В каталоге 182 820 навыков в 14 категориях.
Agent skill for docs-api-openapi - invoke with $agent-docs-api-openapi
Standards for creating AGENTS.md files that guide AI coding agents working with your codebase. Use when creating instruc...
Standardized reference documentation section structure for agents - project guidance, conventions, related agents, and S...
Centralize coding agent configuration with dotfiles and link it into Codex/Claude/Gemini locations on Windows, macOS, or...
Detect schema drift in agent messages and APIs by comparing top-level field names.
Expert developer experience optimizer specializing in build performance, tooling efficiency, and workflow automation. Ma...
The watch-fix-rerun method for making an existing platform agent or automated process efficient and correct: baseline it...
Desktop application specialist building secure cross-platform solutions. Develops Electron apps with native OS integrati...
Use when reading or sending the agent's own email. The acp email commands: identity and provisioning, inbox paging by cu...
Use when setting up an email inbox for an AI agent (Moltbot, Clawdbot, or similar) - configuring inbound email, webhooks...
Use when setting up a secure email inbox for any AI agent — configuring inbound email via Resend, webhooks, tunneling fo...
Deploy and manage AI agents on Vertex AI Agent Engine. Use when deploying ADK agents to production, configuring Agent En...
根据项目事实与已确认讨论生成、精简或审查 AGENTS.md / CLAUDE.md，明确共享规则主文件、可执行约束、PRD / Spec 读取路标和验证入口。用于项目入口只有空模板、规范含糊、双入口冲突或需要设置 Agent 项目说明时。...
Redesign seat-based pricing for the agent era — when one human runs ten agents, per-seat models collapse. Use when agent...
Expert error coordinator specializing in distributed error handling, failure recovery, and system resilience. Masters er...
Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains...
ETL Pipeline Specialist IA — Expert en pipelines ETL (Airflow, dbt, data quality, incremental loads, CDC)
编码代理（Claude Code、Aider、Codex等）在自定义任务上的直接比较，包含通过率、成本、时间和一致性指标
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, a...
Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when...
Test and benchmark agent performance. Covers behavioral testing, accuracy measurement, latency profiling, cost tracking,...
Head-to-head comparison of coding agents (OpenAI Codex, Aider, Codex, etc.) on custom tasks with pass rate, cost, time,...
Use when grading an agent session, transcript, skill, or workflow for execution quality. Score routing, tool use, verifi...
Head-to-head comparison of coding agents
Build a security evaluation for an agent with benign tasks, injections planted in tool results, and utility and attack s...
Use to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, scor...
Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping...
Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates.
Design and implement evaluation frameworks for AI agents. Use when testing agent reasoning quality, building graders, do...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and produc...
Defines measurable evaluation metrics for extraction, matching, tailoring, and application workflows.
Use when testing skills, commands, or agents for quality. Use after creating new skills, before deploying agents, or whe...
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context...
Evaluate AI agent outputs — hallucination detection, quality scoring, behavioral testing, and CI/CD pipelines.
You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in production. You've learned that...
Evaluate agents and skills for quality and standards compliance.
Measure agents before trusting them — task suites, regression gates, calibrated judging, scorecards.
Design reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, base...
Designs and runs reproducible evaluations for AI agents, prompts, tools, skills, and model-backed workflows using realis...
Tests and benchmarks LLM agents covering behavioral testing, capability assessment, reliability metrics, and production...
Evaluate agent and skill behavior or routing.
Expert en architecture événementielle (Kafka, RabbitMQ, event sourcing, CQRS, saga patterns)
Execute Miyabi Agents (Coordinator, CodeGen, Review, Deployment, PR, Issue) with Git Worktree isolation for parallel pro...
Skill minima que apunta al nucleo de los 3 modos de ejecucion multiagente (Tradicional, 4 capas, Intermedio) por contrac...
Redux state for agent execution and firing agent shortcuts. Use when editing features/agents/redux/, building agent UI,...
Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or afte...
Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building d...
Use this skill when a user wants to decide, design, audit, or repair a coordinated multi-agent or expert-team workflow f...
Upload tailored resume to cloud or attach to user session. Handles final formatting and delivery.
Extend the Strategy Coach agent with new capabilities. Use when user says "add coaching phase", "new research pillar", "...
Visual context analyzer for AI agents. Provides screenshots, accessibility scans, DOM snapshots, and element description...
Use when coordinating large repository tasks, searching public GitHub repositories, selecting specialist agents, creatin...
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool acces...
Bootstrap new 33GOD ecosystem agents with standardized configuration. Use when creating new agents, spawning workers, de...
Diagnose failed or unreliable agent workflows by classifying bad assumptions, missing observations, tool misuse, wrapper...
Fashion Tech Specialist IA — Expert en technologies mode (virtual try-on, size recommendation, trend prediction, sustain...
Регистрация косяка агента в системе учёта WP-316 L1. Без LLM — детерминированный скрипт без WP Gate.
Helps a DataStream Corp bootcamp participant extend the Phase 2 AgentCore agent in `phase2/app/agent/agent.py` safely —...
Quick prompt to indicate that the provided info was produced by another agent for consideration. Invoke only when explic...
Fetch and extract full article content from URLs. Returns complete text with structure (headings, links, lists) instead...
Share files between agents, hosts and people through an AFP space (S3-compatible storage such as Garage). Store a file a...
Fintech Algérie — Banque d'Algérie, CIB, Edahabia, BaridiMob, réglementation bancaire DZ
Agent-first screenshots — an agent drives the real app via CDP and produces clean, defect-free product screenshots (news...
Read at Codex startup and before every authorized subagent creation, retry or model change. Select model and reasoning e...
Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agen...
Fitness Tech Specialist IA — Expert en technologies fitness (wearable data, workout programming, nutrition tracking, gam...
使用本机 fleet 分派 Codex GPT-6、Gemini、Grok 或 JEV 任务，或调用 Kollab 图片/视频/音频/多模态能力时使用；包括用户点名 agent-fleet、Nano Banana、nanobanana、香蕉...
Deploy teams of Hermes AI agents to Discord using ClawFleet. Generic + customizable workflow.
The Cianfhoghlaim 12-agent fleet orchestration pattern in `agents/meaisinfhoghlaim/`. Covers 5 frameworks (Custom/ADK/Ag...
Food Tech Specialist IA — Expert en technologies alimentaires (recipe recommendation, allergen detection, supply chain,...
Design, generate, integrate, build, and verify a production iOS App Icon for an AgentFoundry product. Use when creating...
Add a typed durable agent-produced artifact, inline native SwiftUI card, and restorable detail surface to an AgentFoundr...
Create, redesign, or review AgentFoundry SwiftUI iOS product UI with the AgentFoundry iOS 26.1 target baseline, native i...
Design product-agnostic proactive systems for AgentFoundry AI-native products and write an ADR before implementation. Us...
Build an AgentFoundry Product Evolution Agent pipeline that analyzes conversation memory, proposes native product/interf...
Orchestrate the first production proof of an AgentFoundry AI-native iOS product with one upfront setup authorization and...
Add owner-scoped durable operational records and safe OpenAI Agents SDK tools to an AgentFoundry proof. Use after agent-...
Scaffold the reusable production foundation for a new AgentFoundry SwiftUI iOS proof: Tuist plus TCA, Firebase app boots...
Create AI agents and workflows using Microsoft Agent Framework SDK. Supports single-agent and multi-agent workflow patte...
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creati...
Use these when you want low-noise lint/test output (good for LLM/CI logs) while staying aligned with repo policy.
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
agent 时代前端工程手册——写/评审前端代码(React/RN/Next/组件/样式/状态/前端测试)、建立或评审前端仓工程门禁、设计系统对接 AI 时加载。覆盖:设计系统即契约(token 语义/受限组件词表/lint 硬门)、类型端...
Frontend Vue Specialist IA — Expert en développement frontend Vue (Nuxt, Pinia, Composition API, SSR, Vue 3)
End-to-end feature owner with expertise across the entire stack. Delivers complete solutions from database to UI with fo...
The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interch...
Specialist subagent: Expert game developer for Unity, Unreal Engine, and Godot game development
This skill provides knowledge for generating effective Claude Code agents tailored to specific projects. It is used inte...
Generate AGENT.md files with proper YAML frontmatter, role definitions, expertise areas, and prompt templates following...
ユーザーの責任範囲定義から、Agentのマークダウンファイルを生成する。エージェント作成時、プラグイン要素生成時、またはユーザーがエージェント定義、責任範囲、Agent生成、エージェントドキュメントに言及した際に使用する。
Agent skill for github-modes - invoke with $agent-github-modes
Agent skill for github-pr-manager - invoke with $agent-github-pr-manager
Specialist subagent: Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writi...
Agent skill for goal-planner - invoke with $agent-goal-planner
Agent skill for gossip-coordinator - invoke with $agent-gossip-coordinator