Use this agent to scan a codebase for domain terminology, existing story IDs, and project documentation structure. Helps spec writers use consistent language and avoid ID conflicts with existing stories. Examples: <example> Context: 使用者在 Phase 0 確認有程式碼庫可掃描 user: (確認 codebase 可用) assistant: "我會使用 codebase-explorer 來掃描領域術語和既有 Story ID。" <commentary> codebase-explorer 掃描專案以提取領域語言和任何 story/ticket 引用。 </commentary> </example>
Use this agent to read and summarize existing project documents such as PRDs, spec files, sprint plans, or backlog exports. Produces a structured Context Summary that the spec-writing skill uses in subsequent phases. Examples: <example> Context: 使用者在 Phase 0 提供了既有 spec 與 sprint 文件路徑 user: (觸發 Phase 0 情境收集) assistant: "我會使用 context-reader agent 來讀取並摘要你的文件。" <commentary> 使用者提供了既有文件。context-reader 讀取並提取專案名稱、已知限制、 既有 Story ID、Sprint 目標等資訊。 </commentary> </example> <example> Context: 使用者貼上了原始需求文字 user: (在 AskUserQuestion 回應中提供原始文字) assistant: "讓我用 context-reader 來處理這些內容。" <commentary> 原始文字作為任務脈絡傳入。context-reader 解析並結構化。 </commentary> </example>
Use this agent when reviewing user stories or specs for quality. Examples: <example> Context: 使用者剛寫完一組 User Stories,想確認品質 user: "幫我檢查這些 stories 的品質" assistant: "我會使用 spec-reviewer agent 來進行 INVEST 檢查和反模式掃描。" <commentary> 使用者明確要求檢查 stories 品質,觸發 spec-reviewer 進行全面品質檢查。 </commentary> </example> <example> Context: 使用者寫完 spec 後想確認是否有反模式 user: "這個 spec 有沒有什麼問題?" assistant: "讓我用 spec-reviewer agent 來掃描常見反模式和 INVEST 標準。" <commentary> 使用者詢問 spec 問題,觸發 spec-reviewer 進行反模式掃描。 </commentary> </example> <example> Context: 使用者完成了 stories 撰寫,進入品質檢查階段 user: "review my stories" assistant: "I'll use the spec-reviewer agent to check INVEST compliance and anti-patterns." <commentary> 使用者要求 review stories,觸發 spec-reviewer。 </commentary> </example>
Use this agent to decompose a large, ambiguous goal into a structured Story Map (Activity → Task → Story) using Jeff Patton's methodology. Produces a prioritized Stories list for the spec-writing skill's subsequent phases. Examples: <example> Context: 使用者在 Phase 0.5 需要從模糊大目標拆解出 Stories user: (Phase 0 完成,需求是大功能或多角色場景) assistant: "我會使用 story-mapper agent 來建立 Story Map 並拆解出候選 Stories 清單。" <commentary> 需求模糊且範圍大。story-mapper 使用 Story Mapping 方法論,從使用者旅程出發, 建立 Activity → Task → Story 三層結構,並建議 Release 切片。 </commentary> </example> <example> Context: 使用者明確要求進行 Story Mapping user: "幫我做 story mapping" assistant: "我會使用 story-mapper agent 來進行 Story Mapping 拆解。" <commentary> 使用者直接要求 Story Mapping。story-mapper 讀取方法論參考並執行拆解。 </commentary> </example>
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Custom marketplace for development tools including Adobe Animate/CreateJS, xAPI learning analytics, Figma design reading, and spec writing methodology.
Adobe Animate + CreateJS development expert with performance optimization tools.
animate-dev, animate-performancexAPI statement generation and validation expert for educational assessment tracking.
xapi-specification, prompt-engineering/analyze, /generate, /validateRead Figma designs via link, extract structured page layout summaries with minimal context window usage.
figma-read/figma-readSpec/Story 撰寫方法論 — 引導撰寫高品質 User Story 與 Enabler Story,含 INVEST 檢查與反模式掃描。
spec-writingThis marketplace is automatically loaded from:
~/.claude/plugins/marketplaces/user-marketplace/
The plugins should appear in Claude Code's plugin list after marketplace discovery.
user-marketplace/
├── .claude-plugin/
│ └── marketplace.json
├── .claude/skills/ ← symlinks for in-project testing (Claude Code)
│ ├── animate-dev -> ../../plugins/animate-dev/skills/animate-dev
│ ├── deploy-gdrive -> ../../plugins/deploy-gdrive/skills/deploy-gdrive
│ └── ...
├── .cursor/skills/ ← symlinks for in-project testing (Cursor)
│ ├── animate-dev -> ../../plugins/animate-dev/skills/animate-dev
│ ├── deploy-gdrive -> ../../plugins/deploy-gdrive/skills/deploy-gdrive
│ └── ...
├── plugins/ ← real skill files (source of truth)
│ ├── animate-dev/
│ │ ├── .claude-plugin/plugin.json
│ │ ├── agents/
│ │ ├── references/
│ │ └── skills/
│ ├── xapi-engineer/
│ │ ├── .claude-plugin/plugin.json
│ │ ├── agents/
│ │ ├── commands/
│ │ └── skills/
│ ├── figma-reader/
│ │ ├── .claude-plugin/plugin.json
│ │ ├── agents/
│ │ ├── commands/
│ │ └── skills/
│ ├── spec-writer/
│ │ ├── .claude-plugin/plugin.json
│ │ ├── agents/
│ │ └── skills/
│ ├── code-quality-review/
│ │ ├── .claude-plugin/plugin.json
│ │ ├── agents/
│ │ ├── commands/
│ │ └── skills/
│ └── deploy-gdrive/
│ ├── .claude-plugin/plugin.json
│ └── skills/
├── LICENSE
└── README.md
.claude/skills/ 和 .cursor/skills/ 內的 symlink 指向 plugins/ 中的真實 skill 目錄,讓你在此專案內即可直接測試 skill,不需全域安裝。編輯 plugins/ 下的 skill 檔案會立即反映到兩個工具。
Timothy Liao ([email protected])
MIT
npx claudepluginhub tim80411/ai-agent-extension --plugin spec-writer讀書會學習流程工具 — 從原文產生筆記、比對增補、Q&A 調查、導讀建議、Notion 發布
TunnelBox CLI usage guide — manage local static sites, servers, and Cloudflare tunnels via the tunnelbox command
Read Figma designs via link, extract structured page layout summaries with minimal context window usage
在 HTML 文件的 <head> 區段加入完整的 SEO 標籤結構和 Google Analytics 追蹤代碼
Package static website projects into zip files and upload to Google Drive with shareable links via gdrive CLI v3
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.