3499 Claude Code skills tagged Agent. Browse all AI provider, model, or runtime-related skills in the open ClaudSkills registry — free to install, one-click via the desktop app.
Showing top 200 of 3499 skills, ranked by quality score.
Run a health check on an existing project: dependency audit, security scan, test runner detection, CI/CD evaluation, and missing configuration analysis. Maps the three execution ga
security
Research and recommend an MVP deployment platform by combining tech-stack context, a short developer interview, and parallel web research scored against five agent-friendly platfor
science
Assess an existing project's stack for agent-friendliness using the 4 quality gates (typed, convention-based, popular in training data, well-documented) as an evaluation lens. Dete
product
Pick a starter and a stack for a greenfield project after the PRD is written. Reads context/foundation/prd.md, opens with a Q0 path-fork (recommended default for the (product_type,
product
A measurement-first decision discipline for choosing HOW to build something. Before pouring effort into one approach, operationalize a measurable fitness, sketch a few candidate di
general
Multi-agent code review using Agent Teams. Summons up to 8 built-in Ashes (plus custom Ash from talisman.yml), each with their own dedicated context window. Handles scope selection
general
멀티 에이전트 병렬 실행 오케스트레이터. cmux 터미널 멀티플렉서 위에서 여러 Claude Code 인스턴스를 동시에 실행하고, 파일 기반 IPC 메시지 버스로 에이전트 간 메시지를 교환하며, cmux wait-for 시그널로 동기화한다. 백엔드끼리, 프론트끼리, 또는 풀스택 파이프라인 등 어떤 조합이든 지원. 기존 레
product
Multi-agent planning workflow using Agent Teams. Combines brainstorm, research, validation, synthesis, shatter assessment, forge enrichment, and review into a single orchestrated p
science
Crea aplicaciones Lowcoder (low-code platform) desde código usando el SDK @aorizondo/lowcoder-agent-sdk-core o el MCP server @aorizondo/lowcoder-mcp-server. Usa esto cuando el usua
tools
Débat multi-agents avec 6 IA pour valider PRD et code. Utiliser pour obtenir des perspectives diverses sur des décisions critiques, après un PRD en mode FULL, ou après une code rev
product
Predicts the highest-impact next action for your project by running a 5-agent meta-DAG pipeline. Gathers project signals automatically (git, recent files, port-daddy, CLAUDE.md), t
engineering
Lightweight natural-language git commit helper. Interprets the argument as either a glob, a filter phrase ("except tests", "only new files"), a topic phrase ("the auth changes"), o
general
Create a GitHub pull request from the current branch — validates preconditions, discovers PR templates, analyzes commits and file diffs, references PRP artifacts (prds/plans/report
product
Multi-agent work execution using Agent Teams. Parses a plan into tasks, summons swarm workers that claim and complete tasks independently, and runs quality gates before completion.
general
Orchestrate multi-agent development sprints with wave-based parallelism. Use when the user wants to plan a swarm sprint, partition work into file-disjoint waves, map file contentio
science
Этот скилл MUST быть вызван когда есть design.md и нужно разбить доработку на атомарные задачи (2-5 мин) с точными путями файлов и критериями проверки в tasks.md. SHOULD также вызы
general
Low-level SDK install and conversation logging only. Most users should use greenflash-onboard-unified instead — it auto-detects the codebase and runs the full guided setup, delegat
general
AG-UI (Agent-User Interaction) protocol reference for building AI agent frontends. Use when implementing AG-UI events (RUN_STARTED, TEXT_MESSAGE_*, TOOL_CALL_*, STATE_*), building
engineering
Guide for authoring specialized AI agents. Use when creating, updating, or improving agents, choosing models, defining focus areas, configuring tools, or learning agent best practi
general
Agent-based modeling skill for simulating complex adaptive systems with heterogeneous interacting agents
general
Browser automation for web testing, form filling, screenshots, and data extraction. Use when navigating websites, interacting with web pages, filling forms, taking screen — from di
engineering
Browser automation for web testing, form filling, screenshots, and data extraction. Use when navigating websites, interacting with web pages, filling forms, taking screen — from di
engineering
Conversation patterns and interaction protocols for multi-agent systems. Covers request/response, pub/sub, blackboard, delegation chains, debate, critique, consensus, fan-out/fan-i
engineering
Use when creating or configuring Claude AI agents using the Agent SDK. Covers agent initialization, configuration, and basic setup patterns. — from TheBushidoCollective/han
tools
Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, err
engineering
Orchestrates multi-agent workflows by delegating ALL tasks to spawned subagents via /spawn command. Parallelizes independent work, supervises execution, tracks progress in UUID-bas
general
Self-contained multi-platform internet search and read skill. Zero external dependencies — calls upstream tools (curl+Jina, gh, yt-dlp, xreach, mcporter) directly and degrades grac
content
Multi-agent deliberation for Claude Code - orchestrate AI coding assistants (Claude, Codex, Gemini) for council, debate, and consensus workflows
general
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attac
security
Export reusable assets from a project into this repository's v0.2 plugin architecture (skills, templates, agents).
engineering
Import external reusable assets into this repository's v0.2 plugin architecture (skills, templates, agents).
engineering
What you can build and do with an always-on AI agent that has episodic memory. Covers concrete product ideas, workflows, emergent capabilities from persistence plus memory, and rea
engineering
Architecture and systems design for building always-on AI agents with episodic memory. Covers the memory hierarchy (core/recall/archival), persistence layers, agent server infrastr
engineering
How to design contextual inputs for an always-on AI agent with episodic memory. Covers what data to feed the agent, how to structure observations and triggers, ambient context capt
engineering
Safety, privacy, cost management, and frank advice for building always-on AI agents with episodic memory. Covers data hygiene, privacy risk surfaces, runaway cost prevention, scope
engineering
Use atrib as your literal substrate for memory, reasoning, and getting smarter over time, not as instrumentation that observes you from the outside. atrib gives the agent six cogni
general
AWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale. Use when working with any AgentCore service including Gateway, Runtime, Memory, Identity,
engineering
AWS Bedrock AgentCore comprehensive expert for deploying and managing all AgentCore services. Use when working with Gateway, Runtime, Memory, Identity, or any AgentCore c — from en
engineering
OrchestKit security wrapper for browser automation. Adds URL blocklisting, rate limiting, robots.txt enforcement, and ethical scraping guardrails on top of the upstream agent-brows
security
Opens browser at URL for E2E testing via playwright-cli. Provides CLI commands for navigation, screenshots, and interaction. Triggers on keywords: browser, open browser, playwright
engineering
GLAW Investigations Bureau — the Case Commander. An FBI-style multi-agent investigative department that runs Field, Cyber, OSINT, HUMINT, Financial-Crimes, Legal-Intelligence, Coun
security
Kubernetes operator for Gas Town multi-agent orchestration. Triggers on "create polecat", "spawn worker", "kubernetes polecat", "deploy convoy".
engineering
Use when creating or configuring Claude AI agents using the Agent SDK. Covers agent initialization, configuration, and basic setup patterns. — from tools/tools-misc
tools
Use when managing agent context, memory, and conversation state in Claude AI agents using the Agent SDK.
tools
Convert functionality into Claude Code automation. Use when the user says "agentify", "agentic", "automate this", "create an agent", "make a plugin", "make a skill", or wants to au
general
Reference guide for CLI-Anything, which auto-generates production-ready agent-controllable CLI harnesses for any GUI application via a 7-phase pipeline. Use when the user asks abou
tools
Generate a self-updating CLI repo from an API documentation URL. Use when the user says "/clify <url>", "generate a CLI for this API", or wants to create agent-friendly API wrapper
tools
Collaborative multi-agent fix workflow using codex, gemini-cli, and an independent subagent. Use when the user asks to "collab fix", "multi-agent fix", or wants several AI tools to
science
Automatically assigns GitHub issues to appropriate GitHub Copilot agents based on issue type, labels, and content. Triggers on "assign agent", "who should work on this", "route thi
general
Orchestrates complex multi-agent workflows for features requiring coordinated work across multiple GitHub Copilot agents. Triggers on "orchestrate workflow", "coordinate these agen
general
Create agent-optimized CLI skill documentation. Use when: (1) "create a skill for <CLI>", (2) "document <CLI> for agents", (3) adopting a new CLI tool that needs an agent-friendly
tools
Production-grade agentic system development with LlamaIndex in Python. Covers semantic ingestion (SemanticSplitterNodeParser, CodeSplitter, IngestionPipeline), retrieval strategies
engineering
Orchestrate the outreach pipeline. Scans Person notes for the `pipeline_stage:` frontmatter field, picks prospects ready to advance, and spawns fresh-context Agent-tool subagents i
sales
Watch a PR — auto-respond to comments and CI failures. Uses bin/divecode-pr-watch which polls via gh and emits a routing decision (status + route). 6-status / 7-route routing per a
general
Deep research aggregator that searches Brave (Web), Perplexity (AI), GitHub (Code/Issues), ArXiv (Papers), YouTube (Videos), and Wayback Machine simultaneously. Provides a consolid
science
Финализация задачи: Serena memories, agent-only files, fullrepo, git/GitHub, branches, worktrees. Используй после ry-start/review/deploy/newp. Используй для: заверши задачу, синхро
general
Full LP workflow from opportunity scanning to position entry. Autonomously finds the best LP opportunity, designs a strategy, assesses risk, executes any needed swaps, enters the p
general
Multi-agent PR code review. Dispatches 3 parallel reviewers: bugs finder, security auditor, and code quality reviewer. Produces a single consolidated review report. Inspired by Ant
engineering
Multi-agent regulatory council that drafts, fills, and generates all SEC/FINRA/state filings and compliance documents for tokenized fund offerings. Covers Form D (EDGAR), Form ADV
general
**v1.0 AGENTIC PIPELINE**: 6단계 에이전틱 아이디어 팩토리! 프로젝트분석→카테고리분류→아이디어기획(병렬)→기획팀장→PRD개발팀장→CTO최종결정. 4team-review 통합, 상위 0.001% 전문가 수준 기획문서 자동 생성.
product
Install skills, agents, and teams from agent-almanac into any supported agentic framework using the CLI. Covers framework detection, content search, installation with dependency re
general
LangChain 框架学习笔记 - 快速查找概念、代码示例和最佳实践。包含 Core components、Middleware、Advanced usage、Multi-agent patterns、RAG retrieval、Long-term memory 等主题。当用户询问 LangChain、Agent、RAG、向量存储、工具使用、记忆系统时使用
general
Human interface agent that translates ecosystem activity into clear, actionable communication. Creates status briefings, decision requests, celebration reports, concern alerts, and
general
Stateless one-shot skill execution and controlled-variable comparison. `single` mode runs any deck against any task with zero local state — no install, no working-set pollution, no
general
Configure multi-machine LAN mesh for swarm-llm (netllm). Use when the user asks to set up a swarm, connect multiple machines (macOS, Linux, Windows), enable LAN routing, find peers
general
A building experience: create, test, validate, refine, and publish extraction workflows based on existing or new Nimble agents. For users who want to invest in a durable, reusable
general
Run multiple Ralph loops concurrently for independent tasks. Manages parallel agent execution with proper isolation and result aggregation. Use when: (1) multiple independent fixes
general
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, si
tools
Read-only multi-agent ship queue dashboard. Shows what each agent is shipping, what's in flight, what version slots are claimed, and what /ship would pick next. Reads from fstack b
general
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, ag
general
Execute plan tasks via fresh-context subagents (swarm mode)
general
Use when choosing between supervisor, swarm, or pipeline coordination for multi-agent workflows, when two agents produce conflicting findings and deduplication is needed, when TOME
general
Stochastic multi-agent consensus. Spawns N agents with identical prompts to independently analyze a problem. Aggregates by consensus (mode), divergences (splits), and outliers (uni
general
Test-Driven Development debug workflow combined with multi-agent collab-fix. Use when the user asks to "TDD debug", "reproduce and fix with a test", or wants a bug fixed with a fai
engineering
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing
engineering
Backing skill for the /ultra:run and /ultra:resume slash commands — multi-agent swarm with adversarial validation, structured debates, devil's advocate, and anti-AI-slop checks. Us
general
AI-powered virtual laboratory orchestrating multi-agent scientific research teams for autonomous hypothesis generation, experimental design, and validation in biomedical research.
science
Scaffolding completo: estrutura de pastas, configs, .env.example, CI base, README. Projeto nasce agent-ready.
general
Debate multi-agente: 2-4 perspectivas (PM, Arquiteto, QA, Security) debatem decisao tecnica. Output: decisao + rationale + dissenting opinions → ADR. Inspirado no Party Mode do BMA
security
Create a new Claude Code agent file (review or team type) following the official sub-agent schema and token-efficiency budgets. Use when the user wants to add a new review agent, d
general
**DEFAULT for authoring or refining an Ultraprompt agent — produces a new agent definition with frontmatter, body, tool permissions, and orchestration plan.** Different from /skill
general
Создание нового агента (AGENT.md) с промптом, конфигурацией и регистрацией в README. Используй при добавлении нового AI-агента для автоматизации задач проекта.
general
Lint a BDK agent file for best practices and portability. Use when reviewing, creating, or editing an agent (agents/*.md) to verify it meets BDK conventions. Trigger on phrases lik
general
Spawn, list, inspect, and stop sub-agents through the wrapper. Sub-agent config travels as a JSON-serialized string. Flat parameter surface.
tools
Обновление конфигурации, деактивация или переименование агента. Используй при изменении промпта агента, смене модели, деактивации устаревшего агента или миграции на новое имя.
general
Manage restore context files so skills can survive /clear and /compact. Use to write, delete, check, or list .agent-restore-context-* files.
general
Use when: auditing agent instructions, skill files, SKILL.md artifacts, prompt-packaged workflows, AI assistant instruction artifacts, custom agent modes, or reusable assistant gui
general
Agent Team で Issue から PR まで並列実行する開発フロー。「workflow-agent-team-issue」「エージェントチーム Issue フロー」「チーム Issue 開発」「Agent Team Issue」「Issue から並列実装」「チームで PR 作成」「Agent Team で Issue 対応」などで起動。workfl
general
Проверка AGENT.md на соответствие стандарту — frontmatter, промпт, секции, ссылки. Используй после создания или изменения агента, при code review или перед коммитом.
general
Multi-agent orchestration system for coordinating parallel development work. Use when managing complex multi-workstream development, triaging failures, or coordinating parallel age
general
Discover and document existing systems with 10-phase brownfield analysis and drift detection workflows.
general
Bootstrap an AWS EKS cluster optimized for Agentic AI workloads — Karpenter v1.2+ GPU node pools, EKS Auto Mode, Kubernetes 1.32+ with DRA 1.35 GA, VPC CNI, GPU Operator, and basel
engineering
Interactive tool to generate tailored rules and instruction files for any AI coding agent. Use when the user asks to set up agent rules, configure Claude Code instructions, create
content
Run the OWASP-aligned agentic security review path — covers goal hijacking, tool misuse, excessive agency, memory poisoning, secrets exposure, handoff failures, and observability.
security
Wraps the Research Preview `claude agents` CLI (CC 2.1.139+) and `claude plugin details ork` for live observability of parallel agent sessions. Surfaces running/blocked/done state,
science
Get details about a specific agent. Requires authentication. Use for Agentuity cloud platform operations — from tools/cli-builders
tools
**DEFAULT for AI agent safety reviews — dispatches security-auditor + risk-and-controls-reviewer with AI/agent safety focus.**
security
Use when designing or improving AI engineering workflows after the stack direction is already mostly known. Covers prompt pipelines, MCP integrations, tool-using agents, reusable w
engineering
PRIMARY skill creator. Use this by default when creating ANY skill. If user explicitly asks for a "Claude skill", "Claude-compatible skill", or "universal skill", use agent-skill-c
general
Analyze an existing spec for inconsistencies, missing information, ambiguities, and structure issues. Use when user says "analyze spec", "review spec", "spec quality chec — from ma
general
Multi-agent audit for Next.js + React + Supabase apps. Ten specialist auditors run in parallel, findings get validated, and a ranked evidence-backed report is written to `.anthril/
engineering
Deploy a QA agent swarm to analyze the codebase and produce a prioritized findings report, implementation spec, and test plan. Use when the user wants to run QA analysis, find bugs
security
Unified ATV security audit. Scans agentic config (.github/, .vscode/) using AgentShield's 33-rule taxonomy AND application source code for OWASP Top 10 + STRIDE threats. Triggers o
security
Zero-tolerance multi-agent code annihilation system. Spawns parallel brutal agents for Security, Architecture, Quality, Performance, and Style review with full MCP integration. Mod
security
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.
general
[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
general
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees
general
CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting. Runs 6 (lean) or 9 (full) specialized review agents including one
engineering
Audit skills for agentic orchestration quality. Checks subagent dispatch patterns, parallelism opportunities, anti-patterns, and alignment with the three-phase pattern (setup → dis
general
CLUTCH v2 — Claude Layered Unified Team Coordination Hub. Resilient multi-phase orchestration with fail-fast guards, context budgeting, structured checkpoints, and workstream compl
general
Inception 아티팩트(requirements, user-stories, workflow-plan)를 입력으로 받아 agentic 시스템의 컴포넌트 경계·인터페이스 계약·데이터 모델을 설계하고 `.omao/plans/construction/design.md`를 생성한다. Agent·Tool·Memory·Gateway
engineering
Apply a simple code transform via agent-booster's WASM engine — sub-millisecond, deterministic, $0 (no LLM call). Companion to cost-booster-route.
general
Create a new composable pattern — a multi-block sequencer composition that solves a recurring agentic architecture problem. Produces the pattern factory, internal blocks, tests, an
engineering
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing — from luicabref97/sushi-jungle-web
engineering
Morning bridge skill that shapes the GitHub backlog between night-shift runs. Partitions open issues into buckets (prd:draft, ready-for-human, blocked-on-human, swarm, needs-triage
product
Split work across subagents with explicit contracts, interfaces, and merge strategies. Use when parallelizing tasks, distributing workload, or orchestrating multi-agent workflows.
general
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 sequenti
general
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
general
Discover happy paths on a target site using agent-browser, producing structured trace JSON for deterministic test generation.
general
Enriches dbt source and model YAML descriptions for AI-driven query generation. Profiles BigQuery tables for schema metadata, sparse_ratio, and enum values so documentation uses gr
general
This skill should be used when the user asks to "optimize an agent with GEPA", "use reflective optimization", "optimize ReAct agents", "provide feedback metrics", mentions "GEPA op
general
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 with tools",
engineering
Generate wiki documentation from completed spec files — architecture decisions, usage guide, API changes. Posts to ADO Wiki or Confluence depending on provider config. Use as the f
engineering
Diff-aware AI browser testing — analyzes git changes, generates targeted test plans, and executes them via agent-browser (Rust daemon + CDP, ARIA-tree-first). Reads git diff to det
engineering
Peer-to-peer multi-agent discussion skill — seven-phase lifecycle (INVITE / CHARTER / RESEARCH / DISCUSS / CLOSE / REVIEW / SAVE) with charter requirement, decide default mode, rou
content
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. Use when you nee
general
Lightweight version control for agent-generated document changes. Tracks iterative refinement without creating v1, v2, v3 copies. Use when committing agent edits, creating checkpoi
science
KTG content marketing pipeline — SWARM MODE. Orchestrates 7 plugins via parallel agent dispatch. Drop a post, get it published everywhere with maximum parallelism. Local-first: Oll
growth
Every Hudu cmdlet, plus an offline SQLite mirror, cross-entity audits, and agent-native output. Trigger phrases: `hudu hygiene scorecard`, `audit hudu documentation`, `find stale h
security
Create technical implementation plans using Cartographing Kittens research agent swarms for deep codebase understanding. Use when the user says "plan this", "create a plan", "how s
science
Structured code review using Cartographing Kittens-powered reviewer agent swarms. Use when the user says "review this", "check my code", "code review", or before creating a PR. Use
general
Execute implementation plans with Cartographing Kittens-first worker swarms. Use when the user says "build this", "implement", "execute the plan", "start working", or after plannin
general
Design a system's architecture for the agent-assisted era: choose the architecture style, the stack, the module boundaries, the contracts, and the data model — concentrating scarce
security
Evaluate the attached MCP set by running agent-authored scenarios and producing an adversarial friction report. Claude exercises each MCP live, logs every tool call with justificat
content
Design an MCP server's tool surface by analyzing an API and proposing interaction categories. Produces a plan consumable by /mob:swarm for implementation.
general
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
general
워크트리 브랜치를 main으로 squash-merge + conventional commit 자동 생성. codex-swarm 워크트리 자동 인식. '머지해', 'merge worktree', '워크트리 머지', '결과 수집', 'squash merge' 요청에 사용.
general
Convert legacy subagents, slash commands, and rules to the unified Agent Skills format. Use when migrating agent resources, consolidating legacy directories, or standardi — from ma
general
Orchestrates multi-agent task execution using a Royal Navy squadron metaphor — from mission planning through parallel work coordination to stand-down. Use when work needs parallel
general
Run the full agent-team pipeline end-to-end for a single feature — branch + worktree, PM grooms a Tasks Plan, human approves the plan, inner SWE/Tester loop per task, PM acceptance
general
Agentic memory system for writers - track characters, relationships, scenes, and themes — from growth/growth-misc
growth
OpenAI Agents SDK (Python) development. Use when building AI agents, multi-agent handoffs, function tools, guardrails, sessions, streaming, or tracing with the `openai-agents` / `a
security
Maintains a persistent, folder-based log of all agentic-os experiment runs. Each run writes one dated file to context/experiment-log/ and updates index.md. Supports five source typ
science
Validates that a DAG node's output matches its declared JSON schema before passing to downstream nodes. The glue that makes multi-agent DAGs reliable. Use when checking output cont
engineering
Fan a local diff through three independent, axis-focused review passes (correctness, security, conventions), then merge the findings into a single structured report. Each pass is i
security
Generate 20,000+ particle swarm simulators in two modes: sandbox (complete Three.js host runtime with gesture controls, security validation, code injection pipeline) and sim (behav
content
A focused Cloud Run Admin API CLI with agent-native output, local inventory, and command discovery. Trigger phrases: `inspect Cloud Run services`, `list Cloud Run jobs`, `find Clou
general
The first agent-native CLI for Pangolin — every endpoint, plus offline SQLite, cross-org audits Trigger phrases: `expose service through pangolin`, `back up pangolin config`, `audi
security
Multi-agent PR review — component, integration, and routing analysis merged into a structured audit doc with severity and PR buckets.
general
E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls. TRIGGER when user asks to manually test a PR, test a feature end-to-end, or run integration t
engineering
**DEFAULT for any product change crossing teams or with meaningful complexity — produces a full structured product doc with problem, users, goals, non-goals, must/should/won't-have
product
Enable cross-machine Psyche context sync via a private GitHub repo (spt-agent-storage). Drives install + auth checks for the `gh` CLI, creates the repo via `gh repo create --privat
general
Parallel QA using agent teams for comprehensive multi-type testing. Spawns specialized QA agents that simultaneously run different test categories (unit, integration, lint, securit
security
Multi-agent review resolution with trust-but-verify methodology. Accepts a PR number/URL or a local code-review report file. Extracts review comments, verifies each with parallel a
engineering
Use when reviewing an autonomous agent's feature branch before merging to main, verifying agent work quality, checking if ROADMAP claims match actual code, or deciding whether to m
product
Braze platform help — Canvas Flow journey orchestration, email/push/in-app/SMS/WhatsApp/Content Cards campaigns, BrazeAI (predictive, generative, agentic), Braze Data Platform (CDI
sales
KaraX.ai platform help — agentic AI workspace combining multi-LLM chat (Claude/Gemini), real-time meeting transcription, and AI workflow automation across 800+ integrations from a
sales
Planhat platform help — Health Scores, Agentic Automation, Revenue Management, CRM Sync, Enduser Tracking, Projects, NPS, REST API, MCP Server. Use when health scores aren't reflec
sales
Sembly AI meeting platform help — agentic meeting intelligence with AI-generated client deliverables (proposals, briefs, decks), Semblian AI chat, task auto-detection, 48-language
sales
Trigify platform help — AI agent-powered LinkedIn signal intelligence and social listening for B2B GTM teams with custom AI workflows, engagement tracking, competitor monitoring, C
sales
Create minimum viable agentic layer structure for a project. Use when adding agentic capabilities to a new project.
tools
Trigger with "run self-audit", "test the analyzer", "regression test the plugin analyzer", "audit the agent-scaffolders", or "verify the analyzer works correctly". Runs the analyze
tools
Langfuse production trace를 관찰하고 품질 regression·비용 이상·실패 패턴을 자동 분석한 뒤 prompt·skill 수정안을 PR draft 형태로 제안한다. Observe → Analyze → Propose → PR 4단계 루프를 실행하며 self-improving-agent-loop ADR
general
Backfill structured session summaries from Claude Code .jsonl transcripts into the vault's per-project Sessions folder. Distills each CC session into TL;DR / Goal / Outcome / Decis
content
Get details about a specific agent. Requires authentication. Use for Agentuity cloud platform operations — from tools-only/X-Skills
tools
**GUIDE SKILL** — Guide to the Skill Manager for Copilot extension. USE FOR: adding/removing skill repos, syncing skills, pushing feedback, configuring sync intervals, troubleshoot
general
Creates Claude subagents equipped with curated skills for solving problems within DAG workflows. Use when designing a specialist subagent, selecting skills for a subagent, writing
general
Multi-agent slide review (visual, pedagogy, proofreading). Use for comprehensive quality check before milestones.
tools
Multi-agent research that keeps bringing gifts back — like cats! Dispatch multiple agents to research a topic in parallel, compile findings, and iterate on new discoveries.
science
Initialize and run a game with coordinated multi-agent architecture. Use when user wants to start a playtest, run a game, test game rules, or launch multi-agent game simulation.
engineering
Scaffold a new DovePaw background agent end-to-end. Creates agent files in ~/.dovepaw/tmp/ so the agent appears immediately in the Kiln sidebar group, ready to test. Optionally pub
general
Multi-agent debate system supporting 6 AI providers (Gemini, OpenAI, DeepSeek, Groq, Grok, Mistral)
general
Launches pre-configured multi-agent teams for code review, debugging, feature development, security audits, and database migrations. Use when the user asks to start a multi-agent w
security
Agentic 시스템을 위한 TDD 전략을 수립한다. LLM 클라이언트 mock(VCR-style), golden dataset 기반 eval(최소 5건), hypothesis 기반 property-based test로 비결정성을 제어한다. `.omao/plans/construction/test-plan.md`를 산출하며
engineering
통합 CLI 오케스트레이터 + 실행 스킬 front door. 커맨드 숏컷(단일) + 자동 분류/분해(병렬) + 수동 병렬 + 명시 플래그 오버라이드. tfx-route.sh 기반. `--cli`, `--mode`, `--parallel`, `--retry`, `--isolation`, `--remote`, `--shap
tools
DEPRECATED — tfx-auto 로 통합됨. `/tfx-auto --parallel swarm --mode consensus --isolation worktree` 로 리다이렉트. 실제 swarm 엔진 (PRD 파싱, shard 스케줄링, reconcile) 은 `tfx swarm` CLI 에 그대로 유지된다. P
product
Private skill distribution system. Use when the user wants to install, use, add, push, remove, sync, list, or search for skills, agents, or prompts from their private library catal
general
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation
general
Visually verify Ghostfolio UI state using agent-browser after agent actions. Use after /uat add_activity calls to confirm the UI reflects the change.
general
Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API documentation. — from Bra
content
Use when contributing to the Valkey server source - C internals, event loop, data structures, cluster, replication, persistence, memory, threading, modules, scripting, tests, build
general
List wiki pages filtered by type, tag, or status. Use this for agentic search over the vault — narrow down relevant pages before reading them in full.
general
AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browse
engineering
VC signal-to-thesis skill for Marathon-style deal discovery. Weekly all-sector radar, OSS radar, agent-native research workbench, theme drill-downs, company backtrace, and GitHub t
science
Design, deploy, and tune vLLM v0.18.2 inference serving on EKS with PagedAttention v2, Multi-LoRA, FP8 KV Cache, Chunked Prefill, and Continuous Batching. Produces Helm values.yaml
general
Run multi-agent econometric review on estimation code, identification arguments, and research artifacts
science
Agentic memory system for writers - track characters, relationships, scenes, and themes — from Yeachan-Heo/oh-my-claudecode
growth
A/B test agent variants for quality and token cost.
general
Microsoft AutoGen multi-agent configuration for conversational AI systems
general
LLM-driven multi-agent framework for automated single-cell analysis.
general
This skill should be used when the user says "configure MCP", "set up MCP servers", "add MCP integrations", "connect GitHub MCP", "set up Coolify MCP", "configure database MCP", "a
engineering
CrewAI multi-agent orchestration setup for collaborative AI systems
general
Alias skill that invokes /human-agentic-design with all arguments passed through. Provides shorthand for human-agentic-design. Triggers on keywords: had, human agentic design short
general
Complete knowledge of the Haira programming language — syntax, semantics, standard library, and idiomatic patterns. Use this skill whenever the user asks about Haira language synta
general
This skill should be used when the user says "scaffold a company", "set up workspace", "create company structure", "build company folder structure", "initialize agentic workspace",
tools
Use this skill when the task involves creating, reviewing, or refactoring installable skills, shared skill references, or reusable agent-authoring guidance; when the work depends o
engineering
Claude Code ecosystem expertise. Modules: CLI tool (setup, slash commands, MCP servers, hooks, plugins, CI/CD), extensibility (agents, skills, output styles creation), CLAUDE.md (p
general
5-level verification pyramid: static→unit→Playwright E2E (homepage-first, 6bp)→AI visual→post-deploy. 8-check quality gate. Multi-agent testing (functional/security/a11y/ — from se
security
Master index for Odoo 18 guides. This file provides a quick reference to find the appropriate detailed guide for each topic. Use this as an index to locate specific guide — from di
general
AI-агент для управления Facebook рекламой. Вызывай для анализа, оптимизации, создания кампаний и отчётов. — from tools-only/X-Skills
ads
SKILL.md files, not affiliated with, endorsed by, or sponsored by Anthropic.