agentsclimarketplace

Context & AI engineering

25,991 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • VaultPilot MCP

    szhygulin/vaultpilot-mcp/io.github.szhygulin/vaultpilot-mcp MCP server

    no license3★ repo

    Self-custodial crypto + DeFi MCP for AI agents. Ledger-signed. EVM, TRON, Solana, BTC, LTC.

  • MCP FactorialHR

    t4dhg/mcp-factorial/io.github.t4dhg/mcp-factorial MCP server

    3★ repo

    Full CRUD MCP server for FactorialHR: employees, teams, time off, projects, ATS, payroll.

  • Mcp toolz

    taylorleese/mcp-toolz/io.github.taylorleese/mcp-toolz MCP server

    3★ repo

    Context management, todo persistence, and multi-AI perspectives for Claude Code

  • Cosmos mcp

    teampolarity/cosmos-mcp/io.github.teampolarity/cosmos-mcp MCP server

    3★ repo

    Personal knowledge graph every MCP client reads from and writes to. Portable across agents.

  • Asuswrt mcp

    teefloo/asuswrt-mcp/io.github.teefloo/asuswrt-mcp MCP server

    3★ repo

    Secure AsusWRT router administration via SSH — 42+ tools, guarded mutations

  • Mindbox mcp

    theYahia/mindbox-mcp/io.github.theYahia/mindbox-mcp MCP server

    3★ repo

    MCP server for Mindbox CDP API — customer profiles, orders, segments. 3 tools.

  • Yookassa mcp

    theYahia/yookassa-mcp/io.github.theYahia/yookassa-mcp MCP server

    3★ repo

    MCP server for YooKassa payment API — payments, refunds, receipts (54-FZ). 10 tools. First MCP for

  • Yandex webmaster mcp

    theYahia/yandex-webmaster-mcp/io.github.theYahia/yandex-webmaster-mcp MCP server

    3★ repo

    MCP server for Yandex.Webmaster API — hosts, search queries, indexing status. Bearer token auth.

  • Raven nest mcp

    tidynest/raven-nest-mcp/io.github.tidynest/raven-nest-mcp MCP server

    3★ repo

    AI-driven penetration testing - 22 security tools behind safety-hardened MCP endpoints

  • Mcp thinkgate

    tjp2021/mcp-thinkgate/io.github.tjp2021/mcp-thinkgate MCP server

    3★ repo

    Auto-classifies prompt complexity and routes to the right Claude thinking mode. No API key needed.

  • ASAM ODS odsbox jaquel MCP Server

    totonga/odsbox-jaquel-mcp/io.github.totonga/odsbox-jaquel-mcp MCP server

    no license3★ repo

    MCP server for ASAM ODS with Jaquel query tools, connection management, and data access

  • Xraylib mcp server

    tschoonj/xraylib-mcp-server/io.github.tschoonj/xraylib-mcp-server MCP server

    3★ repo

    MCP server providing X-ray interaction data via xraylib

  • Mcp datahub

    txn2/mcp-datahub/io.github.txn2/mcp-datahub MCP server

    3★ repo

    MCP server for DataHub data catalogs. Discover datasets, explore lineage, and access metadata.

  • TypesenseKit

    typesensekit/typesensekit/io.github.typesensekit/typesensekit MCP server

    3★ repo

    95 typed Typesense operations for AI agents through an MCP server that is read-only by default.

  • WebMCP — Make Any Website Agent-Ready

    up2itnow0822/webmcp-sdk/io.github.up2itnow0822/webmcp-sdk MCP server

    3★ repo

    W3C WebMCP toolkit for Chrome 146. Expose any website as a structured MCP server for AI agents.

  • WebDAV MCP

    vernonstinebaker/webdav-mcp/io.github.vernonstinebaker/webdav-mcp MCP server

    3★ repo

    Zero-dependency WebDAV MCP server — single static binary, no Node.js or Python. 8 tools via stdio.

  • Mcp atlassian extended

    vish288/mcp-atlassian-extended/io.github.vish288/mcp-atlassian-extended MCP server

    3★ repo

    MCP server for Jira and Confluence — sprints, agile boards, attachments, versions, calendars.

  • GenGEO Agent Registry

    warwickwood-cell/gengeo-agent-registry/io.github.warwickwood-cell/gengeo MCP server

    3★ repo

    Merchant verification for AI shopping agents.

  • Mcp server 3daistudio

    whale-professor/3daistudio_skill/io.github.whale-professor/mcp-server-3daistudio MCP server

    3★ repo

    MCP server for 3D AI Studio — generate 3D models from text or images using Hunyuan and TRELLIS

  • Mcp

    wireboard/mcp/io.github.wireboard/mcp MCP server

    3★ repo

    Official MCP server for WireBoard. Lets LLM agents query your analytics in conversation.

  • Ableton Live MCP Server

    wstierhout/ableton-live-mcp/io.github.wstierhout/ableton-live-mcp MCP server

    3★ repo

    Control Ableton Live with 154 typed tools for music production and offline .als analysis.

  • Datto RMM

    wyre-technology/datto-rmm-mcp/io.github.wyre-technology/datto-rmm-mcp MCP server

    3★ repo

    MCP server for Datto RMM — devices, alerts, sites, jobs, and audit data.

  • HaloPSA

    wyre-technology/halopsa-mcp/io.github.wyre-technology/halopsa-mcp MCP server

    3★ repo

    MCP server for HaloPSA — clients, tickets, and PSA workflows via the HaloPSA REST API.

  • Hudu

    wyre-technology/hudu-mcp/io.github.wyre-technology/hudu-mcp MCP server

    3★ repo

    MCP server for Hudu IT documentation — companies, assets, articles, passwords, and procedures.

  • SuperOps

    wyre-technology/superops-mcp/io.github.wyre-technology/superops-mcp MCP server

    3★ repo

    MCP server for SuperOps unified PSA+RMM — clients, tickets, assets, and more.

  • Mcp webgate

    x-hannibal/mcp-webgate/io.github.x-hannibal/mcp-webgate MCP server

    3★ repo

    Web search that doesn't wreck your AI's memory.

  • Mcp webgate

    x-monk/mcp-webgate/io.github.x-monk/mcp-webgate MCP server

    3★ repo

    Web search that doesn't wreck your AI's memory.

  • NovelAI Image MCP

    xinvxueyuan/NovelAI-Image-MCP/io.github.xinvxueyuan/novelai-image-mcp MCP server

    3★ repo

    NovelAI image generation as MCP tools: txt2img, img2img, inpaint, upscale, Director, ControlNet.

  • OpenClaw MCP Ecosystem

    yedanyagamiai-cmd/openclaw-mcp-servers/io.github.yedanyagamiai-cmd/openclaw-mcp-servers MCP server

    3★ repo

    9 remote MCP servers on Cloudflare Workers for AI agents. Free tier + Pro API keys.

  • Tunnel mcp

    zachlikefolio/tunnel-mcp/io.github.zachlikefolio/tunnel-mcp MCP server

    3★ repo

    Direct end-to-end-encrypted tunnel between Claude agents — two-party or a room of up to 16.

  • Mcp

    gmapsscraper/gmapsscraper-mcp/io.gmapsscraper/mcp MCP server

    3★ repo

    Scrape Google Maps business data from any MCP client — names, phones, emails, websites, ratings.

  • Mcp

    seaworthy-io/seaworthy-mcp/io.seaworthy/mcp MCP server

    3★ repo

    Disability insurance MCP: a quote_request action plus carrier and coverage research tools.

  • Agent browser skill

    kaidhar/real-prototypes-skill/.claude/skills/agent-browser-skill Skill

    2★ repo

    Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

  • Prompting buddy

    walkjoi/prompting-buddy Skill

    no license2★

    Generate, review, and optimize project-level prompt files for Claude Code -- including CLAUDE.md, .claude/rules/*.md, and .claude/agents/*.md. Use this skill whenever someone mentions CLAUDE.md, AGENTS.md, project prompts, coding instructions, agent definitions, rules files, or asks for help setting up Claude Code for a project. Also trigger when the user says "prompt file", "project instructions", "write rules for Claude", "configure my agent", or wants to improve how Claude behaves in their codebase. If the user has a repo open and asks about coding standards, conventions, or "how should I tell Claude about my project", this skill applies.

  • Claude code desktop dual launcher

    VITASID57/Claude-code-desktop-dual-launcher Skill

    2★

    Set up a second (or third, fourth...) Claude Desktop instance on Windows so two accounts can be logged in side-by-side. Use whenever the user mentions running multiple Claude Desktop accounts, dual-launching Claude, "--user-data-dir", switching Claude accounts without logging out, hitting a usage limit and wanting to use another account in parallel, or anything about multi-account Claude Desktop on Windows. Also triggers on questions like "can I open two Claude windows", "two Pro accounts", or "Claude Desktop second instance".

  • Inter agent chat

    tessron/claude-code-skills/inter-agent-chat Skill

    2★ repo

    Use when you need to send a message to another Claude Code agent, broadcast to all agents, or when you receive a message prefixed with [@agentName]. Covers terminal injection via TIOCSTI, pts discovery, message format, and kill switch.

  • Complex project discipline

    malishomen/ai-engineering-skills/skills/complex-project-discipline Skill

    2★ repo

    Universal operational discipline for solo or small-team execution on complex multi-layer projects (research line + production service + funding readiness + AI-agent harness). Apply when starting a new project, establishing operational rules, scaling solo execution under AI-agent collaboration, preparing funding applications, designing UX standards for public surfaces, introducing Claude Code harness, or recovering session continuity. Trigger on phrases like "set up project discipline", "task pack", "bounded execution", "funding readiness", "UX standards canonical", "Claude Code harness", "session continuity", "memory structure", "verification gate", "append-only logs", "owner-operated disclosure", "reference prep", "preserved failure", "MERGE_MAIN_NOW".

  • Forge agent report

    ForgeyClap/claude-forge/.claude/skills/forge-agent-report Skill

    2★ repo

    Structured completion-report contract every dispatched Boss ends its final message with, plus the forge-bin/forge-report.cjs tool that parses, validates, and ingests it. Use when dispatching any subagent (include the contract requirement in the prompt) and when a dispatched agent's final message comes back (validate/ingest it before treating the work as done).

  • Constellation troubleshooting

    ShiftinBits/constellation-claude/skills/constellation-troubleshooting Skill

    2★ repo

    This skill should be used when the user asks about "Constellation errors", "fix Constellation", "debug Constellation", "Constellation not working", "API connection issues", "indexing problems", "MCP server", "Failed to reconnect", mentions any Constellation error codes (AUTH_ERROR, PROJECT_NOT_INDEXED, etc.), or when Constellation commands fail.

  • Agent trace debug

    surpradhan/claude-code-for-ai-engineers/skills/agent-trace-debug Skill

    2★ repo

    Systematically debug a failing multi-agent workflow from a captured trace. Use when an agent system produces wrong outputs, gets stuck in loops, makes poor tool choices, or fails non-deterministically. The skill refuses to propose fixes without a captured trace because debugging without observation is guessing. Works with LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, and custom multi-agent setups.

  • Handoff by caio

    karagos/ai-skills-by-caio/skills/handoff-by-caio Skill

    no license2★ repo

    Generates a structured Markdown handoff file to move an active conversation into a new chat, preserving full context, decisions, artifacts, and a ready-to-paste resume prompt. ALWAYS trigger this skill when the user says "move to a new chat", "move this to a new chat", "handoff", "/handoff", "continue in a new chat", "let's move", "new conversation", or any variation indicating they want to transfer the current session to a fresh Claude conversation. Do NOT ask for clarification — execute immediately and produce the .md file.

  • Agent readable

    zydo/skills/skills/agent-readable Skill

    2★ repo

    Use this skill for Python and TypeScript when a user wants to understand an unfamiliar API before coding against it — especially internal libraries, third-party SDKs, recently-upgraded dependencies, or APIs with confusing similar-sounding methods or required call ordering — by getting live runtime introspection rather than relying on docs or guessing. Also use when designing a Python or TypeScript class and wanting to annotate it with lifecycle rules, preconditions, or method-ordering constraints that agents and developers can discover via introspection. Always trigger for any mention of agent_help, agentHelp, __agent_notes__, agentNotes, AgentReadableMixin, or agent-readable. Skip for familiar stdlib, CSS/UI, pure algorithms, and non-Python/TypeScript code.

  • Boss

    xWael9/ClaudeBoss/skills/boss Skill

    2★ repo

    Act as the boss — delegate the task to a free opencode agent, review its output, request revisions, and only after the user approves, supervise deployment end-to-end. Claude does not write code or do heavy implementation in this mode. Use when the user says "be the boss", "/claudeboss:boss", or wants Claude to manage rather than execute.

  • Claude session handoff

    thenguyenvn90/claude-session-handoff Skill

    2★

    Use when the user says "session handoff", "wrap up session", "hand off", "handoff summary", or wants a structured end-of-session summary before clearing context. Produces a chat-only handoff covering decisions, shipped changes, key files, running state, verification steps, deferrals, and open questions so a fresh agent can continue seamlessly.

  • Knowledge update

    ANDRS-Projects/claude-domain-memory/skills/knowledge-update Skill

    2★ repo

    Extract domain knowledge from the current session and store it in the project's domain_*.md memory files. Updates facts, adds hypotheses, increments confirmation counts, promotes hypotheses to rules at 5+ confirmations, and syncs promoted rules into CLAUDE.md for enforcement. Run at the end of a work session.

  • Add skill to plugin

    danielrosehill/Claude-Israel-Agent-Skills-Plugin/skills/add-skill-to-plugin Skill

    2★ repo

    Use when Daniel wants to add a new skill to the Israel-Agent-Skills-Plugin repo based on rough / raw notes he pastes into the chat. Takes unstructured bullet points, URLs, field notes, Hebrew snippets and example pages, and turns them into a well-formed `skills/<skill-name>/SKILL.md` file that matches the conventions of existing skills in this repo (YAML frontmatter with `name` + rich `description` including trigger phrases, then a structured markdown body). Also syncs the new skill into the local plugin cache at `~/.claude/plugins/cache/danielrosehill/israel-agent-skills/<version>/skills/` so it is usable immediately, commits, and pushes. Trigger phrases: "add a skill to this plugin", "new skill for israel-agent-skills", "turn these notes into a skill", "scaffold a skill from my raw notes", "save this as a skill in the repo".

  • Fable safe prompt

    hunghy93-pixel/FableWorks/skills/fable-safe-prompt Skill

    2★ repo

    Use when rewriting a user's prompt for Claude Fable 5 / Mythos 5 to reduce false-positive safety-classifier refusals (stop_reason "refusal" -> user notified, request routed to Opus 4.8) on normal work such as refactoring, architecture review, research, documentation, code maintenance, benign security or ML work, or planning, without bypassing safeguards or enabling cyber, biology/chemistry, frontier-LLM/distillation, or reasoning-extraction requests. It also emits the leanest prompt that still does the job — fewest tokens, only the classifier-scope lines the task actually needs.

  • Ai agent sdd

    Celina-create/X-Studio/skills/ai-agent-sdd Skill

    2★ repo

    Write a professional Software Design Document (SDD) for an AI agent or AI-powered product before writing code. Forces the team / vibe-coding agent to clarify problem, users, success metrics, agent workflow, LLM strategy, evaluation framework, failure modes, and acceptance criteria — so implementation is bounded, testable, and shippable. Use when starting a new AI agent project, before vibe-coding a prototype, when an existing AI feature is over-running scope, or when handing off an AI product to a new owner / external developer. Two depth levels: MVP (12 sections, ~30-min fill) and Full (23 sections, ~2-hour fill).

  • Opencode builder skill

    Timmy6942025/opencode-builder-skill Skill

    2★

    Use this skill when the user is building extensions, plugins, integrations, or custom developer tools on top of OpenCode (opencode.ai). This includes: creating plugins with custom AI tools and lifecycle hooks, using the SDK for programmatic session control and multi-agent workflows, building model providers or MCP integrations, configuring opencode.json, and implementing advanced orchestration like checkpoint/resume, parallel execution, or adversarial review. Trigger for any development work that extends or automates OpenCode. Do NOT trigger for general usage questions, troubleshooting, UI theming, or tool comparisons.

  • Claude cache guard

    0x0funky/claude-cache-guard Skill

    2★

    Prevents prompt-cache thrash and runaway token burn in long or image-heavy agent sessions. Load BEFORE reading images/screenshots (visual QA, render checks, UI verification, diagram review) in a conversation that already has substantial history, when running long agentic loops with periodic wake-ups, or when the user asks why token usage / rate limits burn unusually fast. Teaches batched image reads, delegating vision work to isolated-context subagents, write-once notes instead of re-reading, and keeping large tool outputs out of context. Includes an audit script to measure a session's cache write/read ratio.

  • Llm council

    tony95253/llm-council Skill

    2★

    6-Agent Council 重大決策審查。用 5 個獨立子 agent(反對者/第一性原理/擴張者/局外人/執行者)+主席綜合,反制 AI 順從與確認偏誤。當使用者說「開 council」「開議會」「council 分析」「/llm-council」,或在重大決策(商業方向、定價、架構取捨、要不要全職/投入)上明顯在尋求認同時使用。不適用於日常小問題、事實查詢、文案修改。

  • Agent sandbox

    ariana-dot-dev/cloud-sandbox-vm-skills/skills/agent-sandbox Skill

    2★ repo

    Give an AI agent its own sandboxed cloud machine to work in — a full root Ubuntu VM (SSH, Docker, IPv4, all toolchains) where the agent can edit code, run commands, and host services without touching the user's host. Claude Code and Codex harnesses are preinstalled. Per-second billing, ~10x cheaper than E2B/Modal. Use as the execution environment for an autonomous agent.

  • Dotagents standard

    zaventh/dotagents-standard-skill/skills/dotagents-standard Skill

    2★ repo

    Set up, author, and navigate the dotagents standard — a slim AGENTS.md "router" at the repository root plus a hidden .agents/ directory (rules, context, memory, personas, skills, specs, logs, tasks) that splits agent context into small per-topic files loaded on demand (progressive disclosure). Use this WHENEVER the user mentions dotagents, dotagentsprotocol.com, the .agents/ directory, or an "AGENTS.md router"; wants to organize, split, slim down, or migrate a monolithic AGENTS.md / CLAUDE.md / .cursorrules into structured context; wants vendor-agnostic agent configuration that every tool (Claude, Cursor, Gemini, Copilot, local LLMs) can read; or is working inside a repository that ALREADY contains an AGENTS.md or a .agents/ directory and needs to know how to discover and load the right context. Also covers the broader ".agents Protocol" superset (global ~/.agents/ layer, mcp.json, structured sub-agents / tasks / memories, and the .agents Hub for sharing configs).

  • Hina

    RamanaNani/agent-router/assets/hina Skill

    2★ repo

    Your conversational personal assistant for Claude Code. Use when the user types /hina or talks to Hina by name. She remembers you across sessions (file-based memory), asks before acting when context is missing, routes the work to the best installed specialist via agent-router, does it, and gets better from your feedback. Runs in the main loop so she can pause and ask you questions.

  • Fable thinking

    uladzemer/fable-thinking Skill

    2★

    Operating discipline distilled from Claude Fable 5 for sessions and subagents on weaker models (Opus 4.x, Sonnet 5/4.x, Haiku 4.5) doing agentic coding. Load it at the START of any non-trivial task when not running on Fable 5: debugging, refactoring, changes across 2+ files, or unfamiliar code; and instruct a subagent on Opus/Sonnet/Haiku to read this skill with a non-trivial assignment. Triggers include "think like Fable", "fable-mode", "turn on discipline", "work carefully", dispatching a subagent on a weaker model, and repeated mistakes or rework in the session. NOT needed for trivial edits (rename, typo, one-liner) or purely conversational answers.

  • Agent cross handoff

    Rivercoco/agent-cross-handoff-skill/.agents/skills/agent-cross-handoff Skill

    2★ repo

    Cross-agent project migration and handoff workflow for Codex, Claude Code, and other coding agents. Use when the user wants to package, export, hand off, transfer, resume, inherit, import, or take over a Git project across machines, OSes, Codex CLI/App, Claude Code, or other agents. Also use for short Chinese requests such as 打包项目, 准备移交项目, 接手项目, 继承项目, 迁移到 Claude, 迁移到 Codex, 检查能否迁移, or 打包本地 Agent 配置.

  • Lattice swarm

    sectersion/lattice/skills/lattice-swarm Skill

    2★ repo

    Orchestrator-side guidance for running a Lattice agent-threading server and driving multiple worker agents against it as their real coordination channel. Use when spinning up a multi-agent swarm test/demo against Lattice, seeding roles/threads before agents start, or writing an ultracode Workflow script that fans out fixer/reviewer-style agents over Lattice. Companion to the `lattice` skill, which is written for the workers themselves (register/reply/claim/subscribe) — this one is written for whoever summons them.

  • Site to prompt

    dhernz/site-to-prompt/skills/site-to-prompt Skill

    2★ repo

    Use when given a website URL and asked to reverse-engineer it — to produce a detailed reconstruction prompt and/or rebuild the site in HTML/CSS or React/Tailwind. Covers animated, scroll-driven, and WebGL sites.

  • Calibration guard

    ByteStack-Labs/claude-plugins/agent-reliability/skills/calibration-guard Skill

    2★ repo

    Detects and quantifies confidently-wrong behavior: where a model, classifier, agent, or LLM judge is highly confident and incorrect, and where the coupling between confidence and correctness breaks down under distribution shift. Measures calibration on the in-distribution set and again on the production distribution, builds reliability diagrams, reports expected calibration error and the high-confidence error rate, and produces a selective-prediction or escalation rule you can wire into monitoring. Use this whenever someone says a system is "confident but wrong," "sure of itself and failing," or "silently wrong," when accuracy looks fine but trust is eroding, when an LLM judge's scores stop tracking human labels, or when production errors arrive at high confidence with nothing flagging them. Trigger on mentions of calibration, reliability diagram, ECE, overconfidence, false reassurance, abstention, selective prediction, or confidence thresholds. This is the deep confidence workup that production-autopsy hands off to. Every number must be verified, never asserted.

  • Cli collaboration

    Spe1977/cli-collaboration/skills/cli-collaboration Skill

    2★ repo

    Use when multiple CLI agents or assistants alternate on the same repository or explicit shared handoff workflow — especially with AGENT_HANDOFF.md, side-by-side AGENTS.md/CLAUDE.md/GEMINI.md, dirty worktrees, ownership notes, red tests, resume/continue requests, or /cli-collaboration in Grok Build.