Multi-agent orchestration system for coordinating parallel development work. Use when managing complex multi-workstream development, triaging failures, or coordinating parallel…
Discover and document existing systems with 10-phase brownfield analysis and drift detection workflows.
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…
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 existing MCP server implementation for optimization opportunities and best practice compliance. 分析現有MCP服務器實現，識別優化機會與最佳實踐合規性。
Analyze an existing spec for inconsistencies, missing information, ambiguities, and structure issues.
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
Builds, edit or validate Agent Skill through conversational discovery. Use when the user requests to "Create an Agent", "Optimize an Agent" or "Edit an Agent".
Generate a high-quality project CLAUDE.md and AGENTS.md by inspecting the current repository. Use when a repo has no agent config, when onboarding a new project, or when the user…
Drive cmux — the terminal multiplexer / agent-surface control CLI — from natural language. Use this whenever a prompt asks you to open, inspect, prompt, read, or tear down cmux…
Turn vague "what did I do?" into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates.
Execute a natural-language browser intent via page-agent (browser_act) when the target is easier to describe than to select — degrades gracefully when page-agent or an…
Builds new Claude Code agents with consistent structure, enforced standards, and project-aware configuration.
Build a project using Claude Code Agent Teams with tmux split panes. Takes a plan document path and optional team size. Use when you want multiple agents collaborating on a build.
Анализ решений арбитражных судов РФ (АС субъектов, Арбитражные апелляционные суды, АС округов, СКЭС ВС РФ, Президиум ВС РФ) по корпоративным вопросам.
[BETA] Dogfood the active branch end-to-end as a QA engineer. Diffs the branch against main, builds an exhaustive browser test matrix of every change (full user journeys, not just…
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports.
Set up Claude Code GitHub Actions for automated PR creation, code review, issue triage, and CI/CD automation. @claude mentions in PRs and issues.
Create, install, distribute, and manage Claude Code plugins. Marketplace setup, plugin structure, skills, agents, hooks, MCP servers, and community distribution.
[Tooling] Claude Code 스킬 표준 구조(SKILL.md + prompts/ + scripts/ + references/)를 자동 생성하는 스캐폴딩.
Claude Code のバージョンアップ後に、最新の公式推奨手法と現在の構成 （settings.json / commands / rules / skills / CLAUDE.md 等）を照合して改善提案を行う。 「Claude Code の最新機能」「アップデートレビュー」「設定見直し」「ベストプラクティス確認」…
Veille, reference et migration Claude Code. 3 modes : veille, reference, migration. Utiliser quand l'utilisateur demande les nouveautes Claude Code, veut documenter une…
Enable automated collaboration between Claude Code and Codex CLI using Byterover as shared memory. This skill should be used when architectural review or code validation from…
Generate or improve a CLAUDE.md file for any project following Anthropic's official best practices. Analyzes the codebase, detects stack and patterns, and produces a concise,…
Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat.
Audits Claude Code plugins for structure, quality, and best practices. Use when validating plugins, checking plugin health, or before publishing.
Audit skills for agentic orchestration quality. Checks subagent dispatch patterns, parallelism opportunities, anti-patterns, and alignment with the three-phase pattern (setup →…
Scan skills for prerequisite tools, MCP servers, and auth requirements, then check if everything is installed and authenticated. Offers to fix issues.
Audit skill SKILL.md files for compliance with the agentskills.io specification and house conventions.
CLUTCH v2 — Claude Layered Unified Team Coordination Hub. Resilient multi-phase orchestration with fail-fast guards, context budgeting, structured checkpoints, and workstream…
Hand off a task to Codex CLI for autonomous execution. Use when a task would benefit from a capable subagent to implement, fix, investigate, or review code.
Claude plugins marketplace setup: .claude/settings.json, GitHub Actions, plugin pinning. Use when onboarding to claude-plugins, setting up claude.yml, pinning plugins, or…
Deep Corefall BP-LEVEL closure review (BP0..BP12) with T-CAPTURE evidence, grading.json LLM-graded verdicts, Self-Play Validation Matrix, AI-Agent Self-Test Report, Universal…
Apply a simple code transform via agent-booster's WASM engine — sub-millisecond, deterministic, $0 (no LLM call). Companion to cost-booster-route.
エージェント、コマンド、スキルを統合的に作成する高度なメタコマンド。プロジェクト全体の一貫性を保ちながら、相互に連携する3つのコンポーネントを同時に設計・生成します。 実行は専門エージェントに委譲します。
Claude Code 커스텀 에이전트를 만들고 실행할 때 사용하는 스킬. 사용자가 "에이전트 만들어", "Claude agent 생성", "--agents 설정"을 요청하면 활성화됩니다.
Cert Domain 1 (27%): Agentic loops, multi-agent coordination, subagent spawning, handoff patterns, hook enforcement, task decomposition, session state.
Cert Domain 3 (20%): CLAUDE.md hierarchy, commands/skills config, path-scoped rules, plan mode vs direct execution, iterative refinement, CI/CD integration.
Deep exploration and synthesis workflow using Agent Teams with dynamic planning and hub-and-spoke coordination.
Split work across subagents with explicit contracts, interfaces, and merge strategies. Use when parallelizing tasks, distributing workload, or orchestrating multi-agent workflows.
Design new MCP server with interactive guidance and generate comprehensive JSON skeleton specification. 交互式引導設計新MCP服務器，生成完整JSON骨架規範。
Spawn and coordinate a pre-composed agent team from a team definition file. Reads team files from teams/, resolves agents and skills, picks the best spawning mode (peer or…
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
Discover happy paths on a target site using agent-browser, producing structured trace JSON for deterministic test generation.
This skill should be used when the user asks to "build a RAG pipeline", "create retrieval augmented generation", "use ColBERTv2 in DSPy", "set up a retriever in DSPy", mentions…
Full pipeline from ADO story to executed code. Runs requirements, planning, execution, build, review, commit, and PR in sequence with optional human review checkpoints.
Implement code from an RE spec as the Dev Agent — read requirements, implement changes, run self-check (build/test/lint), fix failures, and commit.
Map a described workflow to the right ECC command-GROUP with run-order and stop condition, and browse all command-group recipe families.
Multi-agent group discussion with dynamic participant selection. Use when "party mode".
This skill should be used when the user wants Claude Code to act purely as a manager/architect while Gemini CLI does all the coding work.
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge.
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge.
Generate or edit an image from a text prompt using the Gemini API or OpenRouter (Nano Banana / gemini-2.5-flash-image, FLUX, etc.).
Generate an MCP App widget (self-contained HTML) for an MCP tool. Describe the visual you want and paste your tool's test output.
Generate a single worker task prompt using the existing CLEAR + selective CoVe task design standard and the task structure requirements used by swarm-task-planner.
Submit MCP (Model Context Protocol) servers to 50+ directories, registries, and marketplaces for maximum discoverability.
Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements.
Converts any Claude Code skills repository into an official plugin marketplace. Analyzes existing skills, generates .claude-plugin/marketplace.json conforming to the Anthropic…
Wrap an MCP server as a yakOS agent so tool-side and LLM-side specialists share the same dispatch surface