awesome-agentic-ai-zh is a trilingual learning roadmap for building and using AI agents, which are systems that pursue a goal by choosing steps, using tools, and responding to results. It guides beginners and experienced programmers through LLM basics, agent loops, multi-agent systems, reliability, and practical exercises. Its catalogue add-ons support workflows involving CLI agents such as Claude Code, Codex, and OpenCode.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add WenyuChiou/awesome-agentic-ai-zh --skill tool-calling-tutorgit clone --depth 1 https://github.com/WenyuChiou/awesome-agentic-ai-zhWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wenyuchiou/awesome-agentic-ai-zh/tool-calling-tutor)<a href="https://agentmods.dev/skills/wenyuchiou/awesome-agentic-ai-zh/tool-calling-tutor"><img src="https://agentmods.dev/badge/skills/wenyuchiou/awesome-agentic-ai-zh/tool-calling-tutor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wenyuchiou/awesome-agentic-ai-zh/tool-calling-tutor"><img src="https://agentmods.dev/badge/skills/wenyuchiou/awesome-agentic-ai-zh/tool-calling-tutor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.02315 |
| Opus 5 | $0.00031 | $0.01157 |
| Sonnet 5 | $0.00012 | $0.00463 |
| Haiku 4.5 | $0.00006 | $0.00231 |
Grade A, and why
tool-calling-tutor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Calling Tutor
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.
Step 1 — Triage（first thing you do）
When the user mentions tool calling problems, first infer the route from an explicit symptom and briefly confirm it. Ask one multiple-choice question only when the symptom is not explicit:
- (a) LLM 不呼叫我的 tool — 模型直接用自然語言回答、完全沒觸發 tool_calls
- (b) Tool 被呼叫、但參數錯 — 呼叫對 tool，但
arguments不對（型別錯、缺欄位、值不合理） - (c) ReAct loop 跑不停 / 漏步 — 多步 loop 無限循環，或者中間漏一個 tool 沒呼叫
- (d) 我從零開始、還沒寫 schema — 用戶要新做一個 tool、想知道 schema 怎麼設計
明確的症狀不用重問；確認你推定的 route 後直接繼續。每個 branch 走的 reference 不同。
Step 2 — Branch by symptom
(a) LLM 不呼叫 tool → 看 description 與工具邊界
先檢查這 3 項：
description太籠統：寫的是「處理資料 / Convert a value / Search things」這種給人讀的 docstring，LLM 看不到「這個 tool 解什麼具體問題」。看 debug-flowchart.md Section A。- 多 tool 邊界互相重疊：兩個 tool 的 description 都能套到 user query、LLM 選不出來、乾脆都不選。
- 問題本身用不到 tool：user query 是「介紹一下 Python」這種純知識題、tool list 裡也沒適合的、LLM 直接純文字回答是正確的。
怎麼修：把 description 從「做什麼」改寫成「何時用」。對照 schema-evolution.md 的 bad → good A/B。
(b) Tool 被呼叫、但參數錯 → 看 parameters schema
先檢查這 3 項：
- 參數型別全用
string：{"value": {"type": "string"}}LLM 不知道要傳 number。改成{"type": "number"}。 - 沒有
required：模型可能漏傳必填欄位。明列"required": ["value", "unit"]。 - enum 該用沒用：
unit: string讓 LLM 傳"C""Celsius""celsius"都有可能。改"enum": ["celsius", "fahrenheit"]。
對照 schema-evolution.md 的 4 個改進。
(c) ReAct loop 跑不停 / 漏步 → 看 control flow
跑不停的 3 個典型原因：
- 忘記把 assistant response 加回
messages——下輪 LLM 看不到自己上輪講過什麼、會無限重複 toolmessage 沒帶tool_call_id——LLM 無法配對哪個 result 對應哪個 call、可能重新發起 tool call- 沒設
max_itersafety net——當 tool 結果寫得不好、LLM 會無限呼叫
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/check_evals.py 3.9 KB runs code
- evals/evals.json 2.7 KB
- README.en.md 8.1 KB
- README.md 7.9 KB
- README.zh-Hans.md 8.0 KB
- references/debug-flowchart.en.md 3.6 KB
- references/debug-flowchart.md 3.5 KB
- references/debug-flowchart.zh-Hans.md 3.5 KB
- references/schema-evolution.en.md 3.4 KB
- references/schema-evolution.md 3.2 KB
- references/schema-evolution.zh-Hans.md 3.2 KB
- references/sdk-diff.en.md 4.5 KB
- references/sdk-diff.md 4.5 KB
- references/sdk-diff.zh-Hans.md 4.5 KB
- translations/SKILL.en.md 8.0 KB
- translations/SKILL.zh-Hans.md 8.0 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 112 lines · 62 tokens per session scan A a191709903cd
tool-calling-tutor is a skill published in the GitHub repository WenyuChiou/awesome-agentic-ai-zh (6,754 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 2,315 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
error-translator
A Chinese-language assistant that translates English programming errors and explains what they mean. It covers common errors from languages and frameworks including Python, JavaScript, TypeScript, Java, and others.
eslint-fix
A project-aware assistant for finding and fixing ESLint errors, warnings, and configuration compatibility problems. ESLint is a tool that checks JavaScript and TypeScript code for style and common mistakes.
perf-profiler
A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
detecting-process-injection-techniques
Detects and analyzes process injection techniques used by malware including classic DLL injection, process hollowing, APC injection, thread hijacking, and reflective loading. Uses memory forensics, API monitoring, and behavioral analysis to identify injection artifacts. Activates for requests involving process…
openskills-runtime-debug
Diagnose openskills-runtime execution failures in sandboxed paths (Landlock, seatbelt, native script execution, wasm execution) and produce root-cause-first findings with minimal-risk remediation steps.