Is the Tool Calling Tutor skill free?

Yes. The skill itself is free from WenyuChiou/awesome-agentic-ai-zh. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Tool Calling Tutor SkillProof Score?

8.8/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.

How do I install Tool Calling Tutor?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Tool Calling Tutor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Tool Calling Tutor

Interactive 4-branch diagnostic that walks a developer through why their LLM won't call, or mis-calls, a tool.

by WenyuChiou · WenyuChiou/awesome-agentic-ai-zh

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.8/10
Tested: Jul 10, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 78808a3

The documented standalone-install steps don't copy files its own walkthrough links to two folders up, leaving broken references - confirmed against the README's own instructions, not just a guess.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 4/5

What Tool Calling Tutor does

Runs a mandatory triage question (LLM not calling / wrong args / ReAct loop stuck / greenfield schema design), then branches into a priority-ordered list of causes backed by a bad-to-good schema worked example and an Anthropic-vs-OpenAI SDK diff sheet. Triggers on bilingual tool-calling complaints like "the LLM won't call my tool" or "為什麼 LLM 不呼叫我的 tool", and explicitly routes LangChain/MCP/observability questions elsewhere instead of answering them.

How to install Tool Calling Tutor

git clone https://github.com/WenyuChiou/awesome-agentic-ai-zh
cd awesome-agentic-ai-zh
mkdir -p ~/.claude/skills
cp -r examples/stage-5/tool-calling-tutor ~/.claude/skills/tool-calling-tutor

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Tool Calling Tutor

/tool-calling-tutor Interactive 4-branch diagnostic that walks a developer through why their LLM won't call, or mis-calls, a tool.

It also activates on plain-language prompts like these:

My LLM won't call the tool I defined, help me debug why
The model keeps passing wrong arguments to my function schema
My ReAct loop is stuck calling tools in a circle, fix it

Frequently asked questions

Is the Tool Calling Tutor skill free?: Yes. The skill itself is free from WenyuChiou/awesome-agentic-ai-zh. SkillProof publishes the install command and an independent test verdict at no cost.
Does Tool Calling Tutor work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 10, 2026. Verdict: Works with setup. The documented standalone-install steps don't copy files its own walkthrough links to two folders up, leaving broken references - confirmed against the README's own instructions, not just a guess.
What is the Tool Calling Tutor SkillProof Score?: 8.8/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.
How do I install Tool Calling Tutor?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Tool Calling Tutor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.