custom-skills

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

審視 ECC（everything-claude-code）分發名單，包含兩個模式： (A) 既有清單瘦身：分析 distribution.yaml.enabled 與本地 skills/ 的重疊性與品質，輸出 enabled_remove 建議； (B) 新項目導入評估：根據 ecc-catalog.yaml 與上次更新範圍，介紹 ECC 上游新增 skill、分析適用情境、建議是否加入 enabled。 Use when: (1) 評估 ECC 分發名單是否該瘦身、(2) ECC 上游新增 skill 後決定要不要導入、 (3) 想為終端使用者產 ecc-profile.yaml starter、(4) 季度 / 半年一次定期審視。 Triggers: "分析 ECC skill", "ECC 重疊", "ECC 清單瘦身", "ECC 新項目", "ECC 上游新增", "要不要導入", "ecc analyze", "ecc new items review", "ecc profile starter", "ECC 品質審視".

用追問把模糊需求壓成專案語言，並在必要時更新 CONTEXT.md 或 ADR。 Use when: 需求還不清楚、術語不一致、要進 OpenSpec 前需要需求對齊、 或使用者想先 stress-test plan 而不是直接實作。

找出架構摩擦與 deep module 候選，但不直接修改實作程式碼。 Use when: 使用者要架構回看、找重構候選、改善可測性、 或把實作中暴露的架構摩擦整理成 OpenSpec 候選。

建立 MP 工作入口層的專案規則。Use when: 首次導入 mattpocock/skills 改寫版、 需要設定 docs/agents/、需要讓 Claude Code 與 Codex 共同讀取 issue tracker、 triage states、domain docs 規則，或 mp-* 技能缺少專案入口脈絡。

將 plan、PRD、OpenSpec change 或對話摘要切成可驗證的垂直切片。 Use when: 需要把大型需求拆成 OpenSpec tasks、GitHub issue draft、 或本地 Markdown 工作項目；不適用於直接 TDD 實作。

將既有對話與儲存庫脈絡整理成 PRD 或 OpenSpec proposal 前置素材。 Use when: 使用者要把已討論內容整理成需求摘要、PRD、或進入 OpenSpec 前的 brief； 不適用於重新訪談使用者。

以 tracker 無關的狀態模型分流工作項目。Use when: 需要判斷 issue、 OpenSpec task 或本地 Markdown 是否 ready-for-agent、ready-for-human、 needs-info、needs-triage 或 wontfix。

This skill should be used when the user asks to "analyze from first principles", "第一性原理", "从根本分析", "从零开始思考", "think from scratch", "question this design", "这个设计合理吗", "is this the right approach", "为什么要这样做", "why are we doing it this way", "有没有更好的方案", "is there a better solution", "challenge assumptions", "挑战假设", "should this even exist", "這個需求合理嗎", "先刪除", or needs to evaluate architectural decisions, design choices, or problem-solving approaches without relying on analogies or conventions.

Prevent AI hallucination and ensure evidence-based responses when analyzing code or making suggestions. Use when: analyzing code, making recommendations, providing options, or when user asks about confidence/certainty. Keywords: certainty, assumption, inference, evidence, source, 確定性, 推測, 假設, 來源, 證據.

Design AI-friendly architecture with explicit patterns, layered documentation, and semantic boundaries. Use when: structuring projects for AI collaboration, optimizing codebase for AI analysis, setting up AI context. Keywords: architecture, AI-friendly, context, modules, documentation layers, .ai-context.yaml, 架構, AI 友善, 上下文.

Create and maintain AI instruction files (CLAUDE.md, .cursorrules, etc.) with proper structure. Use when: creating AI instruction files, separating universal vs project-specific rules, configuring AI tools. Keywords: CLAUDE.md, cursorrules, windsurfrules, clinerules, AI instructions, system prompt, 指令檔案, AI 設定.

Guide teams through Acceptance Test-Driven Development workflow. Use when: defining acceptance criteria, running specification workshops, writing user stories with acceptance tests, PO sign-off. Keywords: ATDD, acceptance test, acceptance criteria, user story, product owner, specification workshop, 驗收測試驅動開發.

Guide developers through Behavior-Driven Development workflow. Use when: writing BDD scenarios, using Gherkin syntax, Given-When-Then format, feature files, Three Amigos collaboration. Keywords: BDD, behavior-driven, Given When Then, Gherkin, Cucumber, scenario, feature file, step definition, 行為驅動開發.

Write and maintain CHANGELOG.md following Keep a Changelog format. Use when: creating changelog entries, preparing releases, documenting changes. Keywords: changelog, release notes, CHANGELOG.md, keep a changelog, 變更日誌, 發布說明.

Guide pre-commit quality gates and check-in workflow. Use when: committing code, preparing commits, quality gate verification. Keywords: commit, checkin, pre-commit, quality gate, git add, 提交, 簽入, 品質關卡.

Systematic code review checklist and pre-commit quality gates for PRs. Use when: reviewing pull requests, checking code quality, before committing code. Keywords: review, PR, pull request, checklist, quality, commit, 審查, 檢查, 簽入.

Format commit messages following conventional commits standard. Use when: writing commit messages, git commit, reviewing commit history. Keywords: commit, git, message, conventional, feat, fix, refactor.

Generate usage documentation from project sources. Use when: "generate docs", "create cheatsheet", "usage guide", "feature reference", "list all features" Keywords: documentation, usage, reference, cheatsheet, features, 功能文件, 速查表, 使用說明

Guide documentation structure, content requirements, and project documentation best practices. Use when: creating README, documentation, docs folder, project setup, technical docs. Keywords: README, docs, documentation, CONTRIBUTING, CHANGELOG, ARCHITECTURE, API docs, 文件, 說明文件, 技術文件.

Design consistent error codes following the PREFIX_CATEGORY_NUMBER format. Use when: defining error codes, creating error handling, designing APIs. Keywords: error code, error handling, error format, API errors, 錯誤碼, 錯誤處理.

Derive BDD scenarios and TDD test skeletons from approved SDD specifications. ATDD acceptance test tables are optional output for specialized needs. Use when: spec is approved, starting BDD/TDD implementation, generating test structures. Keywords: forward derivation, spec to test, BDD generation, TDD skeleton, test derivation, 正向推演, 規格轉測試, 測試生成.

Guide Git branching strategies, branch naming, and merge operations. Use when: creating branches, merging, pull requests, Git workflow questions. Keywords: branch, merge, PR, pull request, GitFlow, GitHub Flow, 分支, 合併, 工作流程.

Implement structured logging with proper log levels and sensitive data handling. Use when: adding logging, debugging, setting up observability. Keywords: logging, log level, structured logging, observability, 日誌, 記錄, 結構化日誌.

Manage and guide developers through active development methodology workflows. Use when: TDD, BDD, SDD, ATDD, or custom methodology workflows are needed. Keywords: methodology, workflow, TDD, BDD, SDD, ATDD, phase, checkpoint, development process.

Guide for organizing project directories following language-specific best practices. Use when: creating projects, reorganizing structure, adding modules, setting up builds. Keywords: project, structure, directory, layout, gitignore, scaffold, 專案結構, 目錄.

Guide refactoring decisions and large-scale code improvements. Use when: refactoring code, legacy modernization, technical debt, rewrite decisions. Keywords: refactor, rewrite, legacy, strangler, technical debt, 重構, 重寫, 技術債.

Semantic versioning and changelog formatting for software releases. Use when: preparing releases, updating version numbers, writing changelogs. Keywords: version, release, changelog, semver, major, minor, patch, 版本, 發布, 變更日誌.

Guide requirement writing, user story creation, and feature specification. Use when: writing requirements, user stories, issues, feature planning. Keywords: requirement, user story, issue, feature, specification, 需求, 功能規劃, 規格.

Reverse engineer existing code into SDD specification documents. Use when: analyzing legacy code, documenting undocumented systems, creating specs from existing implementations. Keywords: reverse engineering, legacy code, documentation, spec extraction, code archaeology, 反向工程, 舊有程式碼, 規格提取.

Guide Spec-Driven Development (SDD) workflow for planning changes before implementation. Use when: creating specs, proposals, planning features, using OpenSpec or similar tools. Keywords: spec, specification, SDD, proposal, openspec, design doc, 規格, 提案, 設計文件.

Evaluate test completeness using the 8 dimensions framework. Use when: writing tests, reviewing test coverage, ensuring test quality. Keywords: test coverage, completeness, dimensions, 8 dimensions, test quality, AI test quality, 測試覆蓋, 測試完整性, 八維度.

Testing pyramid and test writing standards for UT/IT/ST/E2E. Supports ISTQB and Industry Pyramid frameworks. Use when: writing tests, discussing test coverage, test strategy, or test naming. Keywords: test, unit, integration, e2e, coverage, mock, ISTQB, SIT, 測試, 單元, 整合, 端對端.

Unified upstream repo operations: audit commit drift, check UDS file-level drift, detect repo overlap with local project, and perform sync maintenance. Use when: reviewing upstream updates, auditing standards drift, evaluating a new repo for integration, updating last-sync.yaml after sync. Triggers: "upstream audit", "uds check", "repo overlap", "sync maintenance", "上游同步", "上游檢查", "上游維護".

Guide development workflow for the custom-skills project (ai-dev CLI tool). Use when: (1) adding/modifying skills, commands, or agents, (2) modifying CLI code in script/, (3) updating copy/distribution logic, (4) releasing new versions, (5) integrating upstream resources. Triggers: "develop custom-skills", "modify ai-dev", "add skill to project", "update copy logic", "release version", "開發 custom-skills", "修改複製邏輯", "發布版本".

Use when user wants a pre-review cleanup pass on changed code by running parallel reviews for reuse, code quality, and efficiency, then applying worthwhile fixes without changing behavior.

以統一格式撰寫計畫、報告、指南、教學、紀錄、規範等文件。 Use when: 使用者要求撰寫或起草文件，包含但不限於：計畫書（新功能/重構/遷移）、報告（調查/階段/分析）、指南、教學、會議紀錄、事件紀錄、決策紀錄、規範文件。 觸發方式: /custom-skills-doc-writer [type] [variant] Keywords: 撰寫文件, 文件模板, 計畫書, 報告, 指南, 教學, 紀錄, 規範, document writer, plan, report, guide, tutorial, record, standard, 寫文件, 起草, draft

Compile personal data (journals, notes, messages, whatever) into a personal knowledge wiki. Ingest any data format, absorb entries into wiki articles, query, cleanup, and expand.

分析計畫、報告或變更提案的完整性與對專案的影響評估。 Use when: 使用者提供一份文件（計畫書、技術債評估、修改方案、RFC、ADR、資安報告等）並要求分析其品質、完整性或潛在風險。 觸發方式: /custom-skills-plan-analyze @文件路徑 Keywords: 計畫分析, 報告評估, 影響分析, 風險評估, 完整性檢查, plan review, impact analysis, risk assessment, change analysis, 技術債, RFC review

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.