Skip to content

README.md

Latest commit

 

History

History
32 lines (21 loc) · 1.86 KB

README.md

File metadata and controls

32 lines (21 loc) · 1.86 KB

Usage Guides

How to load Skillware skills and connect them to language models. Each guide covers one provider adapter in SkillLoader.

Finding skills on disk

SkillLoader.load_skill() accepts an absolute path to a skill directory, or a registry id such as compliance/tos_evaluator. When the id is not already a path on disk, the loader searches in order:

  1. Roots listed in SKILLWARE_SKILL_PATH (OS path separator between multiple roots)
  2. A skills/ directory in the current working directory or its parents
  3. Bundled skills installed with the skillware package (for example under site-packages/skills/)

For pip-installed apps, keep project skills in ./skills/<category>/<name>/ or set SKILLWARE_SKILL_PATH to your skills root.

To list all locally available skills from the terminal, see the CLI reference.

Provider Adapter Guide Agent API key (typical)
Google Gemini to_gemini_tool() gemini.md GOOGLE_API_KEY (install skillware[gemini] for google-genai)
Anthropic Claude to_claude_tool() claude.md ANTHROPIC_API_KEY
OpenAI (ChatGPT) to_openai_tool() openai.md OPENAI_API_KEY
DeepSeek to_deepseek_tool() deepseek.md DEEPSEEK_API_KEY
Ollama (prompt mode) to_ollama_prompt() ollama.md (local; no cloud key)
CLI skillware list cli.md —

Skill-specific Usage Examples (sample prompts and execute payloads) live on each skill catalog page.

Shared patterns (load bundle, run execute, return tool results): agent_loops.md.

Contributors adding Usage Examples to skill catalog pages: skill_usage_template.md.

Skills that call external APIs during execution: API keys for skills.