How to load Skillware skills and connect them to language models. Each guide covers one provider adapter in SkillLoader.
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:
- Roots listed in
SKILLWARE_SKILL_PATH(OS path separator between multiple roots) - A
skills/directory in the current working directory or its parents - Bundled skills installed with the
skillwarepackage (for example undersite-packages/skills/)
For pip-installed apps, keep project skills in ./skills/<category>/<name>/ or set SKILLWARE_SKILL_PATH to your skills root.
To list locally available skills or run bundle tests 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, skillware test |
cli.md | pytest in [dev] for test |
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. Runnable script inventory:
examples/README.md.
Contributors adding Usage Examples to skill catalog pages: skill_usage_template.md.
Skills that call external APIs during execution: API keys for skills.