29 lines
1.3 KiB
Markdown
29 lines
1.3 KiB
Markdown
# SKILL.md — llm-tool-best-practices
|
|
|
|
## Purpose
|
|
Reference guide synthesizing official Anthropic and OpenAI best practices for building, reviewing, and importing agent skills/tools. Use this when:
|
|
- Writing a new skill (SKILL.md or tool definition)
|
|
- Reviewing a downloaded ClawHub skill for safety
|
|
- Debugging why a tool is being misused or ignored by the model
|
|
- Optimizing a skill for a specific LLM (Claude vs. GPT)
|
|
|
|
## How to use
|
|
Read `LLM_TOOL_BEST_PRACTICES.md` in this directory for the full reference.
|
|
|
|
Key sections:
|
|
1. **Universal principles** — applies to all LLMs
|
|
2. **Anthropic/Claude-specific** — schema format, model selection, `input_examples`, eval approach
|
|
3. **OpenAI/GPT-specific** — `strict` mode, tool count limits, reasoning model caveats, safety APIs
|
|
4. **Differences summary** — quick comparison table
|
|
5. **Skill safety checklist** — use before activating any downloaded skill
|
|
6. **OpenClaw authoring notes** — how to write SKILL.md files for this workspace
|
|
|
|
## Sources
|
|
- https://platform.claude.com/docs/en/agents-and-tools/tool-use/implement-tool-use
|
|
- https://www.anthropic.com/engineering/writing-tools-for-agents
|
|
- https://platform.openai.com/docs/guides/function-calling
|
|
- https://platform.openai.com/docs/guides/safety-best-practices
|
|
|
|
## Last updated
|
|
2026-03-05
|