Create, Evaluate, and Connect AI Skills
Python ai-agentsai-skillsartificial-intelligenceknowledge-graphlarge-language-modelsnatural-language-processingopenkgskillnetskills
feat: add MiniMax provider support and fix model default bug
Jiang Chen79112d81e63c
diff --git a/README.md b/README.mdindex f9ad662..bcc60d4 100644--- a/README.md+++ b/README.md@@ -35,7 +35,6 @@ Search 300,000+ community skills · One-line install · Auto-create from repos /-## 📢 News- **🔌 [2026-03-12] SkillNet MCP Server Released!** — We've launched the Model Context Protocol (MCP) integration (maintained by [CycleChain](https://github.com/CycleChain), special thanks for this great contribution!). [Learn more →](#-model-context-protocol-mcp-integration)@@ -168,6 +167,7 @@ from skillnet_ai import SkillNetClientclient = SkillNetClient(api_key="sk-...", # Required for create / evaluate / analyze+ # provider="minimax", # Optional: "openai" (default) or "minimax"# base_url="...", # Optional: custom LLM endpoint# github_token="ghp-..." # Optional: for private repos)@@ -250,6 +250,8 @@ The CLI ships with `pip install skillnet-ai` and offers the same features with r| `evaluate` | Quality report | `skillnet evaluate ./my_skill` || `analyze` | Relationship graph | `skillnet analyze ./my_skills` |+> All LLM-powered commands (`create`, `evaluate`, `analyze`) support `--provider` (e.g. `--provider minimax`) and `--model` flags. See [Using MiniMax as LLM Provider](#using-minimax-as-llm-provider) for details.+>> Use `skillnet <command> --help` for full options.### Search@@ -285,6 +287,9 @@ skillnet create --office ./docs/guide.pdf# From promptskillnet create --prompt "A skill for extracting tables from images"++# Use a specific provider+skillnet create --provider minimax --prompt "A skill for web scraping"```### Evaluate@@ -293,6 +298,7 @@ skillnet create --prompt "A skill for extracting tables from images"skillnet evaluate https://github.com/anthropics/skills/tree/main/skills/algorithmic-artskillnet evaluate ./my_skills/web_searchskillnet evaluate ./my_skills/tool --category "Development" --model gpt-4o+skillnet evaluate --provider minimax ./my_skill```### Analyze@@ -301,6 +307,7 @@ skillnet evaluate ./my_skills/tool --category "Development" --model gpt-4oskillnet analyze ./my_agent_skillsskillnet analyze ./my_agent_skills --no-save # print only, don't write fileskillnet analyze ./my_agent_skills --model gpt-4o+skillnet analyze --provider minimax ./my_agent_skills```---@@ -309,14 +316,14 @@ skillnet analyze ./my_agent_skills --model gpt-4o### Environment Variables-| Variable | Required For | Default |-| :--------------- | :--------------------------------- | :-------------------------- |-| `API_KEY` | `create` · `evaluate` · `analyze` | — |-| `MINIMAX_API_KEY`| MiniMax provider (auto-detected) | — |-| `BASE_URL` | Custom LLM endpoint | `https://api.openai.com/v1` |-| `GITHUB_TOKEN` | Private repos / higher rate limits | — |-| `SKILLNET_MODEL` | Default LLM model for all commands | `gpt-4o` |-| `GITHUB_MIRROR` | Faster downloads in restricted networks | — |+| Variable | Required For | Default |+| :---------------- | :-------------------------------------- | :-------------------------- |+| `API_KEY` | `create` · `evaluate` · `analyze` | — |+| `MINIMAX_API_KEY` | MiniMax provider (auto-detected) | — |+| `BASE_URL` | Custom LLM endpoint | `https://api.openai.com/v1` |+| `GITHUB_TOKEN` | Private repos / higher rate limits | — |+| `SKILLNET_MODEL` | Default LLM model for all commands | `gpt-4o` |+| `GITHUB_MIRROR` | Faster downloads in restricted networks | — |> `search` and `download` (public repos) work without any credentials.>@@ -376,10 +383,10 @@ client.create(prompt="A skill for PDF parsing", output_dir="./skills")client.evaluate(target="./skills/pdf-parser")```-| Provider | Default Model | Base URL | API Key Env |-| :------- | :--------------- | :---------------------------- | :----------------- |-| `openai` | `gpt-4o` | `https://api.openai.com/v1` | `API_KEY` |-| `minimax`| `MiniMax-M2.7` | `https://api.minimax.io/v1` | `MINIMAX_API_KEY` |+| Provider | Default Model | Base URL | API Key Env |+| :-------- | :------------- | :-------------------------- | :---------------- |+| `openai` | `gpt-4o` | `https://api.openai.com/v1` | `API_KEY` |+| `minimax` | `MiniMax-M2.7` | `https://api.minimax.io/v1` | `MINIMAX_API_KEY` |---@@ -389,7 +396,6 @@ A complete end-to-end demo showing how an AI Agent uses SkillNet to autonomously-<table><tr><td>1️⃣</td><td><b>Task</b></td><td>User provides a goal: "Analyze scRNA-seq data to find cancer targets"</td></tr><tr><td>2️⃣</td><td><b>Plan</b></td><td>Agent decomposes into: Data → Mechanism → Validation → Report</td></tr>@@ -434,7 +440,7 @@ Install the skillnet skill from ClawHub.### ⚙️ Configuration-The same three parameters (`API_KEY`, `BASE_URL`, `GITHUB_TOKEN`) apply here — see [Configuration](#configuration) for details.+The same environment variables (`API_KEY`, `BASE_URL`, `GITHUB_TOKEN`, `MINIMAX_API_KEY`) apply here — see [Configuration](#configuration) for details.In OpenClaw, you can pre-configure them in `openclaw.json` so the agent uses them silently — no prompts, no interruptions. If not configured, the agent only asks when a command actually needs the value, injects it for that single call, and never pollutes the global environment.@@ -486,6 +492,7 @@ It empowers agents to autonomously search, download, create, and evaluate 300,00### Installation Options#### 1. Source Build (Node.js & Python)+Ideal for users who want to run the server locally with existing dependencies.```bash@@ -507,6 +514,7 @@ docker pull fmdogancan/skillnet-mcp:latestAdd the following to your `claude_desktop_config.json`:#### Option A: Docker (Recommended)+```json{"mcpServers": {@@ -549,8 +557,8 @@ _(Then, replace `fmdogancan/skillnet-mcp:latest` with `skillnet-mcp-local` in th### Supported Environment Variables-* `API_KEY`: Your API key-* `GITHUB_TOKEN`: GitHub token for private repositories+- `API_KEY`: Your API key+- `GITHUB_TOKEN`: GitHub token for private repositories---@@ -572,16 +580,16 @@ You can also [open an Issue](https://github.com/zjunlp/SkillNet/issues) to repor## 📚 Citation-If you find this work useful, please kindly ⭐ the repo and cite our paper!+If you find this work useful, please kindly ⭐ the repo and cite our paper!```bibtex@misc{liang2026skillnetcreateevaluateconnect,- title={SkillNet: Create, Evaluate, and Connect AI Skills},+ title={SkillNet: Create, Evaluate, and Connect AI Skills},author={Yuan Liang and Ruobin Zhong and Haoming Xu and Chen Jiang and Yi Zhong and Runnan Fang and Jia-Chen Gu and Shumin Deng and Yunzhi Yao and Mengru Wang and Shuofei Qiao and Xin Xu and Tongtong Wu and Kun Wang and Yang Liu and Zhen Bi and Jungang Lou and Yuchen Eleanor Jiang and Hangcheng Zhu and Gang Yu and Haiwen Hong and Longtao Huang and Hui Xue and Chenxi Wang and Yijun Wang and Zifei Shan and Xi Chen and Zhaopeng Tu and Feiyu Xiong and Xin Xie and Peng Zhang and Zhengke Gui and Lei Liang and Jun Zhou and Chiyu Wu and Jin Shang and Yu Gong and Junyu Lin and Changliang Xu and Hongjie Deng and Wen Zhang and Keyan Ding and Qiang Zhang and Fei Huang and Ningyu Zhang and Jeff Z. Pan and Guilin Qi and Haofen Wang and Huajun Chen},year={2026},eprint={2603.04448},archivePrefix={arXiv},primaryClass={cs.AI},- url={https://arxiv.org/abs/2603.04448},+ url={https://arxiv.org/abs/2603.04448},}```diff --git a/skillnet-ai/README.md b/skillnet-ai/README.mdindex 6d1d83b..48ca397 100644--- a/skillnet-ai/README.md+++ b/skillnet-ai/README.md@@ -36,7 +36,7 @@ client.download(url=results[0].skill_url, target_dir="./my_skills")That's it. Search and download are free — no API key, no rate limit.-> For **create**, **evaluate**, and **analyze**, set `API_KEY` (any OpenAI-compatible key). See [Configuration](#%EF%B8%8F-configuration).+> For **create**, **evaluate**, and **analyze**, set `API_KEY` (any OpenAI-compatible key) or `MINIMAX_API_KEY` (for MiniMax). See [Configuration](#%EF%B8%8F-configuration).---@@ -61,6 +61,7 @@ from skillnet_ai import SkillNetClientclient = SkillNetClient(api_key="sk-...", # Required for create / evaluate / analyze+ # provider="minimax", # Optional: "openai" (default) or "minimax"# base_url="...", # Optional: custom LLM endpoint (default: OpenAI)# github_token="ghp-..." # Optional: for private repos or higher rate limits)@@ -68,6 +69,8 @@ client = SkillNetClient(Credentials can also be set via environment variables: `API_KEY`, `BASE_URL`, `GITHUB_TOKEN`.+Provider is auto-detected when `MINIMAX_API_KEY` is set. See [Using MiniMax](#using-minimax-as-llm-provider) for details.+### Search```python@@ -124,6 +127,9 @@ client.create(office_file="./guide.pdf", output_dir="./skills")# From a natural language descriptionclient.create(prompt="A skill for web scraping article titles", output_dir="./skills")++# Use a specific model+client.create(prompt="A skill for PDF parsing", output_dir="./skills", model="gpt-4o")```All modes auto-generate a complete skill package: `SKILL.md` + optional `scripts/`, `references/`, `assets/`.@@ -180,6 +186,8 @@ skillnet <command> --help # Full options for any command| `evaluate` | Quality report | `skillnet evaluate ./my_skill` || `analyze` | Relationship graph | `skillnet analyze ./my_skills` |+> All LLM-powered commands (`create`, `evaluate`, `analyze`) support `--provider` (e.g. `--provider minimax`) and `--model` flags.+### Search```bash@@ -207,6 +215,7 @@ skillnet create --github https://github.com/owner/repo # from GitHub reposkillnet create --office ./docs/guide.pdf # from PDF/PPT/Wordskillnet create --prompt "A skill for table extraction" # from promptskillnet create --office report.pdf --model gpt-4o # custom model+skillnet create --provider minimax --prompt "web scraping" # use MiniMax```### Evaluate@@ -215,6 +224,7 @@ skillnet create --office report.pdf --model gpt-4o # custom modelskillnet evaluate ./my_skills/web_searchskillnet evaluate https://github.com/anthropics/skills/tree/main/skills/algorithmic-artskillnet evaluate ./my_skill --category "Development" --model gpt-4o+skillnet evaluate --provider minimax ./my_skill```### Analyze@@ -223,6 +233,7 @@ skillnet evaluate ./my_skill --category "Development" --model gpt-4oskillnet analyze ./my_skillsskillnet analyze ./my_skills --no-save # print only, don't write fileskillnet analyze ./my_skills --model gpt-4o+skillnet analyze --provider minimax ./my_skills```---@@ -231,13 +242,14 @@ skillnet analyze ./my_skills --model gpt-4o### Environment Variables-| Variable | Required For | Default |-| :--------------- | :--------------------------------- | :-------------------------- |-| `API_KEY` | `create` · `evaluate` · `analyze` | — |-| `BASE_URL` | Custom LLM endpoint | `https://api.openai.com/v1` |-| `GITHUB_TOKEN` | Private repos / higher rate limits | — |-| `SKILLNET_MODEL` | Default LLM model for all commands | `gpt-4o` |-| `GITHUB_MIRROR` | Faster downloads in restricted networks | — |+| Variable | Required For | Default |+| :---------------- | :-------------------------------------- | :-------------------------- |+| `API_KEY` | `create` · `evaluate` · `analyze` | — |+| `MINIMAX_API_KEY` | MiniMax provider (auto-detected) | — |+| `BASE_URL` | Custom LLM endpoint | `https://api.openai.com/v1` |+| `GITHUB_TOKEN` | Private repos / higher rate limits | — |+| `SKILLNET_MODEL` | Default LLM model for all commands | `gpt-4o` |+| `GITHUB_MIRROR` | Faster downloads in restricted networks | — |> `search` and `download` (public repos) require **no credentials at all**.>@@ -263,6 +275,47 @@ Or pass credentials directly in code:client = SkillNetClient(api_key="sk-...", base_url="https://...")```+### Using MiniMax as LLM Provider++SkillNet supports [MiniMax](https://www.minimax.io/) as a first-class LLM provider. MiniMax offers the M2.7 model with a 1M-token context window and OpenAI-compatible API.++**Quick start — environment variable (auto-detected):**++```bash+export MINIMAX_API_KEY="your-minimax-api-key"+skillnet create --prompt "A skill for web scraping"+# Provider, base URL, and model are auto-configured+```++**Explicit provider flag:**++```bash+skillnet create --provider minimax --prompt "A skill for web scraping"+skillnet evaluate --provider minimax ./my_skill+skillnet analyze --provider minimax ./my_skills+```++**Python SDK:**++```python+from skillnet_ai import SkillNetClient++# Auto-detected when MINIMAX_API_KEY is set+client = SkillNetClient()++# Or explicit provider+client = SkillNetClient(provider="minimax", api_key="your-minimax-api-key")+```++**Provider comparison:**++| Provider | Default Model | Base URL | API Key Env |+| :-------- | :------------- | :-------------------------- | :---------------- |+| `openai` | `gpt-4o` | `https://api.openai.com/v1` | `API_KEY` |+| `minimax` | `MiniMax-M2.7` | `https://api.minimax.io/v1` | `MINIMAX_API_KEY` |++**Model priority:** `--model` flag > `SKILLNET_MODEL` env var > provider's default model.+---## 📂 Skill Structurediff --git a/skillnet-ai/src/skillnet_ai/cli.py b/skillnet-ai/src/skillnet_ai/cli.pyindex 3bd1774..953aad4 100644--- a/skillnet-ai/src/skillnet_ai/cli.py+++ b/skillnet-ai/src/skillnet_ai/cli.py@@ -182,7 +182,7 @@ def create(# Output optionsoutput_dir: Path = typer.Option(Path("./generated_skills"), "--output-dir", "-d", help="Directory to save generated skills."),# Model options- model: str = typer.Option(DEFAULT_MODEL, "--model", "-m", help="LLM model to use (e.g., gpt-4o, gpt-3.5-turbo)."),+ model: str = typer.Option(None, "--model", "-m", help="LLM model to use (e.g., gpt-4o, MiniMax-M2.7). Defaults to provider's default model."),max_files: int = typer.Option(50, "--max-files", help="Max code files to analyze (--github only)."),provider: str = typer.Option(None, "--provider", help=f"LLM provider ({', '.join(SUPPORTED_PROVIDERS)}). Auto-detected when omitted."),):@@ -223,15 +223,16 @@ def create(console.print("[bold red]Error:[/bold red] Only one input source can be specified at a time.")raise typer.Exit(code=1)- # 3. Route to appropriate handler+ # 3. Route to appropriate handler (use resolved model from provider config)+ resolved_model = cfg["model"]if github:- _create_from_github(github, output_dir, model, max_files, provider)+ _create_from_github(github, output_dir, resolved_model, max_files, provider)elif trajectory_file:- _create_from_trajectory(trajectory_file, output_dir, model, provider)+ _create_from_trajectory(trajectory_file, output_dir, resolved_model, provider)elif office:- _create_from_office(office, output_dir, model, provider)+ _create_from_office(office, output_dir, resolved_model, provider)elif prompt:- _create_from_prompt(prompt, output_dir, model, provider)+ _create_from_prompt(prompt, output_dir, resolved_model, provider)def _create_from_trajectory(trajectory_file: Path, output_dir: Path, model: str, provider: str = None):@@ -429,7 +430,7 @@ def evaluate(description: str = typer.Option(None, help="Short description of what the skill does."),# Config options- model: str = typer.Option(DEFAULT_MODEL, "--model", "-m", help="LLM model to use."),+ model: str = typer.Option(None, "--model", "-m", help="LLM model to use. Defaults to provider's default model."),max_workers: int = typer.Option(5, help="Concurrency for batch operations (not used for single eval)."),provider: str = typer.Option(None, "--provider", help=f"LLM provider ({', '.join(SUPPORTED_PROVIDERS)}). Auto-detected when omitted."),):@@ -527,7 +528,7 @@ def _display_evaluation_report(target_name: str, data: dict):def analyze(skills_dir: Path = typer.Argument(..., exists=True, file_okay=False, help="Directory containing multiple skill folders to analyze."),save: bool = typer.Option(True, "--save/--no-save", help="Save the result to relationships.json in the directory."),- model: str = typer.Option(DEFAULT_MODEL, "--model", "-m", help="LLM model to use."),+ model: str = typer.Option(None, "--model", "-m", help="LLM model to use. Defaults to provider's default model."),provider: str = typer.Option(None, "--provider", help=f"LLM provider ({', '.join(SUPPORTED_PROVIDERS)}). Auto-detected when omitted."),):"""diff --git a/skillnet-ai/src/skillnet_ai/client.py b/skillnet-ai/src/skillnet_ai/client.pyindex a2c5f77..f2b91cd 100644--- a/skillnet-ai/src/skillnet_ai/client.py+++ b/skillnet-ai/src/skillnet_ai/client.py@@ -155,7 +155,7 @@ class SkillNetClient:office_file: Optional[str] = None,prompt: Optional[str] = None,output_dir: Union[str, Path] = "./generated_skills",- model: str = DEFAULT_MODEL,+ model: Optional[str] = None,max_files: int = 50) -> List[str]:"""@@ -254,7 +254,7 @@ class SkillNetClient:name: Optional[str] = None,category: Optional[str] = None,description: Optional[str] = None,- model: str = DEFAULT_MODEL,+ model: Optional[str] = None,max_workers: int = 5,cache_dir: Union[str, Path] = "./evaluate_cache_dir") -> Dict[str, Any]:@@ -316,7 +316,7 @@ class SkillNetClient:self,skills_dir: Union[str, Path],save_to_file: bool = True,- model: str = DEFAULT_MODEL+ model: Optional[str] = None) -> List[Dict[str, Any]]:"""Analyze a local directory containing multiple skills to infer relationships between them.diff --git a/skills/skillnet/SKILL.md b/skills/skillnet/SKILL.mdindex 4e67b12..7294b73 100644--- a/skills/skillnet/SKILL.md+++ b/skills/skillnet/SKILL.md@@ -165,8 +165,19 @@ skillnet create trajectory.txt --output-dir ~/.openclaw/workspace/skills# From natural-language descriptionskillnet create --prompt "A skill for managing Docker Compose" \--output-dir ~/.openclaw/workspace/skills++# Use MiniMax provider (auto-detected when MINIMAX_API_KEY is set, or explicit)+skillnet create --provider minimax --prompt "A skill for web scraping" \+ --output-dir ~/.openclaw/workspace/skills```+All LLM-powered commands (`create`, `evaluate`, `analyze`) support `--provider` (e.g. `--provider minimax`) and `--model` flags. Provider is auto-detected when `MINIMAX_API_KEY` is set. Model resolution: `--model` flag > `SKILLNET_MODEL` env var > provider's default model.++| Provider | Default Model | API Key Env |+| --------- | -------------- | ----------------- |+| `openai` | `gpt-4o` | `API_KEY` |+| `minimax` | `MiniMax-M2.7` | `MINIMAX_API_KEY` |+**Always evaluate after creating:**```bash@@ -240,13 +251,14 @@ During execution, if any of these occur, suggest the action to the user and proc## Environment Variables-| Variable | Needed for | Default |-| ---------------- | -------------------------------------- | --------------------------- |-| `API_KEY` | create, evaluate, analyze | — |-| `BASE_URL` | custom LLM endpoint | `https://api.openai.com/v1` |-| `GITHUB_TOKEN` | private repos / rate limits | — (60 req/hr without) |-| `SKILLNET_MODEL` | default LLM model for all commands | `gpt-4o` |-| `GITHUB_MIRROR` | faster downloads in restricted networks | — |+| Variable | Needed for | Default |+| ----------------- | --------------------------------------- | --------------------------- |+| `API_KEY` | create, evaluate, analyze | — |+| `MINIMAX_API_KEY` | MiniMax provider (auto-detected) | — |+| `BASE_URL` | custom LLM endpoint | `https://api.openai.com/v1` |+| `GITHUB_TOKEN` | private repos / rate limits | — (60 req/hr without) |+| `SKILLNET_MODEL` | default LLM model for all commands | `gpt-4o` |+| `GITHUB_MIRROR` | faster downloads in restricted networks | — |**No credentials needed for install, search, or download (public repos).** For credential setup, ask templates, and OpenClaw config, see `references/api-reference.md` → "Credential Strategy".diff --git a/skills/skillnet/references/api-reference.md b/skills/skillnet/references/api-reference.mdindex fb20b5f..f5f5c8e 100644--- a/skills/skillnet/references/api-reference.md+++ b/skills/skillnet/references/api-reference.md@@ -101,12 +101,12 @@ Options:--prompt TEXT Natural-language descriptionTRAJECTORY Path to trajectory/log file (positional)--output-dir TEXT Output directory [default: ./generated_skills]- --model TEXT LLM model [default: gpt-4o]- Also reads SKILLNET_MODEL env var.+ --model TEXT LLM model (overrides provider default and SKILLNET_MODEL).+ --provider TEXT LLM provider (openai, minimax). Auto-detected when omitted.--max-files INTEGER Max files for GitHub mode [default: 50]```-Model priority: `--model` flag > `SKILLNET_MODEL` env var > `gpt-4o`.+Model priority: `--model` flag > `SKILLNET_MODEL` env var > provider's default model.Input types (auto-detected):@@ -127,8 +127,8 @@ Options:--name TEXT Override skill name--category TEXT Override category--description TEXT Override description- --model TEXT LLM model [default: gpt-4o]- Also reads SKILLNET_MODEL env var.+ --model TEXT LLM model (overrides provider default and SKILLNET_MODEL).+ --provider TEXT LLM provider (openai, minimax). Auto-detected when omitted.--max-workers INTEGER Concurrency [default: 5]```@@ -144,8 +144,8 @@ Arguments:Options:--no-save Don't write relationships.json- --model TEXT LLM model [default: gpt-4o]- Also reads SKILLNET_MODEL env var.+ --model TEXT LLM model (overrides provider default and SKILLNET_MODEL).+ --provider TEXT LLM provider (openai, minimax). Auto-detected when omitted.```Output: `relationships.json` with edges:@@ -173,7 +173,8 @@ from skillnet_ai import SkillNetClientclient = SkillNetClient(api_key="sk-...", # env: API_KEY (required for create/evaluate/analyze)base_url="https://...", # env: BASE_URL (optional)- github_token="ghp_..." # env: GITHUB_TOKEN (optional)+ github_token="ghp_...", # env: GITHUB_TOKEN (optional)+ provider="minimax", # optional: "openai" (default) or "minimax" (auto-detected))```@@ -211,13 +212,16 @@ Returns `List[Dict[str, Any]]` — relationship edges.## Environment Variables-| Variable | Purpose | Required |-| ---------------- | ---------------------------------------- | ----------------------------- |-| `API_KEY` | LLM API key (OpenAI-compatible) | For create, evaluate, analyze |-| `BASE_URL` | Custom LLM endpoint | No (defaults to OpenAI) |-| `GITHUB_TOKEN` | GitHub PAT for private repos | No |-| `SKILLNET_MODEL` | Default LLM model for all commands | No (defaults to `gpt-4o`) |-| `GITHUB_MIRROR` | Mirror URL for faster downloads | No |+| Variable | Purpose | Required |+| ----------------- | ---------------------------------- | ----------------------------- |+| `API_KEY` | LLM API key (OpenAI-compatible) | For create, evaluate, analyze |+| `MINIMAX_API_KEY` | MiniMax API key (auto-detected) | For MiniMax provider |+| `BASE_URL` | Custom LLM endpoint | No (defaults to OpenAI) |+| `GITHUB_TOKEN` | GitHub PAT for private repos | No |+| `SKILLNET_MODEL` | Default LLM model for all commands | No (defaults to `gpt-4o`) |+| `GITHUB_MIRROR` | Mirror URL for faster downloads | No |++**Provider detection priority:** explicit `--provider` flag > URL-based detection > `MINIMAX_API_KEY` env var presence > OpenAI fallback.## Security & Privacy@@ -249,13 +253,13 @@ export GITHUB_TOKEN="<value>" # only if needed### Command ↔ Variable Requirement-| Command | `API_KEY` | `BASE_URL` | `GITHUB_TOKEN` | `SKILLNET_MODEL` | `GITHUB_MIRROR` |-| ------------------- | ------------ | ---------- | ----------------------------- | ----------------- | --------------- |-| `skillnet search` | — | — | — | — | — |-| `skillnet download` | — | — | Private repos only | — | Optional |-| `skillnet create` | **Required** | Optional | `--github` private repos only | Optional | — |-| `skillnet evaluate` | **Required** | Optional | — | Optional | — |-| `skillnet analyze` | **Required** | Optional | — | Optional | — |+| Command | `API_KEY` | `MINIMAX_API_KEY` | `BASE_URL` | `GITHUB_TOKEN` | `SKILLNET_MODEL` | `GITHUB_MIRROR` |+| ------------------- | ------------ | ----------------- | ---------- | ----------------------------- | ---------------- | --------------- |+| `skillnet search` | — | — | — | — | — | — |+| `skillnet download` | — | — | — | Private repos only | — | Optional |+| `skillnet create` | **Required** | Alt. to API_KEY | Optional | `--github` private repos only | Optional | — |+| `skillnet evaluate` | **Required** | Alt. to API_KEY | Optional | — | Optional | — |+| `skillnet analyze` | **Required** | Alt. to API_KEY | Optional | — | Optional | — |**No env vars are required for install, search, or download (public repos).**@@ -263,7 +267,7 @@ export GITHUB_TOKEN="<value>" # only if needed**API_KEY** — triggered before `create`/`evaluate`/`analyze` when not configured:-> I need an OpenAI-compatible API_KEY (used only for create/evaluate/analyze in this run). Optionally provide BASE_URL and model name (default gpt-4o). May I proceed with your key?+> I need an OpenAI-compatible API_KEY (or MINIMAX_API_KEY for MiniMax) for create/evaluate/analyze in this run. Optionally provide BASE_URL, model name (default: provider's default), or `--provider minimax`. May I proceed with your key?**GITHUB_TOKEN** — triggered only on private repo access or rate-limit (403):diff --git a/skills/skillnet/references/security-privacy.md b/skills/skillnet/references/security-privacy.mdindex 60abe4d..abe690f 100644--- a/skills/skillnet/references/security-privacy.md+++ b/skills/skillnet/references/security-privacy.md@@ -3,6 +3,7 @@## Credential Scope- **API_KEY**: Used solely for authenticating with your chosen LLM endpoint (`BASE_URL`). **Never** sent to the SkillNet search API or any other third party.+- **MINIMAX_API_KEY**: Used solely for authenticating with the MiniMax LLM endpoint (`https://api.minimax.io/v1`). Auto-detected as the provider key when set. **Never** sent to the SkillNet search API or any other third party.- **GITHUB_TOKEN**: Sent only to `api.github.com` to access repositories. Only `repo:read` scope is needed. Never forwarded to any other service.## Network Endpoints & Data Flow