Каталог навыков агентов

通过将技能、命令、规则、钩子和额外内容并行进行仓库感知审查，为特定仓库构建基于证据的 ECC 安装计划，将其分为 DAILY 和 LIBRARY 两类。当 ECC 应精简为项目实际所需而非加载完整包时使用。

通过并行且具备仓库感知的审查过程，将技能、命令、规则、钩子和附加项分类到 DAILY (日常) 与 LIBRARY (库) 桶中，为特定仓库构建有证据支持的 ECC 安装计划。当需要将 ECC 裁剪到项目实际需要的内容，而非加载完整包时使用...

Build an evidence-backed Codex install plan for a specific repo by sorting skills, commands, rules, hooks, and extras in...

Build an evidence-backed ECC install plan

Agent skill for sparc-coordinator - invoke with $agent-sparc-coordinator

Specify an autonomous or tool-using AI agent before building it. Use when asked to design an AI agent, define an agent's...

Designs the cognitive blueprint of an agent before code generation.

Agent skill for spec-mobile-react-native - invoke with $agent-spec-mobile-react-native

Guide creation of focused single-purpose agents following the One Agent One Prompt One Purpose principle. Use when desig...

Agent skill for specification - invoke with $agent-specification

Write a spending mandate that lets an AI agent buy things for you within strict limits: what it may buy, from whom, up t...

Expert SQL developer specializing in complex query optimization, database design, and performance tuning across PostgreS...

Main agent orchestrator that coordinates a specialized squad of agents

Use when creating, refreshing, packaging, inspecting, promoting, or deprecating a named per-seat starting point — Agent...

Use when designing or auditing how an agent becomes useful after launch — AGENTS.md overlays, role files, skills, rig sp...

Manage the project's DuckDB state ledger (.agent/state.duckdb) - features, validation contract, sprint steps and the app...

Use when an agent needs to save where it is in a long task so it can resume later, or when handing a task to another age...

Design resumable agent checkpoints that preserve task state, evidence, changed files, and idempotent next actions after...

Universal agent configuration patterns for any AI coding environment. Use when configuring steering, specs, or context a...

Audit the ~/.claude/agents definitions and give each a verdict.

Work on SSE streaming, plain-text transport, ChatKit events, and session continuity. Use when debugging or modifying age...

Claude Codeエージェントの構造設計を専門とするスキル。エージェント定義、YAML Frontmatter設計、依存スキル形式、ワークフロー設計を担当する。Anchors:• 『The Pragmatic Programmer』（A...

Provides the vendored agent-style v0.3.5 prose rule pack as a portable Claude skill. Use when installing, syncing, apply...

Reviews an MCP server's tool surface for tool poisoning, over-broad parameters, missing descriptions, and privilege esca...

Specialist subagent: Svelte 5 runes, SvelteKit routing, form actions, and compile-time reactivity specialist. Use when b...

Agent skill for swarm - invoke with $agent-swarm

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes),...

Agent skill for swarm-issue - invoke with $agent-swarm-issue

Agent skill for swarm-memory-manager - invoke with $agent-swarm-memory-manager

Designs multi-agent systems with coordinated agent swarms, task distribution, inter-agent communication, and emergent co...

Agent skill for swarm-pr - invoke with $agent-swarm-pr

Jeffrey Emanuel's multi-agent implementation workflow using NTM, Agent Mail, Beads, and BV. The execution phase that fol...

以"管理者—执行者"模式运维 agent-switchboard MCP：受管 Claude supervisor 生命周期、跨模型委派（Codex/Claude/Gemini）、验收纪律与已知陷阱对策。 用于存在任一可用委派通道（mcp_...

Agent skill for sync-coordinator - invoke with $agent-sync-coordinator

Evaluate and improve AgentSystem learning quality for memory/self-compound jobs. Use when bots forget, write filler summ...

Operate and validate AgentSystem live quality alarm (systemd timer + alert state) to keep memory/proactivity/consistency...

Audit and improve AgentSystem memory retention, proactive behavior, learning quality, and agent consistency. Use when bo...

Audit and remediate AgentSystem cron output hygiene by detecting raw tool logs, stack traces, and noisy summaries. Use w...

Audit and harden AgentSystem scheduler reliability, cron contract compliance, and agent consistency. Use when bots skip...

Create tailored resume from job + source resume. Orchestrates the rewriting of bullet points to emphasize relevant exper...

Break a multi-step engineering request into bounded agent tasks with dependencies, acceptance tests, and safe parallel w...

Expert task distributor specializing in intelligent work allocation, load balancing, and queue management. Masters prior...

把千问办公的 agent 任务沉淀到钉钉 AI表格，形成跨 agent、跨窗口的「任务台账 + 交接登记表」。 支持创建/初始化个人台账（定时增量同步）与团队接续台账（仅 handoff 触发写摘要，保护隐私）。 当用户需要创建团队 Age...

Use when a goal needs multiple bounded agent roles, parallel or dependent task packets, explicit scope partitions, and a...

It is a specification for semantic workflows used by agents to plan, generate, formalize, summarize, and execute complex...

Keep your own task board and Eisenhower matrix in AI Maestro current, so the operator can see what you are doing, where...

Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm

统一管理多智能体角色的团队协作框架，支持智能体动态组合、灵活协作和扩展新角色。智能体本质上是"角色定义"，可以根据任务需求灵活组建团队，实现从会议决策到系统构建的完整能力。智能体角色明确分工：有干活的、有指挥的、有挑毛病的，能实时看到沟通过...

Use this skill when the user wants to assemble a multi-role engineering team inside a repository to plan and execute a f...

zephermine 섹션 기반 네이티브 멀티에이전트 오케스트레이션. 의존성 분석, Wave 그룹핑, 파일 소유권 분리, 병렬 구현과 통합 검증을 수행한다. Claude, Codex, Antigravity, Grok의...

啟動 Agent Team 模式，多個 worker 平行處理任務並共享發現。適用於大型重構、codebase 遷移、全面審查。

Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, the...

Codex CLI의 내장 default, explorer, worker를 조합해 병렬 구현을 수행한다. zephermine 섹션 모드와 자유 모드를 지원하며 /agent-team, /poseidon, /agent-t...

Use when designing a new multi-agent team, visible agents folder, role boundaries, handoff flow, PM Soul, Memory Curator...

Framework for self-sustaining AI agent teams with self-service work queues, role ownership, continuous discovery, and pr...

Team lead agent — sprint planning, standups, velocity, impediments, team health

多智能体团队管理。创建、查看、修改、删除 CountBot 的多智能体团队，管理团队成员（角色）和团队级自定义模型配置。当用户要新建 Pipeline/Graph/Council 团队、调整成员分工、修改依赖关系、开关技能系统、设置团队专属...

Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1...

Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement

Coordinate Claude Code Agent Teams through filesystem-based protocol. Use.

Coordinate specialized teammates in Agent Teams for execution, review, and planning. Delegate mode mandatory with TaskCo...

Interact with Microsoft Teams - send messages, read channels, manage reactions

Decompose a task into parallel workstreams, assign agent ownership, run integration at dependency boundaries, and synthe...

Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and fil...

Team composition knowledge for Claude Code Agent Teams - when teams fit, optimal sizing, spawn prompt patterns. Use only...

Orchestration playbook for parallel multi-agent work in Claude Code. Use when fanning out genuinely parallel, independen...

Use when work has genuinely independent streams or distinct builder, evaluator, domain, and integration roles that requi...

Agent Teams orchestration playbook for Claude Code. This skill should be used when the user asks to "create agent teams"...

Technical Writer IA — Expert en documentation technique (API docs, README, architecture docs, ADRs, changelogs). Rend le...

Interact with Telegram through TDLib - authenticate, inspect chats, and send messages

Generate custom agent from template

Specialist skill for agent templates and design patterns.Provides 4 types of agent templates (Analysis, Implementation,...

Guided agent setup from templates — business assistants, security, agents. Triggers on "create an agent for my [business...

Test agent delegation patterns to verify hierarchy and escalation paths. Use after modifying agent structure.

Agent skill for tester - invoke with $agent-tester

Write a threat model or threat assessment for an LLM-agent system by drafting principals, tools, channels, data stores a...

Three-Layer Thinking Chain Architecture — Personality-Driven Agent Self-Evolution Framework

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delega...

Create or modify an OpenAI Agents SDK tool with Zod params, caching, metrics, and agent registration. Use when adding to...

Define tools for the support agent. Use when adding new capabilities like refund processing, license transfer, knowledge...

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and...

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and...

Use when user mentions or implies: agent tool; User mentions or implies: function calling

You are an expert in the interface between LLMs and the outside world. You've seen tools that work beautifully and tools...

Define agent tools using the fail-closed design pattern — unified name/schema/security/execution in one class, with thre...

Use this skill when you need to test AI agent tool-call contracts, authorization, failures, and side-effect boundaries;...

Choosing among agent tooling surfaces — when to add an MCP server vs use a CLI/WebFetch, when to render a diagram with M...

Reference for configuring tool permissions when launching Claude Code agents. Use when setting up --allowedTools flags,...

Use when a task involves designing typed, bounded tool interfaces that an agent can call safely and interpret reliably t...

**UTILITY SKILL** — Browse the tool names a runtime accepts in a custom agent's `tools:` frontmatter and produce a valid...

Agent skill for topology-optimizer - invoke with $agent-topology-optimizer

Tourisme tech — booking, Sahara, Casbah, UNESCO, visa, officiel tourisme DZ

Debug agent execution with tracing — analyze traces, tool calls, durations, errors, and performance metrics. Use when in...

Agent Trace仕様に基づくAI生成コードの帰属追跡・統計・管理スキル。編集履歴の確認、AI/人間の貢献率分析、コンプライアンス対応レポート生成。

Systematically debug a failing multi-agent workflow from a captured trace. Use when an agent system produces wrong outpu...