메뉴
Sync Claude Code skills between local .claude/skills/ and a remote skills repository. Use for: pulling skills from remote, pushing local skills to remote, listing available remote skills.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | skill-sync |
| description | Sync Claude Code skills between local .claude/skills/ and a remote skills repository. Use for: pulling skills from remote, pushing local skills to remote, listing available remote skills. |
Sync Claude Code skills between local .claude/skills/ and a remote skills repository.
uv tool install --from .claude/skills/skill-sync skill-sync
| Command | Description |
|---|---|
skill-sync pull | Auto-compare all installed skills with remote versions.json, pull outdated ones automatically. Conflicts (local newer) are reported but not modified |
skill-sync pull <name> | Pull a specific skill from the remote repo to .claude/skills/<name>/ |
skill-sync push <name> | Push a local skill to the remote repo |
skill-sync list | List all available skills in the remote repo |
| Environment Variable | Default | Description |
|---|---|---|
SKILL_SYNC_REPO | https://github.com/tarrragon/claude-skills.git | Remote skills repository URL |
project-integration/ subdirectories are excluded from both pull and push operationsVersion: 1.1.0
UX / UI 設計的系統性評估方法：把「使用者被困住」類缺口從實機測試提前到設計階段。Use for: (1) 設計或審查畫面狀態（狀態矩陣四欄：顯示 / 可用操作 / 進入條件 / 退出路徑，退出路徑為空 = 死胡同）, (2) Gate 設計（biometric / network / permission / 環境條件的成功、失敗、不確定路徑與 fallback）, (3) 輸入機制（keyboard type / submit model / IME policy / special keys 四維決策、IME 安全）, (4) 錯誤恢復（錯誤訊息、retry、error loop 逃生口、degraded mode）, (5) 導航（go/push 語意、tab / drawer / deep link、iOS vs Material 慣例）, (6) 互動回饋（回饋分層、時間門檻、spinner vs skeleton、SnackBar / Dialog / Banner 選擇、元件語意與版面：切換標籤 / 可點性辨識 / 選中態對比 / 溢出 affordance / 版面保障 / 完成宣告）。Use when: 設計新畫面或流程、審查 UI 實作、UX review、使用者反映被卡住 / 按了沒反應 / 標籤被讀反 / 選中看不到字 / 文字被壓成省略號 / 宣告完成但資料不全 / 通知被忽略。Triggers: UX 設計, UI 設計, 畫面設計, 狀態矩陣, 退出路徑, 死胡同, initializing, gate, fallback, 生物辨識, 權限請求, 破壞性操作, 輸入框, 鍵盤, IME, 表單, 搜尋框, 錯誤訊息, retry, 重試, 降級, degraded, 導航, back 行為, deep link, hash 路由, tab bar, service worker, loading, spinner, skeleton, SnackBar, Dialog, Banner, Bottom Sheet, 通知形式, 按鈕狀態, 切換模式, 標籤語意, 選中態, 對比, 溢出, 截斷, 省略號, ellipsis, 佔位, placeholder, 完成宣告, debounce, 防連點, 回饋.
Use this skill whenever the user wants to create, track, query, or manage tickets. Triggers include: creating new tickets, claiming or releasing tickets, checking ticket status or progress, completing tickets, handing off work between agents, resuming interrupted tasks, migrating tickets between versions, converting plans to tickets, splitting tickets into subtasks, evaluating ticket granularity, or any mention of /ticket, task tracking, ticket lifecycle operations, or ticket splitting. 拆分相關：當用戶問「ticket 怎麼拆」「拆分粒度」時，建立/拆分 ticket 用本 skill，拆分邊界判讀（測試變綠驗收點）見 /tdd skill 的 task-granularity-rules。
WRAP 決策框架 — 認知偏誤防護、選項擴增與資料充足度閘門。用於防護自動駕駛、假選項、證據不足下的倉促決策。內含完整 premortem 流程（失敗原因並行深挖 + 綜合報告），適用版本規劃、提案評估、發版前等高成本決策。Use when: 被困住或連續失敗 2+、準備宣告限制性結論前、偏離核心目標、根因分析、代理人失敗歸因、提案評估、重大架構或規則決策、個人化建議（健康/醫療/金錢/法律）前、Context 沉重時、需要對計畫做事前風險推演時。Triggers: stuck, blocked, loop, no progress, 分析, debug, 限制性解法, 個人化建議, 具體推薦, premortem, 事前驗屍, 事前假設失敗, 壓力測試計畫, 這計畫會怎麼死, 找出盲點。
寫多篇章節後做多輪 agent reviewer audit 的標準操作流程。每輪用不同 frame 切換、跨輪 finding 互不重疊、停止訊號是 frame 涵蓋而非 finding 數遞減。Round 1-A 寫作規範 reviewer 必須同步 invoke `compositional-writing` skill 的字句層 keyword bank（正向陳述 / 口語修辭 / 地區用語 / 廢話前綴 / 裝飾符號 / 對讀者喊話 / 自評誇飾 / 必然性框架）、且命中後要做語意判定（命中是候選不是判決）。觸發詞：多輪審查、Round 1/2/3、frame 切換、跨輪審查、reviewer 規劃、何時停止 review、寫作 audit、batch review、cadence 同骨化、enumeration 不窮盡、正向陳述、self-application sweep。Trigger when reviewing multiple writings via successive rounds of agent reviewers.
Composes atomic, intent-revealing, grep-friendly writing (Zettelkasten) for code comments, docs, logs, prompts, schema/ticket fields, external-analysis transformation, and long-form technical articles. Use when cognitive load and token cost matter. **Also triggers during multi-round review / batch review / 寫作 audit** — provides the keyword bank (正向陳述 / 口語修辭 / 地區用語 / 廢話前綴 / 裝飾符號 / 對讀者喊話 / 自評誇飾 / 必然性框架 / 澄清式框架) and frame-specific check lists that multi-round-review reviewer agents need. Triggers: 寫註解, 寫文件, 寫日誌, 寫 prompt, 寫文章, 技術文章, 商業分析, 外部分析文章, 經驗談轉教學, 訪談整理, 機制重建, post-mortem, 架構決策, 除錯復盤, 欄位設計, atomic, reusable, 多輪審查, multi-round review, batch review, 寫作 audit, 正向陳述, 口語修辭, 字句層 grep.
CLI 工具教學文章的驗證導向生產流程：分類決定驗證分工（非互動 vs 全螢幕 TUI）、Docker 可拋棄 fixture、三層標註（驗過 / caveat / 移除）、實跑 gotcha 回寫。官方 docs fact-check 會放過版本差異與實作落差、只有實機跑過才能抓到。觸發詞：CLI 工具文章、工具教學、驗證流程、Docker fixture、實機驗證、gotcha、tool article、CLI tutorial、verification workflow。Trigger when writing CLI tool tutorial / tool comparison articles.