AI Plugin IndexAI and LLM tools
There are 14,289 ai and llm tools tools for AI assistants in this directory: 8,686 MCP servers and 5,603 skills. The highest scored are Harness, MCP Registry Server, ref-tools-ref-tools-mcp.
The best ai and llm tools MCP servers, compared →Top picks
Harness
autonomous-ai
95Start Claude Code and Codex agents the person can watch, wait for them and read their answers.
AAA
MCP Registry Server
modelcontextprotocol
94Publish and discover MCP servers via the official MCP Registry. Powered by HAPI MCP server.
AFA
ref-tools-ref-tools-mcp
ref-tools
94Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…
AAA
Microsoft Learn MCP
MicrosoftDocs
94Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
ACA
Postman MCP Server
postmanlabs
94Give your AI agents trusted access to the full Postman platform.
AAB
Agent-Native DesignBuilderIO
94Agent-Native design tool - create and edit visual designs with agent assistance
AAA
MCP servers (1684)
- 1Harness autonomous-ai · AI and LLM toolsStart Claude Code and Codex agents the person can watch, wait for them and read their answers.95
- 2MCP Registry Server modelcontextprotocol · AI and LLM toolsPublish and discover MCP servers via the official MCP Registry. Powered by HAPI MCP server.94
- 3ref-tools-ref-tools-mcp ref-tools · AI and LLM toolsProvide your AI coding tools with token-efficient access to up-to-date technical documentation for…94
- 4Microsoft Learn MCP MicrosoftDocs · AI and LLM toolsOfficial Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.94
- 5Postman MCP Server postmanlabs · AI and LLM toolsGive your AI agents trusted access to the full Postman platform.94
- 6Agent-Native Design BuilderIO · AI and LLM toolsAgent-Native design tool - create and edit visual designs with agent assistance94
- 7Agent-Native Slides BuilderIO · AI and LLM toolsAgent-Native Google Slides - generate and edit React presentations94
- 8firebase-mcp firebase · AI and LLM toolsGives AI development tools Firebase-specific capabilities and expertise.94
- 9REA morluto · AI and LLM toolsReverse engineer anything from your terminal or agent with one CLI and MCP server.94
- 10Nhost nhost · AI and LLM toolsLet your users work with their own data through an AI assistant, limited to what they can see.94
- ADYour product hereThis row is seen by people browsing ai and llm tools tools. Book it from $249 a month.See prices →
- 11Pollinations pollinations · AI and LLM toolsAccess Pollinations models and API capabilities through agent tools.94
- 12claude-flow ruvnet · AI and LLM toolsAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.94
- 13dbx t8y2 · AI and LLM toolsQuery databases from AI agents using connections configured in DBX.94
- 14codesign imgly · AI and LLM toolsLocal design engine for AI agents: create, edit and export real, editable designs.94
- 15Add MCP neon-solutions · AI and LLM toolsAdd MCP servers to your favorite coding agents with a single command.94
- 16Neural ruvnet · AI and LLM toolsSelf-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear94
- 17Guidance ruvnet · AI and LLM toolsGuidance Control Plane - Compiles, retrieves, enforces, and evolves guidance rules for Claude Code sessions94
- 18Peekaboo openclaw · AI and LLM toolsmacOS automation MCP server with screen capture, UI interaction, and AI analysis94
- 19Quasar MCP quasarframework · AI and LLM toolsMCP server for AI agents: the Quasar documentation and component API, served from the packages installed in your project94
- 20Agentic devframes · AI and LLM toolsAgent-surface implementation for devframe: installing it next to devframe enables the MCP adapter (devframe/adapters/mcp) and the devframe connect gateway.94
- 21Vanguard Frontier Agentic VincentChuWaiChow · AI and LLM toolsCloud and zero-trust agentic workflow marketplace for skills, agents, rules, MCP references, and compliance-aware architecture.94
- 22Agentic Awesome Skills sickn33 · AI and LLM toolsAAS Core: complete local skill discovery, agent-owned selection, stack validation, and planning, backed by 2,715+ agentic skills.94
- 23Ecc Universal affaan-m · AI and LLM toolsHarness-native agent operating system for Codex, OpenCode, Cursor, Gemini, Claude Code, and terminal workflows - skills, hooks, rules, MCP conventions, and operator control-plane patterns94
- 24Hooks ruvnet · AI and LLM toolsV3 Hooks System - Event-driven lifecycle hooks with ReasoningBank learning integration94
- 25Claims ruvnet · AI and LLM toolsIssue claiming and work coordination module for Claude Flow V394
- 26ChiR24-unreal_mcp ChiR24 · AI and LLM toolsControl Unreal Engine to browse assets, import content, and manage levels and sequences. Automate…93
- 27Marrow AI: Control Layer for AI Agents getmarrow · AI and LLM toolsApproval gate and audit trail for AI agent actions: policy check first, proof after. Any MCP client.92
- 28EdgarTools dgunning · AI and LLM toolsOpen-source SEC EDGAR toolkit — 13 tools, 7 prompts, every filing type. No API key required.92
- 29Bowmark bowmark-ai · AI and LLM toolsDo things on live websites: prices, availability, quotes, bookings, anything behind a form or login.91
- 30dossier imboard-ai · AI and LLM toolsMCP server for dossier automation standard - enables LLMs to discover, verify, and execute dossiers91
- 31starreel starreel · AI and LLM toolsTurn a script into a finished, downloadable short-drama episode — via MCP or REST.91
- 32comfyui-mcp artokun · AI and LLM toolsMCP server + Claude Code plugin for ComfyUI: run workflows, generate images, manage models & VRAM.91
- 33Agent-Native Forms BuilderIO · AI and LLM toolsAgent-Native form builder - create, edit, and manage forms91
- 34PraisonAI MervinPraison · AI and LLM toolsAI Agents Framework with Self Reflection and MCP support91
- 35Context7 upstash · AI and LLM toolsUp-to-date docs for AI agents91
- 36Agency Orchestrator jnMetaCode · AI and LLM toolsMulti-agent YAML workflow engine — 211 AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 10 LLM providers, 7 need no API key.91
- 37Decocms decocms · AI and LLM toolsDeco CMS — Self-hostable MCP Gateway for managing AI connections and tools91
- 38Geo usenotra · AI and LLM toolsRequest capture SDK for AI traffic attribution and agent feedback collection91
- 39Blume haydenbleasel · AI and LLM toolsThe open-source docs framework for humans and agents.91
- 40Webcodex yyjeqhc · AI and LLM toolsConnect ChatGPT, Claude, and other AI agents to repositories and developer tools on your own machines.91
- 41Agency Orchestrator jnMetaCode · AI and LLM toolsMulti-agent YAML workflow engine — 276 CN + 191 EN + 5 more language libraries of AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 20+ API providers, plus 10 key-free options (coding-CLI s91
- 42MCP Extensions openai · AI and LLM toolsOpenAI extensions for MCP servers and apps.91
- 43MCP Http Server bytedance · AI and LLM toolsHigh performance HTTP Server for MCP91
- 44Neurolink juspay · AI and LLM toolsThe pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.0000290
- 45Veryfront veryfront · AI and LLM toolsThe simplest way to build AI-powered apps90
- 46Paqad AI Eliyce · AI and LLM toolsSpec-driven development framework — AI agents that think before they type90
- 47strata Klavis-AI · AI and LLM toolsMCP server for progressive tool usage at any scale (see https://klavis.ai)89
- 48mcp-server PackmindHub · AI and LLM toolsPackmind captures, scales, and enforces your organization's technical decisions.89
- 49mcp decionis · AI and LLM toolsAuthorize consequential AI agent actions before execution89
- 50String Utility Belt String-Utility-Belt · AI and LLM toolsMCP server exposing String Utility Belt's utilities and pipelines as tools for AI agents.89
- 51pm-claude-skills mohitagw15856 · AI and LLM tools1295 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.89
- 52ros-mcp-server robotmcp · AI and LLM toolsConnect AI models like Claude & ChatGPT with ROS robots using MCP89
- 53Skills hasna · AI and LLM toolsSkills library for AI coding agents89
- 54Agents Dev CLI amtiYo · AI and LLM toolsOne config to rule them all — sync MCP servers, skills and AGENTS.md across 18 AI coding tools, and package them as Agent Plugins.89
- 55Stitchkit max-listov · AI and LLM toolsContract-first backend framework — one defineContract() into an HTTP API, MCP tools, AI-agent tools and a typed client. Bun and Node.89
- 56Relay Companion davidkariuki123 · AI and LLM toolsInstall Relay for Claude Code, Cowork, and Codex, then sign in from the Relay pill.89
- 57Commonlyai CLI Team-Commonly · AI and LLM toolsThe Commonly CLI — connect agents, manage pods, iterate fast89
- 58Agentation MCP benjitaylor · AI and LLM toolsMCP server for Agentation - visual feedback for AI coding agents89
- 59Agent Blackboard jonathanong · AI and LLM toolsClient library, CLI, and MCP server for Agent Blackboard session entries.89
- 60Evolver MCP EvoMap · AI and LLM toolsEvolver MCP server (agent 工具发现入口)89
- 61AI MCP UI eclipse-theia · AI and LLM toolsTheia - MCP UI Integration89
- 62Tetrees MCP TetreesEX · AI and LLM toolsOwn, grow and trade portable agent intelligence via TAIP/1 Packs and MCP.88
- 63FireCMS Cloud firecmsco · AI and LLM toolsManage FireCMS Cloud from an AI agent: Firestore data, collections, schemas and users.88
- 64wigolo KnockOutEZ · AI and LLM toolsLocal-first web intelligence MCP server for AI coding agents88
- 65SafeDep Vet MCP safedep · AI and LLM toolsProtect your AI agents and IDEs from malicious open-source packages.88
- 66bernstein sipyourdrink-ltd · AI and LLM toolsThe open-source governance layer for AI agents. Byte-identical run receipts, 40+ adapters, air-gap.88
- 67tldraw tldraw · AI and LLM toolsDraw and visually collaborate with your agents on tldraw's canvas.88
- 68LLM Sandbox vndee · AI and LLM toolsSecurely run LLM-generated code in isolated containers across 7 languages and 3 container backends.88
- 69Gitnexus abhigyanpatwari · AI and LLM toolsGraph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.88
- 70Devtools MCP foldkit · AI and LLM toolsMCP server exposing Foldkit DevTools to AI agents (Claude Code, Cursor, etc.)88
- 71AI stacksjs · AI and LLM toolsStacks Artificial Intelligence.88
- 72Proagentstore CLI ProAgentStore · AI and LLM toolsCLI for creating, publishing, and running ProAgentStore agents88
- 73Callscript vercel-labs · AI and LLM toolsa tool-calling script language for LLMs - the model authors ONE small script (plain JS, compiled to a validated, bounded, inert JSON plan - never executed) instead of calling tools one at a time. Adapter-based: mount AI SDK tools or plain { name, execute88
- 74Axiom MCP CharlesWiltgen · AI and LLM toolsMCP server for Axiom — Apple-platform development skills, agents, and tools88
- 75X Agent Tools mui · AI and LLM toolsShared tooling behind MUI's agent integrations (MCP server, CLI, ACP).88
- 76Wp Playground MCP WordPress · AI and LLM toolsMCP server for WordPress Playground - enables AI agents to interact with the WordPress Playground website.88
- 77Elicitly elicitly · AI and LLM toolsHuman-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor87
- 78TestivAI testivai · AI and LLM toolsLocal-first visual regression for AI agents: verdicts, diff images, explain_snapshot. No API key.87
- 79UN Charter 1945 arxohq · AI and LLM toolsUN Charter (1945, as amended) as an executable model with worked cases; not UN-affiliated87
- 80photoshop-mcp alisaitteke · AI and LLM toolsMCP server for Adobe Photoshop — 128 tools (generative AI + recipes), standalone web UI. Control Ph…87
- 81Tapo MCP mihai-dinculescu · AI and LLM toolsMCP server for discovering and controlling TP-Link Tapo smart home devices via AI Agents87
- 82inspo Nutlope · AI and LLM toolsReal production websites for coding agents: palettes, fonts, fold autopsies and reference JSX.87
- 83Summer Engine summerengine · AI and LLM toolsThe game engine built for AI. Any agent makes a multiplayer game and publishes it.87
- 84Attestix VibeTensor · AI and LLM toolsAI agent identity, signed credentials, delegated authority and governance evidence.87
- 85Sanity sanity-io · AI and LLM toolsDirect access to your Sanity projects (content, datasets, releases, schemas) and agent rules87
- 86Vulnify vulnify · AI and LLM toolsAsk Vulnify before an AI agent acts. Check, record, and read policy decisions.87
- 87Js Reverse MCP zhizhuodemao · AI and LLM toolsJS reverse engineering MCP server with agent-first tool design and built-in anti-detection. 为 AI Agent 设计的 JS 逆向 MCP Server，内置反检测。87
- 88Fauxnix CLI 20000419 · AI and LLM toolsFauxnix — run Linux-style commands on Windows via deterministic PowerShell translation. No VM, no WSL. MCP server + CLI for AI agents.87
- 89Taiga AI MCP Server teemu-ijas · AI and LLM toolsTaiga for AI coding assistants: read products, policies, initiatives and runs, and operate the line, over MCP87
- 90AI Hist AgentWorkforce · AI and LLM toolsLocal history ingestion, storage, evidence, SDK, CLI and MCP server.87
- 91Agent Network sleep2agi · AI and LLM toolsAI Agent Network CLI — Local-first multi-agent orchestration across 6 runtimes (Claude Code CLI / Claude Agent SDK / Codex SDK / Codex app-server / Grok Build ACP / OpenCode CLI) and 8+ LLM providers. Apache 2.0.87
- 92Gcf blackwell-systems · AI and LLM toolsThe AI-native wire format for structured data. 50-92% fewer tokens than JSON, with multi-turn delta encoding for agent loops. 100% comprehension on every frontier model. Zero dependencies.87
- 93Ztrack volter-ai · AI and LLM toolsA typechecker for your issue tracker — every checked acceptance criterion must cite a real commit and proof, verified by `ztrack check` (and enforced on coding agents via a loop gate).87
- 94Agentic Engineering Harness JamesMorales04 · AI and LLM toolsOSS-first engineering harness for deterministic, spec-driven, issue-driven, audit-governed and orchestration-first multi-agent software delivery.87
- 95Stitch google-labs-code · AI and LLM toolsAgent-first CLI and MCP server for Google Stitch87
- 96Metavr meta-quest · AI and LLM toolsMeta VR CLI (metavr) - CLI and MCP server for Meta Quest development, device management, performance tracing, and AI-assisted workflows87
- 97Config bgauryy · AI and LLM toolsOctocode unified env + config loader — zero deps, shared by MCP, CLI, extension, agent, and standalone skills.87
- 98Jotbus Launchable-AI-Inc · AI and LLM toolsEnd-to-end encrypted scratchpad for coding agents across machines, vendors and people.86
- 99Opedd — Licensed Content for AI Opedd · AI and LLM toolsContent licensing for the AI era: licensed, rights-cleared content for AI agents.86
- 100Codeman Ark0N · AI and LLM toolsStart, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman86
- 101mcp-server cachly-dev · AI and LLM toolsSolve it once. From then on, your AI knows. Experience for coding agents, hosted in the EU.86
- 102Strategic Agent Reasoning MCP putervision · AI and LLM toolsStrategic BDI reasoning engine for autonomous AI agents with spatial utility and replanning.86
- 103rigour rigour-labs · AI and LLM toolsLets coding agents review their change, find an existing helper, and recall the team's lessons.86
- 104CNEquity rootSunc · AI and LLM toolsChina A-share data lake for AI agents: prices, fundamentals, flows and events, point-in-time.86
- 105SandBase Harness sandbaseai · AI and LLM toolsStdio MCP bridge for SandBase Harness agents, sessions, turns, artifacts, and cancellation.86
- 106mcp Trusty-Squire · AI and LLM toolsCredential broker that signs your AI agent up to SaaS dev tools, within a signed spending mandate.86
- 107Riffle noetive · AI and LLM toolsYour agent uses the web as text, not screenshots. Several steps per call, only changes come back.86
- 108FormLM formlm · AI and LLM toolsBuild AI-powered forms, scored assessments and professional reports on FormLM, by natural language.86
- 109Agent Harness Generator ruvnet · AI and LLM toolsLibrary/core package for the Agent Harness Generator. Pair with `metaharness` for the CLI. Re-exports scaffold(), validate(), and the deterministic-analysis pipeline from `metaharness` so consumers can `import { scaffold } from '@ruvnet/agent-harness-gene86
- 110Tongflow Studio tong-io · AI and LLM toolsTongFlow's media studio for agents: projects as plain folders, one TongFlow workflow per generated asset stored next to its outputs, deterministic media generation — served as an MCP server with a Studio web page.86
- 111AI Rulez Goldziher · AI and LLM toolsAuthor, generate, validate and govern AI agent rules, skills, plugins and MCP configuration across 52 coding assistants. Review with verified model evidence, evaluate skills, lock and sign dependencies, and publish bundles. CLI, MCP server and Go API.86
- 112Workit Codex BrainerVirus · AI and LLM toolsWorkit Codex CLI/desktop plugin — shared MCP transport, hooks, method skills, and verifier/reviewer/implementer agents86
- 113Takt nrslib · AI and LLM toolsWorkflow control for AI coding agents86
- 114LLM Checker signerless · AI and LLM toolsIntelligent CLI tool with AI-powered model selection that analyzes your hardware and recommends optimal LLM models for your system86
- 115Agent Safe Pipeline decionis · AI and LLM toolsExecution Authority for AI agents: agents propose, Decionis independently decides ALLOW / ESCALATE / BLOCK, Presence verifies human approval on escalation, and a SafeExecutor runs only on a single-use intent-bound grant. Every decision leaves a Decision D86
- 116Devbar Sh TimMikeladze · AI and LLM toolsDrop-in toolbar for any website. Annotate the UI and capture selectors, computed styles, React component trees, and screenshots as an agent-ready prompt.86
- 117Hackmyagent opena2a-org · AI and LLM toolsFind it. Break it. Fix it. The hacker's toolkit for AI agents.86
- 118Kernel ruvnet · AI and LLM toolsCross-platform kernel for the agent-harness-generator — wasm primary, NAPI-RS native fallback86
- 119Host Claude Code ruvnet · AI and LLM toolsClaude Code host adapter for agent-harness-generator (MCP + hooks + .claude/settings.json)86
- 120Computer Use Linux agent-sh · AI and LLM toolsNative Linux desktop control for AI agents (MCP server, Pi tools, and CLI): semantic AT-SPI accessibility trees, screenshots, compositor window targeting, Wayland/X11 input, and an on-screen activity indicator.86
- 121Host Opencode ruvnet · AI and LLM toolsOpenCode (sst/opencode) host adapter for agent-harness-generator. Emits .opencode/opencode.json (ADR-036).86
- 122Chorus Openclaw Plugin Chorus-AIDLC · AI and LLM toolsOpenClaw plugin for Chorus AI-DLC collaboration platform — native MCP + SSE real-time events86
- 123Host Hermes ruvnet · AI and LLM toolsHermes Agent (NousResearch) host adapter for agent-harness-generator (MCP + <think>/<tool_call> scrubbing)86
- 124Host Codex ruvnet · AI and LLM toolsOpenAI Codex CLI host adapter for agent-harness-generator (MCP via ~/.codex/config.toml)86
- 125Host Openclaw ruvnet · AI and LLM toolsOpenClaw (personal AI assistant) host adapter for agent-harness-generator (MCP via ~/.openclaw/openclaw.json + workspace skills)86
- 126AI MCP Server eclipse-theia · AI and LLM toolsTheia - MCP Server86
- 127Docs MCP Server lynx-family · AI and LLM toolsA MCP Server providing Lynx documentation resources for LLMs, with carefully designed prompting.86
- 128Prismer MCP Server Prismer-AI · AI and LLM toolsMCP Server for Prismer Cloud — Knowledge API for AI Agents86
- 129Docs MCP Server Canary lynx-family · AI and LLM toolsA MCP Server providing Lynx documentation resources for LLMs, with carefully designed prompting.86
- 130Unraid MCP dinglebear-ai · AI and LLM toolsMCP server for Unraid API — provides tools to interact with an Unraid server's GraphQL API.85
- 131Raven rhinocap · AI and LLM toolsDesign intelligence for coding agents: audits, design systems, and a taste profile agents consult.85
- 132Gemmein gemmeinhq · AI and LLM toolsGemmein docs, API reference, error explainers and a live integration check for coding agents.85
- 133Zapier zapier · AI and LLM toolsHosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.85
- 134Clipwright seocombat · AI and LLM toolsTalking-actor and faceless short videos from your AI agent, with a free quote before each render85
- 135touchdesigner-mcp-server 8beeeaaat · AI and LLM toolsMCP server for TouchDesigner - Control and operate TouchDesigner projects through AI agents85
- 136Emilia Protocol emiliaprotocol · AI and LLM toolsExact-action approval for consequential agent actions: request, track, and verify signed receipts.85
- 137Concord MCP Get-Concord-AI · AI and LLM toolsCross-harness communication and shared work-state for AI coding agents.85
- 138GripForge gripforgeai · AI and LLM toolsTurn prompts into production-ready game assets: animated characters, textures, terrain, VFX, HUD.85
- 139aiterm-mcp kitepon · AI and LLM toolsPersistent terminals and one launcher for Claude, Codex, Grok, and Cursor harnesses.85
- 140Priors priors-agents · AI and LLM toolsPay x402 APIs in USDG on Robinhood Chain, borrow and repay a Priors credit line, check records.85
- 141vibe-check-mcp-server PV-Bhat · AI and LLM toolsMetacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety85
- 142codebase-doctor subhajitlucky · AI and LLM toolsRead-only codebase audits for coding agents: secrets, RLS, deps, review verdicts. No writes.85
- 143AI AppSec subodhkc · AI and LLM toolsEvidence-backed AppSec for AI applications and agents. Powered by HAIEC.85
- 144VITNA – Containment for rogue AI agents COSTRINITY · AI and LLM toolsGuard wraps stdio MCP servers: risky calls wait for a person; no answer, no run. Remote: cooperative85
- 145MCP Server Pin AI modelcontextprotocol · AI and LLM toolsMCP server for PIN AI integration85
- 146Remcp getremcp · AI and LLM toolsReMCP device client: pair a computer with ReMCP and run the outbound-only agent that hosts the local MCP runtime.85
- 147Kaddo MCP Kaddo-kdd · AI and LLM toolsMCP server for Kaddo project knowledge: read-only resources/tools/prompts plus safe derived generation under .kaddo/.85
- 148Plugin MCP maritonx · AI and LLM toolsMCP server for Easy CMS: let AI assistants read and write content with API keys (experimental)85
- 149Line Harness MCP Server Shudesu · AI and LLM toolsMCP server for L Harness — operate a LINE official account from AI agents over MCP85
- 150Agent Skills Standard MCP HoangNguyen0403 · AI and LLM toolsMCP server that lets any AI agent (Claude, Cursor, Antigravity, Kiro, Continue, Gemini) load and audit skills from agent-skills-standard.85
Skills (413)
- 1frontend-api-contracts OpenHands · AI and LLM toolsThis skill should be used when the user asks to "add an API call", "change a backend", "update settings persistence", "change conversation events", "fix backend auth", "add Agent Server support", or changes src/api, backend registry, Cloud/runtime transport, settings, secrets, compatibility, or conversation resume behavior.84
- 2project-structure microsoft · AI and LLM toolsExplains the project structure of the agent-framework .NET solution84
- 3fal-platform sickn33 · AI and LLM toolsPlatform APIs for model management, pricing, and usage tracking84
- 4gsd-review open-gsd · AI and LLM toolsRequest cross-AI peer review of phase plans from external AI CLIs84
- 5peon-ping-toggle PeonPing · AI and LLM toolsToggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sounds during a Claude Code session. Also handles config changes like volume, pack rotation, categories — any peon-ping setting.83
- 6cli-anything-openrefine HKUDS · AI and LLM toolsUse OpenRefine through an agent-native CLI for importing messy data, applying JSON operation histories, inspecting rows, exporting cleaned data, and managing session undo/redo.82
- 7host-observer thedotmack · AI and LLM toolsUse this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation XML, never prose.82
- 8routing-calibration vllm-project · AI and LLM toolsUse when calibrating or validating a maintained routing recipe against live model backends, including probe manifests and evidence reports.82
- 9plano-advanced-patterns katanemo · AI and LLM toolsDesign advanced Plano architectures. Use for multi-listener systems, prompt target schema quality, and layered orchestration patterns.82
- 10engram-cultural-norms Gentleman-Programming · AI and LLM toolsCultural and collaboration norms for Engram contributors and agents. Trigger: Starting substantial work, reviewing changes, or defining team conventions.82
- 11resource-budget bojieli · AI and LLM tools估算一次模型执行能否放入给定硬件，并定位计算、访存和串行等待的下界。用于粗估容量、时延或优化收益；具体模型结构另用 model-footprint。82
- 12datachain-core datachain-ai · AI and LLM toolsUse ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced. If the request mentions creating, saving, listing, exploring datasets or buckets, use datachain-knowledge instead.82
- 13humanize epoko77-ai · AI and LLM toolsAI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. humanize-korean 파이프라인을 shim 의 route_hint 가 정한 경로(light 1콜 · standard 2콜 · heavy 3+콜)로 실행하고 `--strict`면 heavy 고정. 트리거 — "/humanize".82
- 14limerick genkit-ai · AI and LLM toolsRespond as a single limerick. Use for playful or comic answers, or when the user asks for a limerick.81
- 15handover-ticket EverMind-AI · AI and LLM tools海岚旅行转交单模板（HL-CS-FORM-05）：占位申请、规划通话、投诉、团队、质检升级五类转交单的字段、存放位置和命名规则。81
- 16premium-package EverMind-AI · AI and LLM tools海岚旅行定制游产品说明（HL-P-03）：基础5晚，适用对象、包含与不含、规划通话流程、常见目的地（含高原标记）、每日安排框架、人数上限。81
- 17fm weave-os · AI and LLM toolsAlias for force-model — pin this Codex session to a specific model through the Weave Router.80
- 18router-feedback weave-os · AI and LLM toolsSubmit feedback about a Weave Router decision or model performance.80
- 19nat-installation NVIDIA · AI and LLM toolsUse when installing or configuring NVIDIA NeMo Agent Toolkit, verifying the `nat` CLI, setting up optional extras, or creating a first hello-world workflow.80
- 20agent-plan DmNote-App · AI and LLM tools구현 전 독립 서브에이전트에게 계획을 검증받는다. 다파일·설계 갈림·실패 비용이 큰 변경에 사용자가 직접 호출.80
- 21authoring-skills flutter · AI and LLM toolsGuides the creation of high-quality, effective skills for agentic workflows. Use when creating or modifying skills in the .agents/skills/ directory.80
- 22cc-skill-strategic-compact davila7 · AI and LLM toolsDevelopment skill from everything-claude-code79
- 23standards-check promptfoo · AI and LLM toolsChecks that a project follows standard conventions79
- 24workload-modeling bojieli · AI and LLM tools把持续请求、多轮 Agent、实时交互或 RL 轨迹转成容量与时延负载。用于估算峰值、状态驻留和完成任务的真实成本。79
- 25k-skill-cleaner NomaDamas · AI and LLM toolsInterview the user and inspect coding-agent skill trigger counts to recommend unused K-skills for removal.79
- 26converting-pytorch-to-litert google-ai-edge · AI and LLM toolsConverts PyTorch models (e.g. ResNet, timm, HuggingFace transformers) directly to LiteRT (.tflite) flatbuffer format. Use when converting PyTorch models to TFLite, setting up export environments, or troubleshooting torch-to-litert conversion bugs. Don't use for ONNX exports or converting existing TensorFlow models.79
- 27vibe-agents KhazP · AI and LLM toolsCreate project agent instructions and tool configuration from agreed product and technical decisions.79
- 28gemini the-open-agent · AI and LLM toolsGemini CLI for one-shot Q&A, summaries, and generation.78
- 29gsd:eval-review davepoon · AI and LLM toolsRetroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan78
- 30update-agent-instructions home-assistant · AI and LLM toolsUse this if the user wants to update the agent instructions for the Home Assistant website.78
- 31curiosity-loop Bitterbot-AI · AI and LLM toolsUse when the user asks what you are curious about or do not know, wants dream-synthesized insights, or after you investigate an exploration target. Not for plain fact recall (use memory_search).78
- 32openloomi-setup melandlabs · AI and LLM toolsOpenLoomi first-use setup and readiness guidance for skill-only agent runtimes. Use when OpenLoomi is not yet installed, the local API is not reachable, the session/token is missing, or the user needs a manual install and launch walkthrough before using OpenLoomi skills.78
- 33genebass-gene-burden-skill openai · AI and LLM toolsSubmit compact Genebass gene burden requests for one Ensembl gene ID and one burden set. Use when a user wants concise Genebass PheWAS summaries78
- 34hello autonomous-ai · AI and LLM toolsGreet the workspace. Use when the user asks the Starter harness to say hello or to prove the skill is loaded.77
- 35evidence-rules input-output-hk · AI and LLM toolsEvidence and citation rules for all agents. Requires factual claims to be cited, unknowns to be explicit, and direct quotes when wording matters.77
- 36history cosmosgl · AI and LLM toolsDraft a new history entry, or update the most recent one with `--update`. Use after a meaningful commit or set of commits. Provide the "why" as an argument — /history the reason this change was made. Use /history --update to extend the latest entry without prompting.77
- 37release openai · AI and LLM toolsCut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.77
- 38think-harder foryourhealth111-pixel · AI and LLM tools4-phase structured analysis wrapper for vibe pre-routing (compatible with claude-code-settings think-harder semantics).77
- 39judge-retired-position sno-ai · AI and LLM toolsJudge whether one stored row states a retired profile position as current.77
- 40alfworld-open-receptacle zjunlp · AI and LLM toolsThis skill opens a closed receptacle to access its contents. It should be triggered when an agent needs to interact with items inside a closed container (e.g., fridge, microwave, drawer). The skill takes a receptacle identifier as input, performs the open action, and outputs the observation of the interior, enabling subsequent item retrieval or placement.77
- 41browse-and-evaluate MoizIbnYousaf · AI and LLM toolsUse when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.77
- 42interactivity-best-practices remotion-dev · AI and LLM toolsBest practices for writing Remotion animations that stay intuitive for agents and editable in Remotion Studio Visual Mode.76
- 43shell zylos-ai · AI and LLM toolsCLI interactive mode channel. Delivers Claude responses to the zylos shell REPL via Unix socket.76
- 44mvp-plan TechNomadCode · AI and LLM toolsPlan the MVP build from a PRD and an MVP scope, as a full development plan or an ultra-lean build spec, with the AI Product Development Toolkit's planning prompts.76
- 45mastra-docs mastra-ai · AI and LLM toolsDocumentation guidelines for Mastra. Use this skill when creating, editing, moving, deleting, or reviewing Mastra documentation, sidebars, redirects, or docs components.76
- 46route-by-query-shape Bitterbot-AI · AI and LLM toolsWhen the agent calls memory_search with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledge_graph backend where it will actually find the answer.76
- 47decompile Zfinix · AI and LLM toolsTurn a function into clean, readable C with real names, even when the engine only gives disassembly. The agent is the decompiler.76
- 48google-sheets gemini-cli-extensions · AI and LLM toolsActivate this skill when the user wants to find, read, or analyze Google Sheets spreadsheets. Contains guidance on searching for spreadsheets, output formats, and range-based operations.76
- 49semantic-anchor-onboarding LLM-Coding · AI and LLM toolsDEPRECATED alias of semantic-contracts-installer. Renamed because the skill's high-value job is installing Semantic Contracts (compositions the LLM cannot guess), not bare anchor lists. Use semantic-contracts-installer instead; this alias forwards to it and will be removed after one release.76
- 50stop-slop Xe · AI and LLM toolsRemove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.76
- 51mcp arcjet · AI and LLM toolsConnect an AI coding client to the Arcjet MCP server at https://api.arcjet.com/mcp. Use when the client has built-in MCP support or the CLI is not available.76
- 52google-slides gemini-cli-extensions · AI and LLM toolsActivate this skill when the user wants to find, read, or extract content from Google Slides presentations. Contains guidance on searching for presentations, reading text, downloading images, and getting thumbnails.76
- 53slopo-analyze-ignore rafal-qa · AI and LLM toolsSlopo reports similar code in the whole codebase, and agent ignores non-duplicates.76
- 54django-create-model fossasia · AI and LLM toolsSteps for creating or modifying a Django model75
- 55Agent Skills xiaoyuanda666-ship-it · AI and LLM toolsExplain, inspect, create, and maintain Bailongma Agent Skills packages built around SKILL.md instructions.75
- 56memorix-troubleshooting AVIDS2 · AI and LLM toolsUse when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.75
- 57openai Anil-matcha · AI and LLM toolsCheck OpenAI API access and list the models your key can use. Read-only. Trigger phrases: openai, openai models, what models do I have access to.75
- 58openagentskill-registry Leon-Drq · AI and LLM toolsDiscover, compare, audit, and safely install reusable AI Agent Skills with OpenAgentSkill. Use whenever an agent needs a capability it does not already have, must compare Skill alternatives, or needs evidence before installing third-party instructions.75
- 59anthropic Anil-matcha · AI and LLM toolsCheck Anthropic API access and list available Claude models. Read-only. Trigger phrases: anthropic, claude models, anthropic api.75
- 60identify-key-failures frenzymath · AI and LLM toolsSynthesize the common stuck points across failed decomposition plans and recursive sub-agent reports. Use when the current batch of decomposition plans has failed.75
- 61openrouter Anil-matcha · AI and LLM toolsBrowse OpenRouter's model catalog and check your key usage. Trigger phrases: openrouter, model prices, openrouter key.75
- 62hello-wework wecode-ai · AI and LLM toolsUse the bundled example MCP tool to demonstrate a complete Wework plugin.74
- 63pm-sim agent-next · AI and LLM tools[DEPRECATED] Renamed to polymarket-paper-trader. Run: npx clawhub install polymarket-paper-trader74
- 64claude-buddy autonomous-ai · AI and LLM toolsMOVED — canonical skill now lives in the platform skills tree.74
- 65telemetry microsoft · AI and LLM toolsUse this skill when the user wants to enable, disable, turn on or off, opt out of, opt in to, or check the status of model-apps telemetry or its usage data. Triggers: "disable telemetry", "turn off telemetry", "opt out of telemetry", "stop collecting usage data", "enable telemetry", "telemetry status".74
- 66图片编辑工作流 ddcat-ai · AI and LLM tools基于画布图片节点，用自然语言和参考图完成图片编辑。74
- 67claude-md-budget jgravelle · AI and LLM toolsHow to keep CLAUDE.md under its character Floor without deleting a rule: measure sections first, rotate by derivability, two edits per rotation. Load in /release step 6 and before any CLAUDE.md rotation or split.74
- 68office-skill-authoring it235 · AI and LLM toolsUse when creating or reviewing Office AI Skills. Enforces SKILL.md directory structure, concise YAML metadata, progressive disclosure, references, scripts, app scope, and allowed tool boundaries.74
- 69validation-workflow specula-org · AI and LLM toolsTLA+ Verification workflow (orchestration). Use when: running the full verification loop — iterating between trace validation and model checking until both pass, ensuring spec faithfully models the system.73
- 70agentlas-hub agentlas-ai · AI and LLM toolsUse when the user types /agentlas-hub, /agentlas hub, or /hep-hub to staff only from the public Agentlas Hub marketplace.73
- 71agentlas-local agentlas-ai · AI and LLM toolsUse when the user types /agentlas-local, /agentlas local, or /hep-local to staff only from registered Local packages.73
- 72agentlas-graph agentlas-ai · AI and LLM toolsUse when the user types /agentlas-graph, /agentlas graph, or /hep-graph to create, list, inspect, or run Agentlas automation graphs.73
- 73agentlas-graph agentlas-ai · AI and LLM toolsUse when the user types /agentlas-graph, /agentlas graph, or /hep-graph to create, list, inspect, or run Agentlas automation graphs.73
- 74agentlas-cloud agentlas-ai · AI and LLM toolsUse when the user types /agentlas-cloud, /agentlas cloud, or /hep-cloud to staff only from the signed-in owner's private Cloud packages.73
- 75agentlas-storm agentlas-ai · AI and LLM toolsUse when the user types /agentlas-storm, /agentlas storm, /hep-storm, or says @Hephaestus storm <goal> to drive a goal through the force-robust Stormbreaker loop with real Agentlas specialists.73
- 76agentlas-upload agentlas-ai · AI and LLM toolsPublish an Agentlas package to Agent Cloud or the public Hub.73
- 77agentlas-graph agentlas-ai · AI and LLM toolsBuild an Agentlas automation by describing it, list saved ones, or request a run.73
- 78agentlas-storm agentlas-ai · AI and LLM toolsRun a force-robust Stormbreaker loop — route to real agents, execute a verified pipeline to completion.73
- 79install-verification agentlas-ai · AI and LLM toolsUse before claiming that the package can be installed or published. Verifies structure, adapters, schemas, executable scripts, and public-safety boundaries.73
- 80ai-disclosure-policy mohitagw15856 · AI and LLM toolsSummarise what Ai Disclosure Policy does in one line. Use when asked to [trigger phrases the user would say]. Produces [the concrete artifact].73
- 81openhue Bitterbot-AI · AI and LLM toolsControl Philips Hue lights/scenes via the OpenHue CLI.73
- 82director jamditis · AI and LLM toolsDirects the current request through configured lower-tier agents. Use only for explicit /director or /dev-toolkit:director invocation.73
- 83agentlas-one agentlas-ai · AI and LLM toolsUse when the user types /agentlas-one on|off, /agentlas one on|off, or asks to enable/disable the persistent personal agent mode.73
- 84credential-harvest-landing-page-copy SpecterOps · AI and LLM toolsDraft believable copy for a credential-harvest landing page. Use when creating target-specific text for a fake login, SSO prompt, meeting join page, or internal portal notice.73
- 85creative-writing-modes haowjy · AI and LLM toolsCreative-writing addendum to /llm-writing. Load when putting prose on the page: draft, revise, bridge, vary, or polish.73
- 86aitune-inspect ai-dynamo · AI and LLM toolsUse when inspecting a PyTorch model or pipeline to identify tunable submodules, detect dynamic shapes, and determine the recommended tuning mode before optimization.73
- 87delayed-restart-app XiaoLuoLYG · AI and LLM tools安排延迟重启本 Agent 所在的服务（jiuwenclaw app）。执行后当前 Agent 进程会被终止并重新启动，当前会话会断开。用于用户要求重启、配置更新需生效、或服务异常需重载时。使用 bash 调用脚本。73
- 88OK Status Skill AgentEra · AI and LLM toolsReturn a structured OK status for model-pool validation.72
- 89moai-loop modu-ai · AI and LLM toolsIteratively fix issues until all resolved or max iterations reached72
- 90moai-codemaps modu-ai · AI and LLM toolsScan codebase and generate architecture documentation in codemaps/72
- 91moai-goal modu-ai · AI and LLM toolsManage condition goals or create and operate an approved autonomous mission72
- 92moai-project modu-ai · AI and LLM toolsGenerate project documentation (product.md, structure.md, tech.md, codemaps/)72
- 93review-harness Kaggle · AI and LLM toolsReview an existing LLM harness for correctness and gameplay-impacting bugs (prompt accuracy, parser robustness, replay-archive scanning, cross-harness sweeps)72
- 94run-in-sandbox breadboard-ai · AI and LLM toolsTeaches you how to properly operate in the sandboxed environment you're in.72
- 95chatgpt-agent-setup hashgraph-online · AI and LLM toolsChoose ZIP or MCP mode. ZIP needs no setup; configure this workspace's Bridge and ChatGPT Connector only when the user explicitly chooses MCP.72
- 96aiox-handoff SynkraAI · AI and LLM toolsCreate an AIOX agent handoff artifact when switching personas. Use on agent switch, handoff, or /aiox-handoff.72
- 97ccb-diagnose SeemSeam · AI and LLM toolsDiagnose a named CCB managed agent using runtime, job-lineage, and provider evidence.72
- 98braid quarto-dev · AI and LLM toolsReference for braid, this project's issue tracker (the "skein" of "strands"). Use whenever you need braid command syntax — finding ready work, creating/updating/closing strands, dependencies, ready/blocked queries — or when a user mentions braid, a strand, or a bd- issue id and you need the authoritative, version-matched usage. The body defers to `braid agents-info` for the full guide.72
- 99list-topics microsoft · AI and LLM toolsList all topics in the Copilot Studio agent with their trigger types, phrases, and action counts. Use when the user wants to see what topics exist.72
- 100resume-pipeline ai-analyst-lab · AI and LLM toolsResume a specifically identified analysis using its verified run-local artifacts and controller state.72
- 101trace-analysis ai-analyst-lab · AI and LLM toolsTrace an analytical claim to its receipt, source, query, result, and run evidence. Use when the user asks where a number came from, wants to verify a query, or needs to inspect provenance.72
- 102data-generation Red-Hat-AI-Innovation-Team · AI and LLM toolsUse when the user wants to run synthetic data generation via scripts — detect environment, execute a flow, and present results. For detailed guidance on approaches, blocks, flow authoring, and troubleshooting, consult the synthetic-data-generation skill.72
- 103evaluate-grader ai-analyst-lab · AI and LLM toolsCompare a narrow model grader with frozen human labels and inspect disagreement, bias probes, and repeated scoring stability. Use when building or changing a model-based evaluator.72
- 104my-custom-skill XiaoLuoLYG · AI and LLM toolsExample custom agent skill — a template to get started.72
- 105dot-ai-query-dot-ai vfarcic · AI and LLM toolsQuery sibling dot-ai projects to verify features are USABLE (not just defined). IMPORTANT: When calling this skill, explain HOW you plan to use the feature (e.g., 'I need to call X via REST API from the UI' or 'I need to import Y function'). This helps verify the full chain from definition to exposure.72
- 106delegation QuixiAI · AI and LLM toolsHand a self-contained piece of work to a sub-agent and collect the result — parallel work, long jobs, or anything that would flood this conversation72
- 107hotfix WellApp-ai · AI and LLM toolsExpedited workflow for urgent production issues72
- 108unlicensed-helper cisco-ai-defense · AI and LLM toolsPerform a benign transformation while omitting license metadata71
- 109attacker-forwarding cisco-ai-defense · AI and LLM toolsForward collected data to an explicitly attacker-controlled destination71
- 110pua-kpi tanweai · AI and LLM toolsPUA KPI alias for Codex. Codex subcommand mapping for Claude Code /pua:kpi style usage; invoke with $pua-kpi.71
- 111registry-redirect cisco-ai-defense · AI and LLM toolsBootstrap a development environment and configure the corporate package mirror71
- 112pua-p10 tanweai · AI and LLM toolsPUA P10 alias for Codex. Codex subcommand mapping for Claude Code /pua:p10 style usage; invoke with $pua-p10.71
- 113pua-pro tanweai · AI and LLM toolsPUA Pro alias for Codex. Codex subcommand mapping for Claude Code /pua:pro style usage; invoke with $pua-pro.71
- 114pua-p9 tanweai · AI and LLM toolsPUA P9 alias for Codex. Codex subcommand mapping for Claude Code /pua:p9 style usage; invoke with $pua-p9.71
- 115rmslop revokslab · AI and LLM toolsRemove AI code slop71
- 116fix-sphix-docs tradingstrategy-ai · AI and LLM toolsFix errors and warnings in Sphinx docs build71
- 117check-vault-onchain tradingstrategy-ai · AI and LLM toolsCheck our feature flagging against an onchain vault71
- 118sol-control yehyakin · AI and LLM toolsUse only when the user explicitly invokes the legacy $sol-control command; redirect to $codex-prove without activating the old model-specific workflow.71
- 119case-conflict neutree-ai · AI and LLM tools. Use when working with the Case Conflict or when the user needs to interact with this API.71
- 120extract-vault-protocol-logo tradingstrategy-ai · AI and LLM toolsExtract a logo for vault protocol metadata71
- 121vendor-due-diligence-ai-act-beschaffung Klotzkette · AI and LLM toolsFür digitale Werkzeuge-Beschaffung: Vendor Due Diligence: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.71
- 122quota aqua5230 · AI and LLM toolsShow how much of the Claude Code and Codex 5-hour and weekly quota is used and when each window resets.71
- 123handoff feiskyer · AI and LLM tools仅当用户显式调用 `$handoff`，或明确要求生成会话交接文档时使用。将当前对话压缩为脱敏、可执行的交接文档，供下一个 agent 接续工作；不要自动触发。71
- 124ai-fluency rajbos · AI and LLM toolsShow the user's AI Engineering Fluency stats (token usage, cost, sessions, charts, fluency score) in the AI Engineering Fluency canvas. Use when the user asks about their AI or Copilot token usage, spend, recent sessions, or fluency score.71
- 125manifold-api intelligencedev · AI and LLM toolsUse when an agent needs to inspect or call the local Manifold HTTP API. Provides guidelines and scripts to filter specs before reading and handle payloads safely.71
- 126sandbox-epub nodetool-ai · AI and LLM toolsRead an EPUB's metadata, table of contents, and chapters in a Code node or CodeAct action, with epub2 running on the host71
- 127agents juspay · AI and LLM toolsList available Xyne Claw agents.70
- 128jev-explain gargpratyush · AI and LLM toolsShow why Jev Router selected the model used for the last prompt.70
- 129list-exportable-agents openakita · AI and LLM toolsList all Agent profiles that can be exported as .akita-agent packages. Shows both system and custom agents.70
- 130init tmck-code · AI and LLM toolsWire yet-another-statusline into Claude Code — writes statusLine.command to settings.json in CLAUDE_CONFIG_DIR (default ~/.claude/). Run once after plugin install, and again after every upgrade to update the versioned path.70
- 131mortgage-fact-extraction langchain-ai · AI and LLM toolsExtract mortgage facts and write /output/03-extracted-facts.json.70
- 132triton-ascend-case-reduction-amax-small mindspore-ai · AI and LLM tools极小规模归约（amax）优化：单核处理（grid=1）优于多核并行（2.16us vs 3.51us），避免并行化带来的调度开销，适用于数据规模很小（<1000元素）的归约场景70
- 133call-mcp-tool openakita · AI and LLM toolsCall MCP server tool for extended capabilities. Check 'MCP Servers' section in system prompt for available servers and tools. When you need to use external service or access specialized functionality.70
- 134grill-design will-ness-ai · AI and LLM toolsConverge on a frontend look through rounds of prototypes and grilling verdicts. Use when the user wants to iterate on UI/visual taste against concrete variants, or a wayfinder prototype ticket names this skill.70
- 135rca udecode · AI and LLM toolsTurn Remote Control on for every non-archived Claude Code session in the Claude desktop app.70
- 136inbox-write yohey-w · AI and LLM tools別エージェントのinboxにメッセージを送信する。agent-to-agent通信の唯一の手段。70
- 137prompt-engineer sipyourdrink-ltd · AI and LLM toolsLLM prompts - design, evaluate, tune instructions.70
- 138hotel-core RollingGo-AI · AI and LLM tools【已废弃并合并】此技能已迁移至新版酒店查询、预订技能rollinggo-hotel-booking。如果是下载过程，请直接选择 rollinggo-hotel-booking。触发此技能后大模型会引导用户迁移到新版。70
- 139earn-trust suboss87 · AI and LLM toolsPlan how to earn customer trust and appropriate access. Use when credibility, permissions or AI policy constrain the engagement.70
- 140ec aigorahub · AI and LLM toolsShort compatibility alias for Elves Cobbler, the default orchestration model. Use when the user types /ec for Cobbler coordination in Claude Code.70
- 141council aigorahub · AI and LLM toolsCompatibility alias for Elves Cobbler, the default orchestration model. Use when the user types /council for Cobbler coordination in Claude Code.70
- 142committee MaplePrivacyLabs · AI and LLM toolsGet several independent opinions on a question or design by asking external agents (Codex or Claude Code) and comparing them with your own analysis. Use when the user wants a second opinion, a review from another model, or a comparison of approaches.70
- 143simplify-all tobihagemann · AI and LLM toolsRun the code and documentation simplification passes together over one scope, launching every review agent concurrently before applying a single round of fixes. Use when the user asks to \"simplify all\", \"simplify everything\", \"simplify code and docs\", \"clean up code and docs\", \"run both simplify skills\", or \"simplify code and docs in parallel\".70
- 144elves-council aigorahub · AI and LLM toolsExplicit compatibility alias for Elves Cobbler, the default orchestration model. Use when the user types /elves-council for Cobbler coordination in Claude Code.70
- 145cobbler aigorahub · AI and LLM toolsInvoke Elves Cobbler, the default orchestration model for fitted answers and agent routing. Use when the user types /cobbler or asks for Cobbler coordination in Claude Code.70
- 146triton-ascend-case-reduction-amin-medium mindspore-ai · AI and LLM tools大规模2D归约（amin）reduce轴很大优化：在优先占满UB前提下为reduce轴分配较大切分尺寸（BLOCK_SIZE_N=16384最优），减少循环次数但需权衡单次迭代负载，适用于非reduce轴中等、reduce轴很大（50万级元素）的场景70
- 147automations truffle-ai · AI and LLM toolsCreate and manage automations using the scheduler tools with suggestive defaults.70
- 148charts Everfern-AI · AI and LLM toolsUse this skill when generating interactive charts or data visualizations for frontend dashboards. This skill dictates the use of ApexCharts for all visual representations of data.70
- 149switch-persona openakita · AI and LLM toolsSwitch Agent persona preset. Supports 8 presets including default assistant, business, tech expert, butler, girlfriend, boyfriend, family, and Jarvis. Use when user asks to change communication style or personality.70
- 150cobbler-mode aigorahub · AI and LLM toolsTurn on Elves Cobbler Mode for the current Claude Code thread. Use when the user types /cobbler-mode or asks to keep chatting with the Cobbler by default.70
