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 agentmods add skills/godmakereth/vibe-coding-tw/claude-code-guidenpx skills add godmakereth/vibe-coding-tw --skill claude-code-guidegit clone --depth 1 https://github.com/godmakereth/vibe-coding-twWhat 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 | $0.00065 | $0.03268 |
| Opus 5 | $0.00032 | $0.01634 |
| Sonnet 5 | $0.00013 | $0.00654 |
| Haiku 4.5 | $0.00006 | $0.00327 |
Grade A, and why
claude-code-guide 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 2d 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.
This is a copy
95% identical to claude-code-guide — 497 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code 高階開發指南
全面的 Claude Code 中文學習指南,涵蓋從基礎到高階的所有核心概念、工具使用、開發工作流和最佳實踐。
何時使用此技能
當需要以下幫助時使用此技能:
- 學習 Claude Code 的核心功能和工具
- 掌握 REPL 環境的高階用法
- 理解開發工作流和任務管理
- 使用 MCP 整合外部系統
- 實現高階開發模式
- 應用 Claude Code 最佳實踐
- 解決常見問題和錯誤
- 進行大檔案分析和處理
快速參考
Claude Code 核心工具(7個)
-
REPL - JavaScript 執行時環境
- 完整的 ES6+ 支援
- 預載入庫:D3.js, MathJS, Lodash, Papaparse, SheetJS
- 支援 async/await, BigInt, WebAssembly
- 檔案讀取:
window.fs.readFile()
-
Artifacts - 視覺化輸出
- React, Three.js, 圖表庫
- HTML/SVG 渲染
- 互動式元件
-
Web Search - 網路搜尋
- 僅美國可用
- 域名過濾支援
-
Web Fetch - 獲取網頁內容
- HTML 轉 Markdown
- 內容提取和分析
-
Conversation Search - 對話搜尋
- 搜尋歷史對話
- 上下文檢索
-
Recent Chats - 最近對話
- 訪問最近會話
- 對話歷史
-
End Conversation - 結束對話
- 清理和總結
- 會話管理
大檔案分析工作流
# 階段 1:定量評估
wc -l filename.md # 行數統計
wc -w filename.md # 詞數統計
wc -c filename.md # 字元數統計
# 階段 2:結構分析
grep "^#{1,6} " filename.md # 提取標題層次
grep "```" filename.md # 識別程式碼塊
grep -c "keyword" filename.md # 關鍵詞頻率
# 階段 3:內容提取
Read filename.md offset=0 limit=50 # 檔案開頭
Read filename.md offset=N limit=100 # 目標部分
Read filename.md offset=-50 limit=50 # 檔案結尾
REPL 高階用法
// 資料處理
const data = [1, 2, 3, 4, 5];
const sum = data.reduce((a, b) => a + b, 0);
// 使用預載入庫
// Lodash
_.chunk([1, 2, 3, 4], 2); // [[1,2], [3,4]]
// MathJS
math.sqrt(16); // 4
// D3.js
d3.range(10); // [0,1,2,3,4,5,6,7,8,9]
// 讀取檔案
const content = await window.fs.readFile('path/to/file');
// 非同步操作
const result = await fetch('https://api.example.com/data');
const json = await result.json();
斜槓命令系統
內建命令:
/help- 顯示幫助/clear- 清除對話/plugin- 管理外掛/settings- 配置設定
自定義命令:
建立 .claude/commands/mycommand.md:
根據需求執行特定任務的指令
使用:/mycommand
開發工作流模式
1. 檔案分析工作流
# 探索 → 理解 → 實現
ls -la # 列出檔案
Read file.py # 讀取內容
grep "function" file.py # 搜尋模式
# 然後實現修改
2. 演算法驗證工作流
# 設計 → 驗證 → 實現
# 1. 在 REPL 中測試邏輯
# 2. 驗證邊界情況
# 3. 實現到程式碼
What ships with it
2 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.
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.
- 2d ago First seen · 471 lines · 65 tokens per session scan A 90c63291ab97
claude-code-guide is a skill published in the GitHub repository godmakereth/vibe-coding-tw (47 stars, last pushed 8mo ago), licensed MIT. It adds 65 tokens to every session and 3,268 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to claude-code-guide, differing in 497 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…