Overview
tool-calling-tutor is an open-source workflow skill for Claude Code and compatible agents, published by WenyuChiou. Its author describes it as: “When the user is building a tool-calling agent and gets stuck — "為什麼 LLM 不呼叫我的 tool", "我這 schema 哪裡寫壞", "tool 被呼叫但 args 不對", "ReAct loop 跑不停", "the LLM won't call my tool", "help me design a function schema", "debug t…”. The project has 5.5k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/WenyuChiou/awesome-agentic-ai-zh ~/.claude/skills/tool-calling-tutor`.
What tool-calling-tutor does
You are now in the **tool-calling debugging** context. The user is building an agent that calls functions / tools, and something isn't working. Your job is to walk them through diagnosis + fix, not to write code for them.
Best for
What’s inside
The SKILL.md for tool-calling-tutor is organised into these sections:
- Step 1 — Triage（first thing you do）
- Step 2 — Branch by symptom
- (a) LLM 不呼叫 tool → 看 description 與工具邊界
- (b) Tool 被呼叫、但參數錯 → 看 parameters schema
- (c) ReAct loop 跑不停 / 漏步 → 看 control flow
- (d) 從零設計 schema → 走 5 步法
- Step 3 — SDK 差異提醒
- Step 4 — Mock test first（強烈建議）
- Step 5 — When to escalate / route away
- Don't
- References
Installation
Add tool-calling-tutor to your agent with:
git clone https://github.com/WenyuChiou/awesome-agentic-ai-zh ~/.claude/skills/tool-calling-tutorReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — declared in the repository topics
License
tool-calling-tutor is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in WenyuChiou/awesome-agentic-ai-zh, an established project with 5,457 GitHub stars
- Works with Claude Code
- Actively maintained — repository updated in the last 90 days
Author
Topics
Frequently asked questions
- What does tool-calling-tutor do?
- When the user is building a tool-calling agent and gets stuck — "為什麼 LLM 不呼叫我的 tool", "我這 schema 哪裡寫壞", "tool 被呼叫但 args 不對", "ReAct loop 跑不停", "the LLM won't call my tool", "help me design a function schema", "debug this tool-use behavior". Walks them through a 4-branch diagnostic + 5-step schema design walkthrough, with references to bad/good schema A/B and SDK-diff cheatsheet. Do NOT use for: pure LangChain / LangGraph / CrewAI framework questions (route to Stage 4 frameworks), MCP server building (route to cookbook 2), production agent observability (route to Stage 7).
- How do I install tool-calling-tutor?
- Run git clone https://github.com/WenyuChiou/awesome-agentic-ai-zh ~/.claude/skills/tool-calling-tutor in your agent, then reload your skills. Review the source at https://github.com/WenyuChiou/awesome-agentic-ai-zh before installing.
- Is tool-calling-tutor free to use?
- Yes. tool-calling-tutor is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does tool-calling-tutor work with?
- tool-calling-tutor lists Claude Code — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does tool-calling-tutor come from?
- tool-calling-tutor ships inside WenyuChiou/awesome-agentic-ai-zh, a repository that contains 2 catalogued skills in total. The repository's 5,457 GitHub stars apply to that whole collection, not to this skill on its own.
