Каталог навыков агентов

Use for creating high-quality Claude Code subagents

This skill provides procedures for creating new agents when project complexity requires delegation. Agents should be cre...

Expert guidance for creating effective Claude Code agents (subagents). Use when users want to create a new agent, update...

Create or audit a Claude Code subagent: tools, model and effort, permissions, memory, isolation, and the system-prompt b...

Create new Claude Code subagents (the .claude/agents/ kind, NOT skills). Use this skill whenever the user wants to creat...

Design and scaffold new skills, subagents, and MCP surfaces. Use when choosing which primitive to create. NOT for invoki...

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill...

Creates and validates agent files for the dev-team-agents repository. Enforces all authoring standards from CLAUDE.md —...

Guide for creating optimized Claude Code agents. Use to design a new specialized agent, a swarm sub-agent, or a multi-ag...

Creates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .cla...

Purpose: Guide creation of Claude Code agents following Anthropic official best practices.

Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.

Guide for creating effective Claude Code agents. This skill should be used when users want to create a new agent (or upd...

Create or adapt Claude Code agent definitions. Use when creating an agent, changing subagent configuration, selecting ag...

Create production-grade agent .md files aligned with the current Anthropic subagent contract. Also validates existing ag...

Author a safe project agent definition with valid frontmatter, bounded authority, skill-tool closure, and passing reposi...

Scaffold vexjoy-agent operator .md files: frontmatter, routing block, operator context, reference loading table, phase/g...

Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suit...

Create new OpenCode agents with a gpt-5.2-codex default.

Create, update, migrate, or validate Codex native custom agents that can be spawned as subagents. Use when the user asks...

Create new specialist agents, modify and improve existing agents, and validate agent behavior. Use when users want to cr...

Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.

Create or improve a Claude Code subagent definition under `.claude/agents/<name>.md`. Use when the user explicitly invok...

Guide for creating custom subagents for Claude Code (Markdown files in .claude/agents/ or ~/.claude/agents/ with YAML fr...

Guide for creating custom subagents for OpenAI Codex (standalone TOML files in .codex/agents/ or ~/.codex/agents/, each...

Guide for creating custom agents for GitHub Copilot (cloud agent on GitHub.com, Copilot CLI, VS Code, and other IDEs). U...

Creates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .cla...

Provision and register autonomous GPIA agent workspaces with unique IDs, helper functions, and execution reports; use wh...

Guide for creating custom agents for the OpenCode CLI, V2 (default) and V1. Use this skill whenever a user wants to buil...

Interview-based system for creating specialized Claude Code agents. Use when users want to create a Claude Code agent, n...

Structured cross-review protocol between specialized agents. Ensures scope alignment, priority calibration, and domain-a...

Deep curation of a single agent definition through structured human conversation. Coordinates knowledge research, person...

Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL....

Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, net...

Expert data analyst specializing in business intelligence, data visualization, and statistical analysis. Masters SQL, Py...

Data Analyst IA — Expert en analyse de données (SQL, BI dashboards, Metabase, Superset, reporting, KPIs)

Specialist subagent: ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when bu...

Expert en data mesh (domain ownership, data products, self-serve, gouvernance fédérée)

Agent skill for data-ml-model - invoke with $agent-data-ml-model

Data Quality Specialist IA — Expert en qualité des données (profiling, cleaning, déduplication, validation de schéma, Gr...

Expert data researcher specializing in discovering, collecting, and analyzing diverse data sources. Masters data mining,...

Expert data scientist specializing in statistical analysis, machine learning, and business insights. Masters exploratory...

Use when a consequential decision has genuinely competing positions that need bounded adversarial review before a human...

Use when a program crashes, a test fails, or code produces wrong results and reading the source isn't enough to see why....

Mint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access,...

Terminal session manager for AI coding agents. Use when user mentions "agent-deck", "session", "sub-agent", "MCP attach"...

Build, validate, and troubleshoot deep links for Codex, Cursor, VS Code, Visual Studio, and similar tools. Use when user...

Improve codebases so coding agents reliably do the right thing by default. Use for architecture, type/invariant, static-...

用途: 定义 Agent（Subagent）的职责、擅长领域和配置

Use this skill when creating or refining Claude Code sub-agent definitions. Helps design specialized AI assistants with...

当系统提示词需要设计多代理协作架构、子代理专业化分工、代理间上下文隔离与传递机制、任务生命周期管理时调用此 Skill。适用于 AI Agent 平台、多工具编排系统、代码审查流水线、跨应用协作场景等。不适用于：单代理系统（无委派需求）、简...

Specializes in agent dependency and interface design. Defines skill references, command coordination, and inter-agent co...

Deploy a scaffolded agent to OpenShift using a UBI 9 Python S2I build. Run when the user asks to deploy, build, or run a...

Implement CI/CD pipelines for AI agent deployment with evaluation gates. Use for GitHub Actions workflows, GitOps with A...

Guidelines for designing tools and action spaces for AI agents. Use when building agent harnesses, designing tool interf...

Design AI agents with recommended patterns and architectures

Use when building an LLM agent that uses tools over multiple steps. Covers tool design, the agent loop, error recovery,...

Fires when a fellow is designing ONE production agent and asks what it should be built from — "design an agent for X", "...

This skill should be used when the user asks to "configure agent profile", "add skills to agent", "set up MCP servers",...

Design effective AI agent systems with clear architecture, capability planning, and tool integration. Use when building...

Best practices for designing Claude Code agent files (.claude/agents/*.md). This skill should be used when writing or re...

Expert en design system markdown specs (73+ design systems as markdown, tokens, components)

Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent...

This skill selects and reviews the higher-level strategy behind an LLM-based agent's build — the architectural backbone,...

Use when the user asks to design multi-agent systems, create agent architectures, define agent communication patterns, o...

Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation. Use when...

Agent Designer - Multi-Agent System Architecture

Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), genera...

Use the built-in `Computer` sub-agent with `agent-desktop` for macOS desktop automation. Apply when a task needs applica...

Control native desktop apps with agent-desktop accessibility snapshots and actions on macOS, Windows, or Linux. Use for...

Agent skill for dev-backend-api - invoke with $agent-dev-backend-api

AI agent development standards including frontmatter structure, naming conventions, tool access patterns, model selectio...

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatte...

Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting promp...

Create and audit Claude subagents. Use when building specialized workers with isolated context. Includes frontmatter, al...

Create or improve agent configurations, prompts, and workflows using secure research-first methodology. Use when buildin...

Core principle: Follow ConstructAI unified agent framework standards for consistent, maintainable, and scalable agent de...

Drive the Apex Factory app on a leased iOS simulator or Android emulator with agent-device through .agents/scripts/devic...

Automates Apple-platform apps (iOS, tvOS, macOS), Android devices, and Amazon Vega OS TV apps in Vega Virtual Devices. U...

Use your own real devices with the Agent Device Protocol (ADP). List them, jump to one, check health, take a picture, wa...

DevOps & Infrastructure IA — Gère le VPS, Docker, déploiements, monitoring, sécurité, tunnels Cloudflare. Expert Hetzner...

DevSecOps IA — Expert en intégration sécurité dans les pipelines CI/CD (SAST, DAST, SCA, container scanning, compliance...

Discover and invoke any of 69 specialist agents. All agents are latent (not loaded at startup) and activated on demand v...

Disclosing a surface's existing fixed AI jobs in the shell's top Agents menu. Use when a page, panel, overlay, or window...

Interact with Discord servers - send messages, read channels, manage reactions

Interact with Discord servers using bot tokens - send messages, read channels, manage reactions

Discovers all Claude Code agents in the system including built-in, plugin, project, and user-level agents. Use when you...

Automatically discover and route to appropriate specialist agents

Build dependency-aware, batched dispatch queues for parallel agent execution.

Use when deciding whether to do work directly, delegate it, or which agent/skill gets it: routing a task, picking a spaw...

Coordinates specialized agent roles for complex feature workflows

Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omg/skills/) — every rule chec...

Analyze code changes and recommend appropriate documentation. Evaluates git diffs to determine if changes warrant README...

Create documentation optimized for AI agent consumption. Use when writing SKILL.md files, README files, API docs, or any...

Use when writing documentation optimized for AI agent consumption - SKILL.md files, README files, API docs, or any docum...