Notionの仕様ページから実装タスクを作成するスキル。画面仕様や機能仕様を読み取り、実装タスクに分解してタスク管理データベースに登録する。「仕様からタスクを作成」「タスクに分解して」などの指示で使用。
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Notionの仕様ページから実装タスクを作成するスキル。画面仕様や機能仕様を読み取り、実装タスクに分解してタスク管理データベースに登録する。「仕様からタスクを作成」「タスクに分解して」などの指示で使用。
Docker コンテナを管理する。「コンテナ一覧」「docker ps」「コンテナ確認」「コンテナ止めて」「コンテナ起動」「コンテナ再起動」「コンテナに入って」「コンテナの状態」「実行中のコンテナ」「コンテナのリソース」「docker stats」「docker inspect」「コンテナのログ」「docker logs」などで起動。
Initializes and updates screen specification documents. Use as a foundation skill for all screen documentation workflows.
影響範囲を分析
提供内容营销、增长策略、社交媒体管理和应用商店优化能力。当需要创建营销内容、制定增长策略或管理社交媒体时使用。
将 Java 项目转换为标准 Maven 结构，自动重组目录、转换包名（test→example）并生成 pom.xml。当用户需要将非 Maven Java 项目转换为 Maven 项目、重构现有项目为 Maven 标准结构，或请求 Maven 项目设置/转换时使用此技能。
Coding specialist for COMAP MCM/ICM Problem C (C题数据处理与建模落地). Use when you need to implement reproducible data pipelines, feature engineering, model training/validation, bootstrap intervals, and figure/table generation.
Sanity-check & validation specialist for COMAP MCM/ICM Problem C. Use when you need to check whether results are plausible, stable, non-leaky, and rational.
Web research & external data acquisition specialist for MCM/ICM Problem C. Use ONLY when the problem statement explicitly allows or requires external/exogenous data, or when you need credible background context that does not enter the model inputs. Produces cited sources, cleaned datasets, and a reproducibility log.
Multi-persona product meeting with PM and CTO to discuss UX vs technical tradeoffs. Converts vague feedback into concrete requirements, updates REQUIREMENTS.md, and syncs with Linear.
EXPERIMENTAL: Three-layer parallel meta-cognition analysis. Triggers on: /meta-parallel, 三层分析, parallel analysis, 并行元认知
提供微服务分布式架构思考框架，涵盖服务拆分、通信机制、基础设施、治理策略、可观测性五大维度。当需要设计微服务系统、评审分布式架构、或需要全局视角审视服务边界与协同时使用。支持 DDD 领域建模、同步/异步通信、API Gateway、服务网格、熔断降级等分布式系统关键决策。
>
Draft patent claims based on: **$ARGUMENTS**
Draft a complete patent application based on: **$ARGUMENTS**
- skill
Gaggiuino skill for machine control, espresso shot analysis through profile intent, dial-in guidance, shot graph rendering, and synchronized overlay videos. Use when checking machine status, analyzing latest or historical shots, switching profiles, reading settings, or generating shot graphs and overlay videos.
仕様適合検証エージェント。仕様書から受入基準を抽出し、実装が仕様通りか敵対的に検証。BDDシナリオ生成・トレーサビリティマトリクス・適合レポートを発行。仕様ベースの品質ゲートが必要な時に使用。コードは書かない。
比較原始 spec-kit 與當前版本在設計上的差異
JSONスキーマ検証（JSON Schema Validation）機能の開発・修正を行う際に使用。ユーザー登録スキーマ、Identity Verificationスキーマ、外部API検証実装時に役立つ。
Implements a task locally (without worktree) following TDD with IPC status reporting. Use when working on a task in an existing branch.
当需要由 Gemini 作为总控代理，调用 Codex 通过 OpenSpec Skills 完成 propose、apply、测试验证、archive 全流程时使用。
在内置 spark-workflow 中，用于更大的 Apply 阶段；通过实现者与审查者分离的循环提升质量并控制上下文体积。
Fast, modern JavaScript runtime and toolkit. IMPORTANT: This is Bun, NOT Node.js. Use Bun-specific APIs below. Do NOT use Node.js APIs like require(), process, fs (use Bun.file() instead).
**Version**: 1.0.0
>
Use only when the user explicitly wants to build with the Agently framework (mentions Agently/agently/OpenAICompatible/TriggerFlow/ToolExtension/ChromaCollection, or says “用 Agently 做/用 agently 做”). Deliver runnable code plus regression tests validating schema/ensure_keys and streaming (delta/instant/streaming_parse), with optional tools (Search/Browse/MCP), TriggerFlow orchestration, KB (ChromaDB), and serviceization (SSE/WS/HTTP). Do not use for generic streaming/testing questions that are not about Agently, or for prompt-only writing without tests/structure.
从产品 PRD 产出“复刻级可落地”的 UI/UX 研发规格文档包（目录同构骨架、公共基座、组件/页面契约、覆盖映射、索引与 worklog）。适用于需要把 PRD 转成前端可复刻实现的规格文档、UI/UX 研发规格、界面契约与验收标准的场景；避免用于只要视觉灵感/纯 UI 赏析或直接写代码实现的请求。
Write comprehensive PRDs for AI Agent products—covering agent identity, capability architecture (skills, tools, memory, RAG, workflows), behavior specifications, safety guardrails, and evaluation frameworks. Use when: designing conversational agents, autonomous agents, copilots, multi-agent systems, or any LLM-powered agentic application. Triggers: 'AI agent PRD', 'agent product requirements', 'design AI agent', 'agent capability spec', 'LLM agent requirements', '智能体PRD', '智能体需求文档', '对话机器人PRD', '多智能体系统需求'. Anti-triggers: '传统PRD（非智能体）', '只润色提示词/只写Prompt', '只写用户故事/验收标准但不涉及工具调用、记忆或RAG'.
Build, debug, and maintain 香色闺阁/香色书源 JSON and XBS files. Use when users ask to create or fix book sources, convert between xbs and json, debug empty parsed fields, validate XPath and JS parser rules, or produce import-ready XBS outputs for the app.
通过goplaces命令行工具查询Google地点API（新版），用于文本搜索、地点详情、解析和评论。用于人性化的地点查找或脚本的JSON输出。
Cache-first and live-search access to Shanghai Jiao Tong University Shuiyuan Forum topics. Use when work involves Shuiyuan topic IDs or URLs, when the user wants you to search Shuiyuan for relevant posts or latest discussions, or when you need to trace a specific user's historical posts and related topics. Prefer local cache for known topics, but use live search first for discovery tasks.
- Respond in Japanese.
AI.MD v4 \u2014 The Complete AI-Native Conversion System workflow skill. Use this skill when the user needs Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
Expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality.
保研信息自动化跟踪-保包
- **React 18.3.x**
Fully local free text-to-image skill for OpenClaw and general assets. Generates SVG from prompt, then converts SVG to PNG with local tools only (no online API calls).
>
Record semantic history (.intent/) — goals, snapshots, and decisions that persist across agent sessions. Triggered when user asks to record semantics.
claude-to-im
構造化されたアプリ開発と問題解決のためのトークン効率の良いSerena MCPコマンド。デバッグ、設計、レビュー、実装のパターンを提供し、インテリジェントな開発支援を実現します。
This skill helps you systematically assess where Bitcoin sits in its market cycle — from extreme fear (accumulation opportunity) to extreme greed (distribution/exit signal). Through a weighted evaluat
>-
Provides comprehensive guidance for Rspack bundler including configuration, plugins, loaders, optimization, and Webpack compatibility. Use when the user asks about Rspack, needs to configure Rspack, optimize build performance, or migrate from Webpack.
Intelligently organize and categorize Markdown notes within an Obsidian vault. This skill leverages Obsidian MCP tools to analyze the vault's current folder structure and note content, ensuring new or misplaced notes are moved to their most contextually appropriate locations (e.g., PARA, Zettelkasten, or custom taxonomies).
.claude/skills/api-versioning/SKILL.md
autocli
不安全代码与 FFI 专家。处理 unsafe, raw pointer, FFI, extern, transmute, *mut, *const, union, #[repr(C)], libc, MaybeUninit, NonNull, SAFETY comment, soundness, undefined behavior, UB, 安全抽象, 裸指针, 外部函数接口, 内存布局, 未定义行为
使用 Chrome DevTools MCP 进行前端页面调试、布局优化、性能诊断及交互验证。