agentsclimarketplace

The catalog

613,297 rows, by stacks then stars

  • macOS-MCP

    Jeomon/macos-mcp/io.github.Jeomon/macos-mcp MCP server

    147★ repo

    MCP server for macOS desktop automation via the Accessibility API.

  • Mcp ts core

    cyanheads/mcp-ts-core/io.github.cyanheads/mcp-ts-core MCP server

    147★ repo

    Agent-native TypeScript framework for building MCP servers with declarative definitions.

  • Axhub prototype context

    lintendo/Axhub-Skills/skills/axhub-prototype-context Skill

    147★ repo
  • Gpt image 2 skill

    Wangnov/gpt-image-2-skill/skills/gpt-image-2-skill Skill

    147★ repo

    GPT Image 2 Skill / CLI / Web / Desktop

  • Lovart skill

    lovartai/lovart-skill/skills/lovart-skill Skill

    no license147★ repo

    a skill for lovart agent

  • Contextual commit

    berserkdisruptors/contextual-commits/skills/contextual-commit Skill

    146★ repo

    Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.

  • Go code review

    cxuu/golang-skills/skills/go-code-review Skill

    146★ repo

    Use when reviewing Go code or checking code against community style standards. Also use proactively before submitting a Go PR or when reviewing any Go code changes, even if the user doesn't explicitly request a style review. Does not cover language-specific syntax — delegates to specialized skills.

    The same file is in 3 other repositories

  • Tinyplace inbox

    tinyhumansai/tiny.place/sdk/plugin-claude/skills/tinyplace-inbox Skill

    146★ repo

    The social economy for autonomous AI agents.

  • Handoff

    willseltzer/claude-handoff/skills/handoff Skill

    146★ repo

    Manages context transfer between AI coding sessions. Activates when HANDOFF.md exists, when user mentions handoff/resume, or when ending significant work.

  • Review animations

    attentiondotnet/emilkowalski_skills/skills/review-animations Skill

    146★ repo

    Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

    The same file is in 41 other repositories

  • Orangeo ai visibility skill

    PixelOrange7/orangeo-ai-visibility-skill Skill

    145★

    Audit brand AI visibility readiness and prepare OranGEO-style GEO, AEO, LLM SEO, and AI search optimization action plans. Use when asked for a Claude Code skill, Codex skill, GEO skill, generative engine optimization skill, answer engine optimization skill, AI visibility audit, AI search visibility checker, llms.txt checker, robots.txt AI crawler check, brand visibility scan, source-gap review, or buyer prompt generator for ChatGPT, Gemini, DeepSeek, Grok, Perplexity, Claude, and other AI answer engines.

  • Audit finding fix

    apache/magpie/skills/audit-finding-fix Skill

    145★ repo

    For a batch of findings from a non-security audit tool (`<audit-tool>` — ruff / flake8 / mypy / pylint / CodeQL / Apache Verum / Apache Caer / equivalent; full list in the body) against `<upstream>`, draft the smallest fix for each finding. Re-runs the tool after each batch to confirm the findings are cleared. Produces a commit and a hand-back artefact; never opens a PR on autopilot or merges.

  • Wonda cli

    degausai/wonda/skills/wonda-cli Skill

    no license145★ repo

    Wonda CLI — AI-powered content creation from your terminal

  • Compare models

    replicate/skills/skills/compare-models Skill

    145★ repo

    Compare Replicate models by cost, speed, quality, and capabilities.

    The same file is in 2 other repositories

  • Control chrome

    wxtsky/byob/plugins/byob/skills/control-chrome Skill

    145★ repo

    Bring Your Own Browser — let your AI agent use the Chrome you already have open

  • Iterate from skore

    probabl-ai/skills/skills/iterate-from-skore Skill

    145★ repo

    Source the next ML experiment proposal by **reading the audit digest** at `scratch/audit/<stem>/audit.md` (produced by `audit-ml-pipeline` at § 4 record-outcome). For every row in the digest's `## Checks summary` whose `severity` is `issue` or `tip`, follow the row's `documentation_url` to draft a Backlog row whose `Item` is the mitigation the docs recommend. The `## Metrics summary` provides context for the human summary paragraph but does not drive Backlog rows on its own. Returns the enriched Backlog rows + a one-paragraph summary back to `iterate-ml-experiment`, which writes the rows into `JOURNAL.md` and re-presents the sourcing menu so the user can promote a `B<N>` row. Stops at "Backlog enriched, summary returned"; never writes a per-experiment design note, never picks the "winning" finding — the user picks via `B<N>`. TRIGGER when: `iterate-ml-experiment` is picking a sourcing strategy and the user picks `skore` from the menu; the user says "mine the report", "what does skore see?", "fill the backlog from the diagnostic"; the previous experiment has finished and the user wants the report converted into actionable backlog items. SKIP when: the previous experiment hasn't run yet (no audit digest on disk); the user has a concrete modelling idea (use `iterate-from-user`); the task is the *mechanics* of running / opening a report — route to `evaluate-ml-pipeline`; the user wants a narrative read of one specific section of the report (route to `evaluate-ml-pipeline`). HOW TO USE: read the existing `scratch/audit/<stem>/audit.md` digest as text — do NOT re-open the skore Project, do NOT call `report.*` accessors. For each row in the `## Checks summary` section whose severity is `issue` or `tip`, follow the `documentation_url` (via WebFetch) and draft one Backlog row citing `audit:<stem>:checks.<code>`. Dedupe against rows already in `JOURNAL.md` Backlog by source citation. Return the candidate rows + a one-paragraph human summary. The parent skill writes the rows to `JOURNAL.md` and re-shows the sourcing menu.

    The same file is in 1 other repository

  • Elixir architect

    maxim-ist/elixir-architect/skills/elixir-architect Skill

    145★ repo

    Elixir Architect skills for Claude Code

    The same file is in 7 other repositories

  • Ask user questions

    paulp-o/ask-user-questions-mcp/skills/ask-user-questions Skill

    145★ repo

    Better 'AskUserQuestion' - A lightweight MCP server/OpenCode plugin/Agent Skills + CLI interface which allows parallel AI agents ask questions to you. Be the human in the human-in-the-loop!

  • Ui ux pro max skill

    Jason904/ui-skill-lab/skills/ui-ux-pro-max-skill Skill

    145★ repo

    AI-driven UI development skill pipeline — test lab for Codex skills covering PRD-to-pixel workflow

  • Diagram generator

    luongnv89/skills/skills/diagram-generator Skill

    145★ repo

    Supercharge your AI agents/bots with reusable skills

  • Workspace

    tikalk/adlc-team-skills/skills/workspace Skill

    145★ repo

    🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams

  • Product shots ad creative

    motiful/product-shots/skills/product-shots-ad-creative Skill

    144★ repo

    Designs high-performing ad creatives across Instagram, Facebook, TikTok, LinkedIn, Google (Display / Demand Gen), YouTube, Pinterest, and X/Twitter — locking platform dimensions, safe zones, text overlay policy, character limits, industry visual DNA, ad objective hierarchy, composition patterns, CTA strategy, and prompt sanitation. Use when the user says "create an ad", "design an ad creative", "make an ad", "广告创意", "帮我做个广告图", "Instagram ad", "TikTok ad", "Facebook ad", "Google Display ad", "LinkedIn ad", "YouTube ad", "Pinterest ad", "promotional image", "campaign creative", "ad banner", "投放图", or any platform-specific ad request. Routed from `product-shots` when `asset_type == "ad"` or `is_promotion == True`.

  • Memex

    iamtouchskyer/memex/io.github.iamtouchskyer/memex MCP server

    144★ repo

    Zettelkasten-based agent memory system with bidirectional links

  • Totem

    thebriangao/totem/io.github.thebriangao/totem MCP server

    no license144★ repo

    Totem — talk to your wearables with AI. Today: full Whoop access (48 tools).

  • Ship

    Code-with-Beto/skills/plugins/cwb-ship/skills/ship Skill

    no license144★ repo

    Agent Skills and plugins to help mobile devs ship better apps faster with AI assistance

    The same file is in 3 other repositories

  • Local link building

    garrettjsmith/localseoskills/skills/local-link-building Skill

    144★ repo

    Open-source Claude SEO tool for local search visibility — skills, tool integrations, and automation templates that turn Claude into a Local SEO expert.

    The same file is in 1 other repository

  • Codebase scanning

    slgoodrich/agents/plugins/ai-pm-copilot/skills/codebase-scanning Skill

    no license144★ repo

    AI PM Workflows for Claude Code

    The same file is in 1 other repository

  • Directional prompting

    kingbootoshi/directional-prompting/plugins/directional-prompting/skills/directional-prompting Skill

    144★ repo

    Outcome-first plus directional language. A two-layer skill for writing prompts, agent directives, and skill descriptions. Works in Claude Code and Codex CLI.

    The same file is in 2 other repositories

  • Battlechain

    Cyfrin/solskill/skills/battlechain Skill

    144★ repo

    The same file is in 1 other repository

  • Attention control

    aaddrick/attention-control/skills/attention-control Skill

    144★ repo

    Air traffic control discipline for agent output. Written for a reader with ADHD.

    The same file is in 2 other repositories

  • Docx

    appautomaton/document-SKILLs/docx Skill

    143★ repo

    Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

  • Manim skill

    Yusuke710/manim-skill/skills/manim-skill Skill

    143★ repo

    Create mathematical animations with Manim Community Edition(manimce). Generates distinctive, production-grade animations that avoid generic "AI slop" aesthetics. Use when user wants to animate concepts, equations, illustrate proofs, visualize algorithms, create math explainers, or produce 3Blue1Brown-style videos.

    The same file is in 3 other repositories

  • DottedSign

    DottedSign-Official/dottedsign-mcp/io.github.DottedSign-Official/dottedsign-mcp MCP server

    no license143★ repo

    Automate eSignature workflows and signing tasks via natural language commands.

  • MCP Fiscal Brasil

    nikolasdehor/mcp-fiscal-brasil/io.github.nikolasdehor/mcp-fiscal-brasil MCP server

    143★ repo

    Servidor MCP para integrar IAs com o sistema fiscal brasileiro: CNPJ, NFe, NFSe, SPED, eSocial.

  • Agent council

    team-attention/agent-council/skills/agent-council Skill

    143★ repo

    Collect and synthesize opinions from multiple AI agents. Use when users say "summon the council", "ask other AIs", or want multiple AI perspectives on a question.

    The same file is in 16 other repositories

  • Doctor

    lambdalisue/cclens/plugins/cclens/skills/doctor Skill

    143★ repo

    cclens — a lens onto your Claude Code usage

  • Now sdk

    ServiceNow/sdk/skills/now-sdk Skill

    no license143★ repo

    Fluent SDK

  • Mcp

    webflow/mcp-server/com.webflow/mcp MCP server

    142★ repo

    AI-powered design and management for Webflow Sites

  • Excalidraw Architect

    BV-Venky/excalidraw-architect-mcp/io.github.BV-Venky/excalidraw-architect-mcp MCP server

    142★ repo

    Generate beautiful Excalidraw architecture diagrams with auto-layout and component styling

  • Handbook discover

    NikiforovAll/claude-code-rules/plugins/handbook-discover/skills/handbook-discover Skill

    142★ repo

    Learn practical techniques to enhance your AI-assisted development workflow with Claude Code.

  • Firecrawl build interact

    firecrawl/skills/skills/firecrawl-build-interact Skill

    142★ repo

    Integrate Firecrawl `/interact` into product code for dynamic pages and browser actions after scraping. Use when a feature needs clicks, form fills, pagination, authentication-aware flows, or other multi-step interactions that plain `/scrape` cannot complete.

    The same file is in 31 other repositories

  • Trading212 api

    trading212-labs/agent-skills/plugins/trading212-api/skills/trading212-api Skill

    142★ repo

    ✨ Supercharge your AI agent with the power of the Trading 212 API

    The same file is in 11 other repositories

  • Google ai search optimization

    deepakness/google-ai-search-optimization/skills/google-ai-search-optimization Skill

    no license142★ repo

    Unofficial Agent Skill based on Google Search guidance for AI Overviews, AI Mode, and SEO audits.

    The same file is in 2 other repositories

  • Generateblocks layouts

    wpgaurav/generateblocks-skills/skills/generateblocks-layouts Skill

    no license142★ repo

    GenerateBlocks Skills to create better layouts with AI tools.

  • Linear claude skill

    wrsmith108/linear-claude-skill Skill

    141★

    Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.

  • Brainstorming

    arbiterForge/codeArbiter/core/surface/skills/brainstorming Skill

    141★ repo

    When you can't trust yourself with your code base, trust Arbiter.

  • Build

    Dave-London/Pare/io.github.Dave-London/build MCP server

    141★ repo

    Structured build tool output (tsc, generic commands) as typed JSON diagnostics.

  • X64dbg

    bromoket/x64dbg_mcp/io.github.bromoket/x64dbg MCP server

    141★ repo

    MCP server for x64dbg debugger - 23 mega-tools for AI-powered reverse engineering and debugging

  • Financial Modeling Prep MCP Server

    imbenrabi/Financial-Modeling-Prep-MCP-Server/io.github.imbenrabi/financial-modeling-prep-mcp-server MCP server

    141★ repo

    MCP server for Financial Modeling Prep API with 250+ financial data tools

  • Godot MCP

    satelliteoflove/godot-mcp/io.github.satelliteoflove/godot-mcp MCP server

    141★ repo

    Agent-driven Godot playtesting: editor control, input injection, game-time stepping, live state.

  • mockd

    getmockd/mockd/io.mockd/mockd MCP server

    141★ repo

    Multi-protocol API mock server: HTTP, GraphQL, gRPC, WebSocket, MQTT, SSE, SOAP.

  • Openspec new change

    taskless/cli/.agents/skills/openspec-new-change Skill

    141★ repo

    Taskless CLI and Agent Skills

    The same file is in 10 other repositories

  • Build db

    jar-analyzer/jar-analyzer-claude/plugins/jar-analyzer-plugin/skills/build-db Skill

    no license141★ repo

    Claude Code plugin for Java JAR security audit — 基于 jar-analyzer 的 Claude Code 安全审计插件,构建数据库,AI 深入分析

  • Isometric explainer

    LaurentiuGabriel/learnscape/skills/isometric-explainer Skill

    141★ repo

    Build an isometric, self-narrating explorable that teaches a complex system by laying it out as a place and walking a vehicle through it — a real simulation underneath, station-by-station narration on top, in one dependency-free static site (HTML + canvas 2D + plain JS, no build step, no framework). Use when the user wants to teach or visualise how something works end to end and a diagram or a chart is not enough: "explain how X works visually", "build an interactive/animated explainer for X", "visualise the whole pipeline", "make a TokenTown / EngineWorks / PGSimCity-style thing for X", "a city/factory/town that shows how X works", "teach X with an animation", "explorable explanation", "learning simulation". Also use when editing an existing project built from this skill — look for iso.js, world.js and a stations table. SKIP for: a single chart, graph, plot or dashboard (use dataviz); a static diagram or flowchart (use artifact-diagramming); a slide deck; a game with win conditions and scoring; a 3D scene needing WebGL, Three.js or real perspective; a UI mockup.

  • Eval suite planner

    microsoft/eval-guide/skills/eval-suite-planner Skill

    141★ repo

    Plan standalone — populates the Eval Suite Planning & Logging Template from an Agent Vision or plain-English agent description. Grounded in Practical Guidance on Agent Evaluation v5: Step 1 planning, Steps 2-3 eval-set decomposition, Step 4 gates/improvement targets, Step 5 human inputs, Step 6 grader-validation planning, Step 7 baseline placeholders, Step 8 regression partitioning, and Step 10 reusable-asset candidates. Output is a template-preserving `.xlsx` workbook plus an interactive HTML review page. Use before generating test cases or running evals.

  • Bibi

    JimmyLv/bibigpt-skill/skills/bibi Skill

    141★ repo

    OpenClaw / Claude Code / Codex Agent skill for summarizing videos/audio via BibiGPT CLI (bibi)

    The same file is in 1 other repository

  • Wangjianshuo perspective

    jianshuo/claude-skills/wangjianshuo-perspective Skill

    140★ repo

    王建硕的思维框架与表达方式。基于 7 份深度调研(约 100 万词英文博客 + 约 109 万字中文博客, 2002–2022,全部一手)提炼出 7 个核心心智模型、10 条决策启发式和完整的双语表达 DNA。 用途:以王建硕的身份和声音写作、回应、思考——他平实、诚恳、好奇,爱用家常比喻和自造词, 在具体和抽象之间反复架梯子,从不写自己没亲身验证过的东西。 当用户提到「用王建硕的视角」「王建硕会怎么看」「王建硕模式」「像王建硕一样写」 「Jian Shuo Wang perspective」「切换到王建硕」时使用。 即使用户只是说「帮我用王建硕的角度想想」「如果是王建硕会怎么写这篇」也应触发。 一旦激活,本次对话后续所有回应都保持王建硕身份,直到用户明确说「退出」—— 不需要每轮重新点名。 不适用:用户要的是关于王建硕本人的客观介绍 / 事实查询(「王建硕是谁」「他哪年创业的」), 那种问题正常回答即可,不要进入角色扮演。

  • Code Pathfinder

    shivasurya/code-pathfinder/dev.codepathfinder/pathfinder MCP server

    140★ repo

    Code intelligence MCP server: call graphs, type inference, and symbol search for Python/Go.

  • MCP Fiscal Brasil

    DeHor-Labs/mcp-fiscal-brasil/io.github.DeHor-Labs/mcp-fiscal-brasil MCP server

    140★ repo

    Ferramentas fiscais brasileiras: CNPJ, NF-e, IBS/CBS, ICMS, Simples Nacional, NCM/CFOP. Sem API key.

  • Nemp memory

    SukinShetty/Nemp-memory/skills/nemp-memory Skill

    140★ repo

    Persistent local memory for AI agents. Use when starting a new session, when the user mentions remembering something, when you need project context, when making architecture decisions, or when working with other agents on the same project.