Skip to content
mcp/skillhub

Agent Skill

Tool Calling Tutor skill

tool-calling-tutorWenyuChiou/awesome-agentic-ai-zhexamples/stage-5/tool-calling-tutor/SKILL.md

Use when a tool-calling agent does not call a tool, sends wrong arguments, loops without stopping, or needs a function schema. Guides a four-branch diagnosis and five-step schema repair. Do not use for framework-specific, MCP-server, or production-observability questions.

7.8kMIT

always on

62 tokname + description

once used

2,239 tokSKILL.md body

bundled files

161 scripts

repo stars

7.8kGitHub

Install the Tool Calling Tutor skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/WenyuChiou/awesome-agentic-ai-zh --skill tool-calling-tutor

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/WenyuChiou/awesome-agentic-ai-zh.git /tmp/awesome-agentic-ai-zh
mkdir -p ~/.claude/skills
cp -R /tmp/awesome-agentic-ai-zh/examples/stage-5/tool-calling-tutor ~/.claude/skills/tool-calling-tutor

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description62 tok
When the agent uses itThe SKILL.md instructions2,239 tok
Only if opened16 bundled files (80 KB)varies

Until it is used, tool-calling-tutor costs about 22× less than the median MCP server we measured (1,362 tokens on every turn). Skills vs MCP study

Checks

  • Ships scripts the agent can run. Read them before installing.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Tool Calling Tutor
  • 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