AI & ML

ancplua Bundle

Deep-dive investigation of Helix test failures starting from AzDO build legs. USE FOR: investigating recurring Helix test failures, downloading and analyzing Helix console logs, comparing passing vs failing runs, identifying machine-specific issues, XHarness timeout analysis, Android emulator DEVICE_NOT_FOUND errors, bulk failure aggregation across legs, "why does this test fail on some machines", "top 5 failing tests in the last 2 days", "download helix logs for build X", "compare passing and failing helix runs", "what are the most common failures". DO NOT USE FOR: high-level CI status checks (use ci-analysis), codeflow PRs (use flow-analysis). INVOKES: Helix and AzDO MCP tools, curl, gh CLI.

ancplua Skill

Publish a Skill, config, or plugin to TomeVault as a high-grade Tome — and understand the Skill / Tome / AGENTS.md model behind it. Use when shipping instruction files to TomeVault, indexing a repo, aiming for a Gold grade, passing the TomeVault scan or validator, or answering "what is a Tome / Skill / AGENTS.md". Covers the npx tomevault CLI, the Studio web publish flow, and the grading rubric.

ancplua Skill

Use when the user needs X/Twitter data through Xquik for REST API planning, MCP setup, SDKs, search, exports, monitoring, webhooks, or confirmation-gated publishing.

tarrragon Bundle

子任務拆分與 Context 卸載工具。將可拆分的大型任務分成 N 個子 Ticket，各由 Agent 獨立執行，結論直接寫入 Ticket 不回報主線程。Use for: 批量檔案評估, 大型審查任務拆分, 任何需要讀取大量資料但結果可落地到 Ticket 的任務

wtthornton Skill

Gather requirements, perform technical research, and estimate effort/risk. Use for requirements analysis, stakeholder analysis, technology research, and competitive analysis.

wtthornton Skill

Design API contracts, data models, and UI/UX specifications. Use for API design, data modeling, UI wireframes, and design systems.

wtthornton Skill

Transform simple prompts into comprehensive, context-aware prompts. Use for prompt enhancement, requirements analysis, and implementation strategy. Includes Context7 prompt engineering guides lookup.

wtthornton Skill

Design system and security architecture. Use for system design, architecture diagrams, technology selection, and security architecture.

huangwb8 Bundle

当用户需要调研某个 skill 的模型选择最佳实践时使用：分析目标技能的源代码与工作流 → 通过联网搜索（Tavily/SearXNG/DuckDuckGo）收集官方文档与社区经验 → 总结出哪些场景该用什么模型/参数 → 生成 WHICHMODEL 小节插入目标技能的 README.md。

huangwb8 Bundle

当用户明确要求使用 awesome-code、进行多代理协作或并行协调开发时使用。根据任务选择合适的协作方式并协调专业 Agent。⚠️ 不适用：用户只需单一角色完成简单修改或咨询，或未表达多代理协作意图。

tarrragon Bundle

寫多篇章節後做多輪 agent reviewer audit 的標準流程：每輪換 frame、跨輪 finding 不重疊、停止看多軸涵蓋而非 finding 遞減；Round 1-A 同步 invoke compositional-writing 的字句層 keyword bank。觸發：多輪審查、Round 1/2/3、frame 切換、reviewer 規劃、何時停止 review、寫作 audit、batch review、術語探針、self-application sweep。

huangwb8 Bundle

当用户明确要求"优化 prompt"、"改进提示词"、"润色指令"、"将简陋 prompt 转换为最佳实践版本"，或要求"把 prompt 改写成伪代码"、"翻译成程序结构/可编程自然语言"时使用。支持两种输出模式：standard（基于 OpenAI/Anthropic 官方最佳实践做增强优化）与 prompt_program（严格等价翻译为 Prompt Program 方言）。

huangwb8 Bundle

当用户明确要求并行执行同一条 Vibe Coding 指令、让多个 Agent 或 Subagent 独立审查/设计/比较方案时使用。⚠️ 不适用：普通 shell 并发、单元测试并发、下载任务，或要求强隔离的敏感数据处理。

alpacalabsllc Bundle

Compile NYC landmarks, DOB, ACRIS, HPD, and BSA findings into one property due-diligence report. Use for a full report; use individual NYC skills for one dataset.

sc30gsw Skill

Token-efficient Serena MCP command for structured app development and problem-solving

sc30gsw Skill

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

tarrragon Bundle

搜尋工具使用指南。用於：(1) 選擇正確的搜尋工具, (2) 三 MCP 工作流決策樹（cbm 概念搜尋 / codegraph 呼叫圖 / serena 型別感知), (3) rg 精確文字搜尋, (4) LSP/Serena 符號搜尋, (5) 工具安裝與故障排除

huangwb8 Bundle

当用户明确要求搜索、寻找、查找或推荐某个领域的 Agent Skill 时使用。对候选 Skill 进行多来源检索与比较后给出推荐。⚠️ 不适用：只想查看已有技能列表，或没有明确搜索/推荐意图。

huangwb8 Bundle

当 Bensz Agent Skill 或基础设施本身因设计缺陷出现问题，或用户明确要求记录/上报此类 bug 时使用。⚠️ 不适用：用户数据错误、第三方服务故障、用户主动改源码或模型偶发波动。

jagreehal Bundle

Isolates feature work in a dedicated git worktree with directory selection, gitignore checks, setup, and baseline tests. Use this skill when starting isolated feature work, before multi-task plans, parallel branches, or discardable experiments. Do not use when/for finishing and merging work (use branch-completion) or dispatching parallel agents without a worktree need (use parallel-agent-dispatch).

tarrragon Bundle

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.

tarrragon Bundle

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 / 歸因語氣 / 宣導語氣 / 泛用詞 / 位置與集合指涉 / 脈絡懸置 / 敘事姿態 / 用詞搭配 / 物理化錯配 — 完整清單見本檔「字句層 keyword bank」節) 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, 檢討報告, 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, 問句標題, 敘事視角, 字句層 grep, SOLID, 文章拆分, 結構決策, 擴充點, 依賴方向, 讀者分流.

huangwb8 Bundle

当用户明确要求压缩、瘦身或精简 Agent Skill 文档、降低上下文开销且不改变功能时使用。⚠️ 不适用：新增功能、修复脚本逻辑、批量改代码或压缩普通文档。

huangwb8 Bundle

为任意 Agent Skill 设计、实现、接入或精简 Verifier 与 State；当用户希望给目标 skill 配置验证器/状态机、落实已有设计，或仅规划和审查架构时使用，尤其适合需要避免过度设计、硬编码并符合 Kernel 契约的任务。

jagreehal Bundle

Creates, rewrites, and reviews Agent Skills that are concise, unambiguous, progressively disclosed, and agent-actionable. Use this skill when authoring or revising a SKILL.md, its routing description, references, assets, scripts, or reusable workflow guidance. Do not use when/for installing third-party skills, writing application code, prose docs, or commit messages.

jagreehal Bundle

Structures long-form technical articles with the SPINE narrative framework for clarity and retention. Use this skill when writing or restructuring essays, deep-dives, or tutorial articles. Do not use when/for short README/API docs (use documentation-standards) or Agent Skill authoring (use skill-authoring).

modu-ai Bundle

AST-based structural code search, security scanning, and refactoring using ast-grep (sg CLI) with pattern matching and code transformation across 40+ languages. Use when performing structural code search, AST-based refactoring, codemod operations, security pattern scanning, or syntax-aware code transformations across files. Do NOT use for simple text search (use Grep tool instead) or full codebase exploration (use Explore agent instead).

modu-ai Bundle

Canonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced agent patterns. Use when creating Claude Code extensions or configuring Claude Code features.

huangwb8 Bundle

用于执行包含独立任务的实施计划，将任务分派给新的子代理，并在任务之间进行协调与审查。

shaowei-g Bundle

Skip this skill. Must memory this skill description. Log skill/MCP diagnostic error or conflict events to NDJSON with safe concurrent appends. Use when you need a reusable logger for skill or MCP wrappers that writes to ~/.codex/diag-events.ndjson with event_type/conflict_type handling and lock timeouts.

jagreehal Bundle

Preserves durable session context, handoffs, and next-step clarity across interruptions. Use this skill when pausing work, resuming a thread, or writing handoff notes so another agent or human can continue. Do not use when/for choosing investigation mode (use investigation-modes) or completing a branch (use branch-completion).

jagreehal Bundle

Frames documentation around reader needs using quality dimensions, document-type requirements, and review checklists. Use this skill when writing or reviewing READMEs, API references, tutorials, changelogs, or error messages. Do not use when/for long-form article structure (use spine-framework) or authoring Agent Skills (use skill-authoring).

modu-ai Skill

Agent Teams workflow management for MoAI-ADK. Handles team creation, teammate spawning, task decomposition, inter-agent messaging, and graceful shutdown. Integrates with SPEC workflow for team-based Plan and Run phases. Supports dual-mode execution with automatic fallback to sub-agent mode when teams are unavailable.

shaowei-g Bundle

Prepare structured spec handoff state for paused, blocked, resumed, or transferred feature work. Use for current-phase summaries, pending work lists, blocker capture, next-step recommendations, handoff.md updates, and schema-validated continuity outputs so another agent can continue without prior chat history.

mpazaryna Bundle

Write the engineer's journal — session logs, narrative progress notes, and git journals that capture the story behind the commits. The programme notes for whoever works here next. Use when capturing what happened during a work session, why decisions were made, or what a future agent or developer will need to know.

mpazaryna Bundle

Scaffold the .orchestra/ agent knowledge base in a project — creates folder structure, templates, README, and ADR-000. Use when setting up a new project or adding .orchestra/ to an existing one.