has no skill?
- MECE check. Review
skills/manifest.jsonandskills/RESOLVER.md. Does any existing skill already cover this? If so, extend it instead of creating a new one. - Create SKILL.md. Use this template:
---
name: {skill-name}
version: 1.0.0
description: |
{One paragraph describing what the skill does and when to use it.}
triggers:
- "{trigger phrase 1}"
- "{trigger phrase 2}"
tools:
- {tool1}
- {tool2}
mutating: {true|false}
---
# {Skill Title}
## Contract
{What this skill guarantees — 3-5 bullet points}
## Phases
{Numbered workflow steps}
## Output Format
{What good output looks like}
## When it fails
Follow the [agent operator protocol](../conventions/agent-operator-protocol.md) for any gbrain error `code`, exit code, `[AGENT]` block or notice block. Specific to this skill:
{2-5 concrete failures this skill hits — error codes, refusals, notices — and what to do and tell the user}
## Anti-Patterns
{What NOT to do — 3-5 items}
## Tools Used
{GBrain operations used, with descriptions}
- Add to manifest. Update
skills/manifest.jsonwith name, path, description. - Add to resolver. Update
skills/RESOLVER.mdwith routing entry in the appropriate category. - Verify. Run
bun test test/skills-conformance.test.tsto confirm the new skill passes.
Output Format
New skills/{name}/SKILL.md file + updated manifest + updated resolver.
When it fails
Follow the agent operator protocol for any gbrain error code, exit code, [AGENT] block or notice block. Specific to this skill:
bun test test/skills-conformance.test.tsfails: the new SKILL.md lacks a required section (Contract, Anti-Patterns, Output Format, When it fails) or frontmatter; add it and re-run.gbrain check-resolvablereports the skill unreachable: add the RESOLVER row in a fitting category, then re-run.
Anti-Patterns
- Creating a skill that overlaps with an existing one (violates MECE)
- Skipping the MECE check against existing skills
- Creating a skill without triggers in frontmatter
- Not updating manifest.json and RESOLVER.md
- Creating a skill without an Anti-Patterns section