Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
Home › Tag › Agent

Agent — Claude Code Skills

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.

10x-health-check

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

10x-infra-research

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

10x-stack-assess

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

10x-tech-stack-selector

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

anneal

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

appraise

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

cmux-agent-teams

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

devise

Multi-agent planning workflow using Agent Teams. Combines brainstorm, research, validation, synthesis, shatter assessment, forge enrichment, and review into a single orchestrated p

science

lowcoder

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

multi-mind

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

next-move

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

prp-commit

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

prp-pr

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

strive

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

swarm-wave

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

write-plan

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

greenflash-onboard

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-protocol

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

agent-authoring

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-simulator

Agent-based modeling skill for simulating complex adaptive systems with heterogeneous interacting agents

general

agent-browser

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

agent-browser

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

agent-conversation-protocols

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

claude-agent-sdk-agent-creation

Use when creating or configuring Claude AI agents using the Agent SDK. Covers agent initialization, configuration, and basic setup patterns. — from TheBushidoCollective/han

tools

agent-interchange-formats

Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, err

engineering

agent-orchestrator-manager

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

agent-reach

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

agent-tower-plugin

Multi-agent deliberation for Claude Code - orchestrate AI coding assistants (Claude, Codex, Gemini) for council, debate, and consensus workflows

general

agentic-actions-auditor

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

agentic-export

Export reusable assets from a project into this repository's v0.2 plugin architecture (skills, templates, agents).

engineering

agentic-import

Import external reusable assets into this repository's v0.2 plugin architecture (skills, templates, agents).

engineering

always-on-agent-applications

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

always-on-agent-architecture

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

always-on-agent-inputs

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

always-on-agent-safety

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

atrib

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-agentic-ai

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-agentic-ai

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

browser-tools

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

browser

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-bureau

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

gastown-operator

Kubernetes operator for Gas Town multi-agent orchestration. Triggers on "create polecat", "spawn worker", "kubernetes polecat", "deploy convoy".

engineering

claude-agent-sdk-agent-creation

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

claude-agent-sdk-context-management

Use when managing agent context, memory, and conversation state in Claude AI agents using the Agent SDK.

tools

agentify

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

cli-anything

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

clify

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

collab-fix

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

copilot-agent-coordinator

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

copilot-workflow-orchestrator

Orchestrates complex multi-agent workflows for features requiring coordinated work across multiple GitHub Copilot agents. Triggers on "orchestrate workflow", "coordinate these agen

general

create-cli-skill

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

developing-llamaindex-systems

Production-grade agentic system development with LlamaIndex in Python. Covers semantic ingestion (SemanticSplitterNodeParser, CodeSplitter, IngestionPipeline), retrieval strategies

engineering

dispatch-outreach

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

divecode-pr-watch

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

dogpile

Deep research aggregator that searches Brave (Web), Perplexity (AI), GitHub (Code/Issues), ArXiv (Papers), YouTube (Videos), and Wayback Machine simultaneously. Provides a consolid

science

flow-post-task-sync

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

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

genius-code-review

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

glaw-fund-regulatory-council

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

idea-factory-orchestrator

**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-almanac-content

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-notes

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

liaison

Human interface agent that translates ecosystem activity into clear, actionable communication. Creates status briefings, decision requests, celebration reports, concern alerts, and

general

lythoskill-arena

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

netllm-swarm

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

nimble-agent-builder

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

parallel

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

printing-press-output-review

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

queue

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

rag-retrieval

Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, ag

general

run-swarm

Execute plan tasks via fresh-context subagents (swarm mode)

general

rune-orchestration

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

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

TDD-debug

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

testing-llm

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

launcher

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

virtual-lab-agent

AI-powered virtual laboratory orchestrating multi-agent scientific research teams for autonomous hypothesis generation, experimental design, and validation in biomedical research.

science

ag-criar-projeto

Scaffolding completo: estrutura de pastas, configs, .env.example, CI base, README. Projeto nasce agent-ready.

general

ag-mesa-redonda

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

agent-add

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

agent-author

**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

agent-create

Создание нового агента (AGENT.md) с промптом, конфигурацией и регистрацией в README. Используй при добавлении нового AI-агента для автоматизации задач проекта.

general

agent-lint

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

agent-mgmt

Spawn, list, inspect, and stop sub-agents through the wrapper. Sub-agent config travels as a JSON-serialized string. Flat parameter surface.

tools

agent-modify

Обновление конфигурации, деактивация или переименование агента. Используй при изменении промпта агента, смене модели, деактивации устаревшего агента или миграции на новое имя.

general

agent-restore-context

Manage restore context files so skills can survive /clear and /compact. Use to write, delete, check, or list .agent-restore-context-* files.

general

agent-skill-audit

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

shiiman-workflow:agent-team-issue

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

agent-validate

Проверка AGENT.md на соответствие стандарту — frontmatter, промпт, секции, ссылки. Используй после создания или изменения агента, при code review или перед коммитом.

general

agentbase

Multi-agent orchestration system for coordinating parallel development work. Use when managing complex multi-workstream development, triaging failures, or coordinating parallel age

general

agentic-brownfield

Discover and document existing systems with 10-phase brownfield analysis and drift detection workflows.

general

agentic-eks-bootstrap

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

agentic-rules-writer

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

agentic-security-review

Run the OWASP-aligned agentic security review path — covers goal hijacking, tool misuse, excessive agency, memory poisoning, secrets exposure, handoff failures, and observability.

security

agents-view

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

agentuity-cli-cloud-agent-get

Get details about a specific agent. Requires authentication. Use for Agentuity cloud platform operations — from tools/cli-builders

tools

ai-agent-safety-review

**DEFAULT for AI agent safety reviews — dispatches security-auditor + risk-and-controls-reviewer with AI/agent safety focus.**

security

ai-agent-workflow

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

amp-skill-creator

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-spec

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

application-audit

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

qa-swarm:attack

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

atv-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

brutal-review

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-with-agent-team

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

ce-dogfood-beta

[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

ce:review

Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees

general

ci-review

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

claude-skill-orchestration-audit

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

CLUTCH v2 — Claude Layered Unified Team Coordination Hub. Resilient multi-phase orchestration with fail-fast guards, context budgeting, structured checkpoints, and workstream compl

general

component-design

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

cost-booster-edit

Apply a simple code transform via agent-booster's WASM engine — sub-millisecond, deterministic, $0 (no LLM call). Companion to cost-booster-route.

general

fsd:create-pattern

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

customaize-agent:create-hook

Create and configure git hooks with intelligent project analysis, suggestions, and automated testing — from luicabref97/sushi-jungle-web

engineering

day-shift

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

delegate

Split work across subagents with explicit contracts, interfaces, and merge strategies. Use when parallelizing tasks, distributing workload, or orchestrating multi-agent workflows.

general

dispatching-agent-teams

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

do-competitively

Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis

general

do-discover-paths

Discover happy paths on a target site using agent-browser, producing structured trace JSON for deterministic test generation.

general

document-dbt

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

dspy-gepa-reflective

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

dspy-react-agent-builder

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

dx-doc-gen

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

expect

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

gaia-meeting

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-task

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

airesearchorchestrator:gitmem

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

hub-swarm

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

hudu

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

kitty-plan

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

kitty-review

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

kitty-work

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

load-bearing

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

mcp-eval

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

mcp-topo

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

memorize

Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering

general

merge-worktree

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

migrate-to-skills

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

nelson

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

night

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

writer-memory

Agentic memory system for writers - track characters, relationships, scenes, and themes — from growth/growth-misc

growth

openai-agents-sdk

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

os-experiment-log

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

output-contract-enforcer

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

pairing-multi-agent-review

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

particle-swarm-sim

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

pp-cloud-run-admin

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

pp-pangolin

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

pr-audit

Multi-agent PR review — component, integration, and routing analysis merged into a structured audit doc with severity and PR buckets.

general

pr-test

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

prd-standard

**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

psyche-sync-setup

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

qa-swarm

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

resolving-pr-issues

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

review-agent-branch

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

sales-braze

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

sales-karax

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

sales-planhat

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

sales-sembly

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

sales-trigify

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

scaffold-layer

Create minimum viable agentic layer structure for a project. Use when adding agentic capabilities to a new project.

tools

self-audit

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

self-improving-loop

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

session-backfill

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

agentuity-cli-cloud-agent-get

Get details about a specific agent. Requires authentication. Use for Agentuity cloud platform operations — from tools-only/X-Skills

tools

skill-manager-guide

**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

skillful-subagent-creator

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

slide-excellence

Multi-agent slide review (visual, pedagogy, proofreading). Use for comprehensive quality check before milestones.

tools

infinite-gratitude

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

start-game

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

sub-agent-builder

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

synod

Multi-agent debate system supporting 6 AI providers (Gemini, OpenAI, DeepSeek, Groq, Grok, Mistral)

general

teams

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

test-strategy

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

tfx-auto

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

tfx-swarm

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

library

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

tree-of-thoughts

Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation

general

uat-verify

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-docs

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

valkey-dev

Use when contributing to the Valkey server source - C internals, event loop, data structures, cluster, replication, persistence, memory, threading, modules, scripting, tests, build

general

vault-list

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

vc:agent-browser

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-signals

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

vllm-serving-setup

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

workflows:review

Run multi-agent econometric review on estimation code, identification arguments, and research artifacts

science

writer-memory

Agentic memory system for writers - track characters, relationships, scenes, and themes — from Yeachan-Heo/oh-my-claudecode

growth

agent-comparison

A/B test agent variants for quality and token cost.

general

autogen-setup

Microsoft AutoGen multi-agent configuration for conversational AI systems

general

cell_agent

LLM-driven multi-agent framework for automated single-cell analysis.

general

configure-mcp

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-setup

CrewAI multi-agent orchestration setup for collaborative AI systems

general

had

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

haira

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

scaffold-company

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

ub-authoring

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-ecosystem

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

quality-and-verification

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

odoo-18

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

ads-agent

AI-агент для управления Facebook рекламой. Вызывай для анализа, оптимизации, создания кампаний и отчётов. — from tools-only/X-Skills

ads