Deep analysis and problem solving with multi-dimensional thinking. Use when facing complex architectural decisions, strategic planning, or problems requiring thorough analysis…
Determine the conceptual proximity of a topic -- its parent topic, its most relevant sibling topics, and its most relevant child topics -- optionally grounded in Internet/Web…
Scaffold a SwiftUI iOS app (iPhone + iPad) with offline-first persistence, push notifications plumbing, SwiftFormat + SwiftLint, CI, and optional GitHub repo creation.
Investigate a codebase question using an isolated subagent. Use when you need to read many files without bloating the main context.
Extract all entity types (interventions, pathways, biomarkers, conflicts) from Google Drive transcript analyses using a three-stage LLM pipeline with Claude Opus 4.5 for…
Exposes Claude's reasoning chain as an auditable, decomposable artifact. Quick mode (default) gives assumption inventory + weakest-link in 2 stages.
Capture, persist, and query research findings across sessions through a 7-phase workflow with structural anti-skip enforcement.
Diagnosis and repair guide for errors and failures including CI. Use when user mentions something broken, errors, it doesn't work, CI failures, CIが落ちた, build errors, test — from…
Delete an API key (soft delete). Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports.
Vocalize Claude's last response using local Qwen3-TTS. Default voice is the Oracle (deep, resonant Dune narrator). Use --preset for emotion-controlled preset speakers.
Search for vectors using semantic similarity. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Evaluate a research source from report_notes, understand its purpose, and create a Linear issue.
nWave concierge — ask any question about methodology, project state, commands, migration, or troubleshooting. Read-only, contextual answers.
Runs autonomous loop fetching stories from GitHub Issues. Implements and closes issues as done. Triggers on "loop through my PRDs", "work on my issues", "start the autonomous…
Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 — from…
Checks for information leakage across module boundaries. Use when the user asks to check information hiding, when modules seem to change together, when implementation details leak…
Deploy to QA environment (QA1 or QA2). Use when deploying code to the QA testing environments via GitHub Actions. Includes pre-deployment checks for persistence.xml.
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/Al — from…
Start babysitting in non-interactive mode — no user interaction or breakpoints, fully autonomous execution.
ブラウザを手足のように操る。ページ遷移、フォーム入力、スクショ、なんでもこい。Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows.
Use when user asks to "create a skill", "make a command", "generate a prompt", "write a slash command", "build a Claude extension", or needs help crafting optimized skills and…
Technical research methodology using Context7, Exa, and Sequential Thinking for documentation, best practices, and complex investigations.
Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies. — from majiayu000/claude-skill-registry
Find quotes for a set of topic keywords and place them into a 2x2 matrix, spanned by the presence of an author/origin and by the literal containment of a keyword, optionally…
EXPERIMENTAL: Three-layer parallel meta-cognition analysis. Triggers on: /meta-parallel, 三层分析, parallel analysis, 并行元认知
AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic…
Get statistics for vector storage. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Think out loud about a problem, decision, or approach — Socratic friction to help you find clarity, not sympathy
Cheatsheet for the full task tracking and audit system — skills, modes, prompts, workflows
Constructive critic and stress-tester for ideas and proposals. Use when the user needs someone to challenge their thinking, find weaknesses, anticipate objections, or str — from…
Search research papers via Gemini for broad literature discovery. Use when user says "gemini search", "gemini papers", "search with gemini", or wants AI-powered literatur — from…
Narrow bare `rescue _ ->` / `rescue e ->` so UndefinedFunctionError, KeyError, and typos propagate instead of being swallowed.
Generates a contextual onboarding document for a new contributor or agent joining the project. Summarizes project state, architecture, conventions, and current priorities relevant…
First-principles, truth-seeking, zero-assumption section review. Decomposes the problem before judging the solution. Questions every decision. Red-teams inputs.
Deep collaborative analysis pipeline. Multi-perspective exploration, deep analysis, user-driven discussion loops, and cross-perspective synthesis.
Git change frequency hotspot analysis — find the most-changed files in your codebase
Integrates Power Pages generative-AI summarization APIs (PREVIEW) into a Single Page Application (SPA) site — the Search Summary API and the Data Summarization API — on any…
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants — from…
Execute a structured codebase exploration workflow to gather insights. Use when asked to "analyze codebase", "explore codebase", "understand this codebase", or "map the codebase".
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full — from…
Claude Gateway Discord 환경에서 파일을 Discord 채널로 첨부 업로드합니다. 응답에 FILE: /절대경로/파일명 형식으로 파일 경로를 포함하면 게이트웨이가 자동으로 감지하여 Discord로 전송합니다.
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/Al — from…
Analyze a book (EPUB/PDF) and generate detailed chapter-by-chapter notes with extracted key concepts. Use when given a book file path to process.
Reusable deep exploration and synthesis workflow. Use when asked for "deep analysis", "deep understanding", "analyze codebase", "explore and analyze", or "investigate codebase".
Quick entry point for structured knowledge elicitation with epistemic tracking. PROACTIVELY activate for: (1) interviews and requirements gathering, (2) problem definition, (3)…
Open the Cross-Code Organizer (CCO) dashboard — view and manage all memories, skills, MCP servers, hooks, and configs across scopes
Harnessダッシュボードを表示。現状を一目で把握できる司令塔。Use when user mentions '/harness-ui', dashboard, monitoring, or UI display.
Finds every file and location affected by a GitHub issue change. Use when scoping an issue, finding blast radius, or answering "what does this touch".
Scaffold or update a complete JPA persistence adapter (outbound adapter) — entity, JPA repository, mapper, and adapter class — for a domain aggregate.
프로젝트의 의존성, PRD, 구조를 분석하여 필수/선택 Rule을 자동 생성합니다. package.json, tsconfig.json 등 설정 파일과 문서를 분석하여 기술 스택에 맞는 Claude Rules 구조를 구성합니다. "프로젝트 룰 생성", "규칙 자동 생성", "프로젝트 분석해서 룰 만들어줘" 요청 시 활성화.
Delete a vector namespace and all its vectors. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Analyze an existing spec for inconsistencies, missing information, ambiguities, and structure issues.
Brutally honest engineering retrospective. Analyzes git history for what actually happened — not what people think happened.
Product Discovery Facilitator - Conduct a comprehensive interview to crystallize a fuzzy project vision into a complete MASTER_PRD.md.
Tạo một Claude skill mới theo đúng chuẩn Agent Skills. Dùng khi người dùng muốn tạo skill, tạo claude skill, hoặc thêm khả năng mới cho Claude trong project này.
Delete one or more vectors by key. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Get a value from the keyvalue storage. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
This skill should be used when the user asks to "create a ReAct agent", "build an agent with tools", "implement tool-calling agent", "use dspy.ReAct", mentions "agent wit — from…
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing.