Skills MCP Plugins Subagents

Browse by category

DevOps & CI/CD Skills Productivity & Workflow Skills Other Skills Product & Project Management Skills Documentation & Knowledge Skills Code Review & Refactor Skills Backend & APIs Skills Agent Meta & Communication Skills Research Skills Security Skills UX UI & Design Skills Testing & QA Skills See all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →

Agent Skills MCP Servers Plugins Subagents Coding Agents

Collections Official publishers Glossary FAQ Blog Search Saved Feedback

Privacy Terms llms.txt Sitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

home/skills/agent meta & communication

home/skills/agent meta & communication

Agent Meta & Communication Skills

3318 agent meta & communication agent skills for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh. handoff leads with 463k installs a month.

#Type

1handoffCompact the current conversation into a handoff document for another agent to pick up.SkillsJul 2026463k189k
2lark-sharedUse for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing…SkillsJul 2026390k16k
3lark-eventLark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM…SkillsJul 2026387k16k
4lark-vc-agent飞书视频会议会中能力：用于让应用机器人真实加入或离开正在进行的会议，并读取当前身份可见的会中事件、发送会中文本消息或会中表情。适用于用户询问正在开的会议发生了什么、谁在发言、是否共享内容，或需要发现当前可读的进行中会议 ID。不负责已结束会议搜索、参会人快照、纪要、逐字稿或录制查询，这些使用 lark-vc 技能。SkillsJul 2026275k16k
5ask-mattAsk which skill or flow fits your situation. A router over the skills in this repo.SkillsJul 2026248k189k
6paperclip-create-agentCreate new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft…SkillsJul 2026242k7
7paperclipInteract with the Paperclip control plane API to manage tasks, coordinate with other agents, and follow company governance.SkillsJul 2026242k7
8cavecrewDecision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2…SkillsJul 2026220k93k
9using-superpowersUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questionsSkillsJul 2026199k261k
10subagent-driven-developmentUse when executing implementation plans with independent tasks in the current sessionSkillsJul 2026160k261k
11dispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesSkillsJul 2026149k261k
12claude-handoffHand the current conversation off to a fresh background agent that picks up the work immediately.SkillsJul 202688k189k
13orchestrationUse Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch, worker_done/escalation waits, task…SkillsJul 202671k29k
14orca-cliUse the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and the browser embedded inside…SkillsJul 202670k29k
15batch-grill-meA relentless interview that asks every frontier question at once, round by round.SkillsJul 202641k189k
16gws-chatGoogle Chat: Manage Chat spaces and messages.SkillsJul 202627k30k
17gws-chat-sendGoogle Chat: Send a message to a space.SkillsJul 202626k30k
18gws-eventsSubscribe to Google Workspace events.SkillsJul 202625k30k
19gws-events-renewGoogle Workspace Events: Renew/reactivate Workspace Events subscriptions.SkillsJul 202625k30k
20gws-events-subscribeGoogle Workspace Events: Subscribe to Workspace events and stream them as NDJSON.SkillsJul 202625k30k
21agent-developmentThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…SkillsJul 202616k139k
22context-engineeringOptimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure…SkillsJul 202616k80k
23wecomcli-msg企业微信消息技能。提供会话列表查询、消息记录拉取（支持文本/图片/文件/语音/视频）、多媒体文件获取和文本消息发送能力。当用户需要"查看消息"、"看聊天记录"、"发消息给某人"、"最近有什么消息"、"给群里发消息"、"看看发了什么图片/文件"时触发。SkillsJul 202615k2.6k
24using-agent-skillsDiscovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task.SkillsJul 202615k80k
25puaTrae-compatible PUA high-agency governance skill. Use only for explicit PUA requests, repeated failures, user frustration, giving-up/passive behavior, or…SkillsJul 202610k19k
26parallel-feature-developmentCoordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation.SkillsJul 20267.6k38k
27task-coordination-strategiesDecompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing.SkillsJul 20267.5k38k
28team-communication-protocolsStructured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid.SkillsJul 20267.3k38k
29team-composition-patternsDesign optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection.SkillsJul 20267.3k38k
30ask-questions-if-underspecifiedClarify requirements before implementing. Use when serious doubts arise.SkillsJul 20266.6k6.3k
31validate-skillsValidates skills in this repo against agentskills.io spec and Claude Code best practices. Use via /validate-skills command.SkillsJul 20265.3k1.6k
32okx-aiERC-8004 Agent identity: 注册/更新/上架/下架/搜索agent, register/update/activate/deactivate/search — User/ASP/Evaluator(买家/卖家/仲裁者); 我的agent/ASP,…SkillsJul 20264.2k315
33skill-judgeEvaluate Agent Skill design quality against official specifications and best practices.SkillsMar 20264.0k2.2k
34session-handoffCreates comprehensive handoff documents for seamless AI agent session transfers.SkillsMar 20263.9k2.2k
35councilCollect independent perspectives for an explicitly high-stakes or contested judgment. Triggers: "council", "multi-judge review", "independent perspectives".SkillsJul 20262.8k414
36pua-enTrae-compatible English PUA/PIP high-agency governance skill. Use only for explicit PUA/PIP requests, repeated failures, user frustration, passive/giving-up…SkillsJul 20262.6k19k
37expo-skill-feedbackSubmit feedback on an Expo skill—or Expo itself—and control bundled anonymous usage telemetry (off by default / opt-in).SkillsJul 20262.5k2.3k
38skill-writerGuide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md…SkillsJul 20262.5k102k
39mcp-duckgoSkills for web search and content scraping via DuckDuckGo MCP Server. Used when users need online searching and web scraping.SkillsJul 20262.3k146
40mcp-hassThe skill for control Home Assistant smart home devices and query states using MCP protocol.SkillsJul 20262.3k146
41create-cowork-pluginGuide users through creating a new plugin from scratch in a cowork session.SkillsJul 20262.2k23k
42agentforce-architecture-analyzeDeclared architecture snapshot for one Agentforce agent: planner, topics, actions, flows, Apex, prompt templates, and NGA plugins.SkillsJul 20262.2k765
43agent-builderCreate and manage Agent Builder agents and custom tools in Kibana. Use when asked to create, update, delete, test, or inspect agents or tools in Agent Builder.SkillsJul 20262.1k542
44agentforce-observeAnalyze production Agentforce agent behavior using session traces and Data Cloud.SkillsJul 20262.1k765
45agentforce-d360-analyzeData Cloud 360° view of a single Agentforce session. TRIGGER when user asks to trace, inspect, summarize, or describe a specific Agentforce session by session…SkillsJul 20262.1k765
46mcp-vods用于追剧/追番的技能，为AI提供搜索影视播放地址的能力，并支持在小米电视上直接播放。当用户想搜索影视、动漫、短剧、综艺等节目信息或更新进度时使用此技能。SkillsJul 20262.1k146
47agentic-walletCrypto wallet operations via the awal CLI — sign in, check balances, send USDC/ETH/POL/SOL, trade tokens, fund the wallet, and use the x402 payment protocol to…SkillsJun 20262.0k121
48sentry-sdk-skill-creatorCreate a complete Sentry SDK skill bundle for any platform. Use when asked to "create an SDK skill", "add a new platform skill", "write a Sentry skill for X",…SkillsJul 20262.0k244
49configureSet up the Discord channel — save the bot token and review access policy.SkillsJul 20261.9k33k
50accessManage Discord channel access — approve pairings, edit allowlists, set DM/group policy.SkillsJul 20261.9k33k
51mcp-larkBased on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.SkillsJul 20261.9k146
52single-cell-rna-qcPerforms quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive…SkillsJul 20261.8k23k
53pua-jaお前のAIを詰めろ。日本企業の詰め文化と体系的デバッグ方法論で全ての手段を尽くさせる。トリガー条件：(1) タスク失敗2回以上または同じアプローチの微調整ループ; (2)「解決できません」と言おうとする・手動対応を推奨・未検証で環境を原因帰属; (3) 受け身——検索しない・ソースを読まない・指示待ち; (4)…SkillsJul 20261.7k19k
54p9P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself.SkillsJul 20261.7k19k
55pua-loopPUA Loop alias for Codex. Codex subcommand mapping for Claude Code /pua:loop style usage; invoke with $pua-loop.SkillsJul 20261.6k19k
56dingtalk-message钉钉消息发送。当用户提到"钉钉消息"、"发消息"、"发通知"、"群通知"、"群消息"、"Webhook"、"机器人消息"、"机器人发消息"、"工作通知"、"单聊消息"、"群聊消息"、"撤回消息"、"消息已读"、"发送Markdown"、"发卡片消息"、"ActionCard"、"@某人"、"@员工"、"at某人"、"…SkillsJun 20261.5k94
57skill-writerCreate, synthesize, and iteratively improve agent skills following the Agent Skills specification.SkillsJul 20261.5k892
58context-canaryInstall a per-turn canary signal (e.g. starting every reply with the user's name and a turn counter) so silent context degradation becomes visible the moment…SkillsJul 20261.5k134
59handoffWrite compact caller-authored session evidence without choosing continuation. Triggers: "handoff", "write compact session handoff".SkillsJul 20261.3k414
60typstTypst document creation and package development. Use when: (1) Working with .typ files, (2) User mentions typst, typst.toml, or typst-cli, (3) Creating or…SkillsJul 20261.3k110
61code-documentationUse this skill when the user requests to generate, create, or improve documentation for code, APIs, libraries, repositories, or software projects.SkillsJul 20261.3k78k
62implementExecute one bounded RED to GREEN experiment from bead or caller intent; return derived subject identity and check facts.SkillsJul 20261.3k414
63statusReport observable AgentOps evidence without selecting work. Triggers: "status", "show AgentOps status".SkillsJul 20261.3k414
64writing-clearly-and-conciselyApply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text.SkillsOct 20251.2k449
65sharedShared runtime and evidence references loaded only by a consuming skill. Triggers: none — internal library, not user-routable.SkillsJul 20261.2k414
66genshijin超圧縮コミュニケーションモード。原始人のように話してトークン使用量を約75%削減。技術的正確性は完全に維持。強度レベル: 丁寧・通常（デフォルト）・極限の3段階。「原始人モード」「短く」「簡潔に」「トークン節約」と言うか、/genshijin で起動。SkillsJul 20261.1k287
67prompt-optimizerCreates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates.SkillsJul 20261.1k892
68agent-coordinationAgent spawning, lifecycle management, and coordination patterns. Manages 60+ agent types with specialized capabilities.SkillsJul 20261.0k66k
69agent-orchestrator-taskAgent skill for orchestrator-task - invoke with $agent-orchestrator-taskSkillsJul 20261.0k66k
70agent-memory-coordinatorAgent skill for memory-coordinator - invoke with $agent-memory-coordinatorSkillsJul 20261.0k66k
71context-engineeringUnderstand the components, mechanics, and constraints of context in agent systems.SkillsJul 20261.0k1.3k
72agent-coordinator-swarm-initAgent skill for coordinator-swarm-init - invoke with $agent-coordinator-swarm-initSkillsJul 202699766k
73agent-performance-benchmarkerAgent skill for performance-benchmarker - invoke with $agent-performance-benchmarkerSkillsJul 202699766k
74agent-raft-managerAgent skill for raft-manager - invoke with $agent-raft-managerSkillsJul 202699666k
75agent-hierarchical-coordinatorAgent skill for hierarchical-coordinator - invoke with $agent-hierarchical-coordinatorSkillsJul 202699566k
76agent-gossip-coordinatorAgent skill for gossip-coordinator - invoke with $agent-gossip-coordinatorSkillsJul 202699466k
77agent-quorum-managerAgent skill for quorum-manager - invoke with $agent-quorum-managerSkillsJul 202699266k
78carouselWhen the user wants to design, optimize, or audit carousel/slider layouts for content display.SkillsJun 2026990765
79agent-queen-coordinatorAgent skill for queen-coordinator - invoke with $agent-queen-coordinatorSkillsJul 202698866k
80create-ruleUse when found gap or repetative issue, that produced by you or implemenataion agent.SkillsJul 20268851.3k
81apply-anthropic-skill-best-practicesComprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structureSkillsJul 20268751.3k
82plan-do-check-actIterative PDCA cycle for systematic experimentation and continuous improvementSkillsJul 20268711.3k
83create-agentComprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic…SkillsJul 20268581.3k
84create-commandInteractive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integrationSkillsJul 20268551.3k
85build-mcpGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.SkillsJul 20268521.3k
86statusDisplay the current state of the FPF knowledge baseSkillsJul 20268481.3k
87genshijin-help全 genshijin モード・スキル・コマンドのクイックリファレンスカード。 1回限り表示・モード変更なし・状態永続化なし。「/genshijin-help」「原始人ヘルプ」「原始人の使い方」で起動。SkillsJul 2026826287
88genshijin-stats現セッションのリアルトークン使用量と推定削減量を表示。Claude Code セッションログから直接読込 — AI 推定なし。 `/genshijin-stats` で起動。出力は mode-tracker フックが注入し、モデル自身は数値計算しない。SkillsJul 2026791287
89genshijin-crew原始人スタイル subagent への委譲判断ガイド。`genshijin-investigator` (コード位置特定)、 `genshijin-builder` (1-2ファイル編集)、`genshijin-reviewer` (diff レビュー) を inline作業 or vanilla `Explore`…SkillsJul 2026783287
90create-skillScaffolds new agent skills for the dotnet/skills repository. Use when creating a new skill, generating SKILL.md files, or setting up skill directory…SkillsJul 20267594.8k
91qiaomu-goal-meta-skillTurn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evidence, and…SkillsJun 2026747803
92dispatchDispatch background AI worker agents to execute tasks via checklist-based plans.SkillsApr 2026724410
93routerRoutes any game-development request to the right specialized skill(s): it detects the engine (Godot, Unity, Unreal, Bevy, Phaser, PixiJS, three.js, LÖVE,…SkillsJul 2026627357
94create-skill-testScaffolds eval.yaml test files for agent skills in the dotnet/skills repository.SkillsJul 20266254.8k
95efficient-fableUse when running Claude Fable on codebase-heavy or token-heavy work and the user wants Fable to orchestrate research, coding, and testing while cheaper…SkillsJul 20266033.8k
96agent-skills-creatorGuides creation and improvement of best-practice agent skills following the open format specification.SkillsJul 202659671
97huashu-agent-swarm多Agent蜂群并行协作，纯git自组织，适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。SkillsApr 20265851.3k
98agent-skill-creatorCreate cross-platform agent skills from workflow descriptions.SkillsJul 20265762.0k
99skills-voteFind the most relevant external agent skills for the current task, then submit grounded feedback about which skills were actually used and useful in the same…SkillsJul 2026549293
100create-agent-skillsExpert guidance for creating, writing, building, and refining Claude Code Skills.SkillsApr 20264942.0k

More skills categories

DevOps & CI/CD5519 Productivity & Workflow5248 Other4998 Product & Project Management4964 Documentation & Knowledge4545 Code Review & Refactor4435 Backend & APIs4325 Research3084 Security2954 UX UI & Design2699 All Skills →