agentsclimarketplace

The catalog

608,475 rows, by stacks then stars

  • Atp ctp check

    MetaFloor-AI/metafloor-scm-plugin/skills/business-workflows/atp-ctp-check Skill

    1★ repo

    Supply-chain operator expertise + a deterministic safety gate for Claude Code — 55 enterprise systems, 16 end-to-end workflows, autonomy dial.

  • Office docs overview

    G-Yong/office-docs/skills/office-docs-overview Skill

    1★ repo

    Use when an agent needs to read, write, edit, or generate Microsoft Office files (Word .docx/.doc, Excel .xlsx/.xls/.csv) on Windows - routes to the right COM automation skill and decides COM vs library-based approaches

  • Qvts orchestration

    JSungMin/vts-local-orchestrator/skills/qvts-orchestration Skill

    1★ repo

    Routing rules for delegating cheap, high-volume CODE-LOCATION and FILE-READING work to a local Qwen (Ollama, full-GPU) that drives vs-token-safer's vs-search tools — so Claude spends tokens on reasoning, not raw search/file output. Use whenever you need to find symbols/usages/files (def_search/search), survey a module, or summarize/assess a big file or diff without reading it into context (qvts digest/digest-dir/triage-diff); the raw stays in the local model and only a compact brief returns to Claude.

  • Using superpowers

    obra/temp-sp-codex/skills/using-superpowers Skill

    1★ repo

    Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

    The same file is in 56 other repositories

  • Scaffold benchmark

    VassilisSoum/prove/skills/scaffold-benchmark Skill

    1★ repo

    Measure a proposed change for the developer — author and run the experiment, don't hand them a blank template. Use when someone asks "is X better?", "should I ship this?", "did this improve Y?", or proposes swapping/tuning an implementation. Reads the change from the code (git diff / the named functions), scaffolds the bench/ harness if absent, WRITES the arms + a starter case set (including adversarial cases) by reading the repo, shows the cases for a quick human OK, runs it, and reports the verdict. The developer's whole job is: ask the question, eyeball the cases, read the result.

  • Create image

    noahrasheta/shipfast/create-image/skills/create-image Skill

    1★ repo

    A collection of plugins, agents. and skills that I use to ship fast!

  • Learner

    Tykok/learning-with-claude/skills/learner Skill

    1★ repo

    Turns Claude Code into a learning loop: quizzes you on your own diffs, tracks weak spots per developer.

  • Safe migrations

    jonedavis/migration-marshal/skills/safe-migrations Skill

    1★ repo

    Use when reviewing, writing, or editing a Postgres schema migration: any DDL such as ALTER TABLE, ADD/DROP COLUMN, ALTER COLUMN TYPE, ADD CONSTRAINT, or CREATE INDEX, including .sql files and migrations generated by Prisma, Drizzle, TypeORM, or Knex. Classifies lock and downtime risk and provides zero-downtime rewrite recipes for high-traffic production tables.

  • Authoring reference

    pkloehn1/techdocs-authoring/skills/authoring-reference Skill

    1★ repo

    Use when writing, structuring, or reviewing any README, how-to, tutorial, reference, ADR, runbook, release notes, or AI-agent-readable docs. Reference knowledge and an authoring playbook for technical documentation: picking a canonical style guide, the Diataxis four-mode model (tutorial/how-to/ reference/explanation), copy-paste templates and reviewer checklists, single-sourcing and content reuse, a writing process that leads with the bottom line, and writing docs that serve both humans and AI agents.

  • Literature in depth reading

    XuananLu/literature-In-depth-reading-skill/plugins/literature-in-depth-reading/skills/literature-in-depth-reading Skill

    no license1★ repo
  • Koica regulation research

    amnotyoung/oda-intelligence-plugin/plugins/oda-intelligence/skills/koica-regulation-research Skill

    1★ repo

    Public Claude, Codex, and ChatGPT integration for the ODA Intelligence read-only MCP gateway

  • Peek

    pj4316/vibe-recipe/plugins/vibe-recipe/skills/peek Skill

    1★ repo
  • Feature ship

    r1ckshot/team-marketplace/plugins/tax-navigator-toolkit/skills/feature-ship Skill

    no license1★ repo

    The same file is in 1 other repository

  • Vc market definition

    extruct-ai/vc-skills/skills/vc-market-definition Skill

    no license1★ repo
  • Vanta workspace

    Elnora-AI/elnora-vanta/skills/vanta-workspace Skill

    1★ repo

    Read-only Vanta compliance CLI — frameworks, tests, controls, documents, vulnerabilities, risks, people, integrations, policies, vendors, groups, computers. Agent-friendly JSON output, strictly HTTP GET. Use when: checking compliance status, failing tests, missing evidence, vulnerability SLAs, risk register, audit prep, or any Vanta query. TRIGGERS: "vanta", "compliance", "soc 2", "iso 27001", "failing tests", "compliance tests", "controls", "evidence", "vulnerabilities", "vulns", "SLA", "risk register", "audit", "security posture"

  • Claude harness visualizer

    staqsIO/claude-harness-visualizer/skills/claude-harness-visualizer Skill

    1★ repo

    Visualize a Claude Code harness setup — agents and their model tiers, hooks across the session lifecycle, orchestrator routing, the review pipeline, and installed commands/skills/plugins/MCP servers — as an interactive page. Use when the user says "/claude-harness-visualizer", "visualize my harness", "show my Claude Code setup", "map my agents and hooks", "what hooks do I have", "diagram my config", or asks how their harness is wired. Also use when auditing a config for model-tier drift (bare `inherit`, unpinned agents) or reviewing which hooks fire when.

  • Integrate posthog

    ThiloReintjes/skills/skills/integrate-posthog Skill

    1★ repo

    Integrate or upgrade PostHog across a web, full-stack, serverless, edge, or AI application. Use when adding product analytics, identity tracking, session replay, error tracking, performance monitoring, first-party ingestion, backend events, or AI observability with PostHog.

  • Organize commits

    identity16/brown/skills/organize-commits Skill

    no license1★ repo
  • Review

    matthewalton/speccle/packages/plugin/skills/review Skill

    1★ repo

    A software factory for Claude Code — an inner loop that builds spec-defended feature slices, an outer loop of risk-gated reviews, and a meta loop that turns every finding into prevention

  • Production readiness review

    juanibosco/prod-review/skills/production-readiness-review Skill

    1★ repo

    Spine of the Production Readiness suite. Aggregates per-area readiness reports into one weighted score (0-100) and a phased, evidence-backed go-live plan. Owns the shared scoring contract, severity rubric, evidence rule, and report template. Tuned for NestJS / TypeORM / Cloudflare / GCP / PM2-Ubuntu stacks. Use when consolidating area results from /prod-review:audit, or to score a single area's findings against the contract. Does not re-judge — it only aggregates.

  • Hebrew rtl best practices

    meytalp-dev/meytal-claude-code-basic/.claude/skills/hebrew-rtl-best-practices Skill

    1★ repo

    Implement right-to-left (RTL) layouts for Hebrew web and mobile applications. Use when user asks about RTL layout, Hebrew text direction, bidirectional (bidi) text, Hebrew CSS, "right to left", or needs to build Hebrew UI. Covers CSS logical properties, Tailwind RTL, React/Vue RTL, Hebrew typography, and font selection. Do NOT use for Arabic RTL (similar but different typography) unless user explicitly asks for shared RTL patterns.

    The same file is in 1 other repository

  • Generate repograph

    rwaltenberg/repograph/skills/generate-repograph Skill

    no license1★ repo
  • Failure injection testing

    13eholder/zflow/skills/failure-injection-testing Skill

    1★ repo

    通过受控故障注入验证系统的容错能力。在验证节点宕机、网络分区、磁盘慢盘/坏盘、时钟漂移等故障路径时使用。当系统声称具备容错/高可用能力但缺乏故障路径证据时、上线前需要验证恢复流程时,或需要建立常态化混沌工程实践时使用。

  • Arch

    supostat/mneme-plugin/plugin/skills/arch Skill

    no license1★ repo

    Persistent cross-project memory and phase-workflow engine for Claude Code — human-gated, local-first, event-sourced. Ships as a plugin.

  • Kabelsalat

    ThePixelPilgrim/kabelsalat/skills/kabelsalat Skill

    1★ repo

    A crash-safe GTK4/libadwaita terminal emulator with tabs organised into colour-coded groups

  • Appstore requirements

    crgeee/apple-appstore-toolkit/skills/appstore-requirements Skill

    1★ repo

    Claude Code plugin: App Store readiness review toolkit for React Native & Swift iOS apps

  • Run agent hive

    mckova/agent-hive/plugins/claude-code/agent-hive/skills/run-agent-hive Skill

    1★ repo

    Multilingual, budget-aware agent orchestration for Codex and Claude Code with model routing, guardrails, memory, monitoring, and resumable execution.

  • Onboard

    lucafossen/claude-rigor/skills/onboard Skill

    1★ repo

    Scientific research workflow for Claude Code

  • Software factory

    yasnoyas944-ops/claude-software-factory/skills/software-factory Skill

    1★ repo

    Build a full software project or website end-to-end from a single brief, by orchestrating the whole tool stack: superpowers discipline (brainstorm/plan/TDD/verify), karpathy code restraint, a ruflo agent swarm with shared memory, ECC agents + AgentShield security gate, and open-design for frontend. Use when the user wants to build, scaffold, or ship a complete app/website/service and wants one command to run the entire pipeline hands-free.

  • Formal methods guide

    kotaroyamame/formal-agent-contracts/skills/formal-methods-guide Skill

    1★ repo

    Provide reference knowledge on VDM-SL and formal methods. Triggered by "VDM-SL syntax", "how to write types", "what is a pre-condition", "what is an invariant", "meaning of proof obligations", "what are formal methods", or "formal specification". Also responds to Japanese: 「VDM-SLの文法」「事前条件とは」「形式手法とは」等。 Referenced as background knowledge by other skills (define-contract, verify-spec).

  • Multi ai review agent

    MathieuDoyon/multi-ai-review-agent/skills/multi-ai-review-agent Skill

    1★ repo

    Adversarial multi-AI peer review of a code change via the Cursor `agent` CLI across diverse model families (GPT/Codex, Claude/Opus, Grok, and more), with interactive model selection, selectable thinking level, base-ref override, extra focus, and a remembered last-used lineup. Use when the user asks for a "multi-AI review", "cross-AI review", "peer review", "review with cursor / agent / multiple models", or wants an independent second/third opinion on a diff, PR, or commit before merging.

  • Claude md improver

    AstyanM/claude-am-plugin/skills/claude-md-improver Skill

    1★ repo

    Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".

    The same file is in 152 other repositories

  • Brain

    skitzo2000/amnesia-labs-plugins/brain/skills/brain Skill

    no license1★ repo

    Amnesia Labs internal plugins (alpha). Invite only.

  • Patch bot

    CrackedResearcher/patch-bot/skills/patch-bot Skill

    no license1★ repo

    A Claude Code skill that fixes your prod bugs and opens the PR. ‎ ‎‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ npx skills add CrackedResearcher/patch-bot

  • Create general agent

    hungson175/claude-agent-kit/skills/create-general-agent Skill

    1★ repo

    Create ONE self-contained personal AI agent in its own folder, with a two-part brain: file-based memory plus a knowledge base built with Andrej Karpathy's "LLM wiki" method (append-only raw/ + distilled wiki/). The agent is standalone — it does NOT report to or coordinate with any other agent. Use this whenever someone asks to "create an agent", "make/spawn/bootstrap a new agent", "set up a personal assistant/tutor/research agent", "scaffold an agent with memory and a knowledge base", or wants a dedicated agent for one topic, project, or domain. Do NOT use for multi-agent teams.

  • Deep research

    Branded-Mayhem-Collective-LLC/brandprint-engine/skills/deep-research Skill

    1★ repo

    Use when a task needs enterprise-grade research across many sources with citation tracking and verification. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.

  • Teamvault

    Seibert-Data/teamvault-cli/skills/teamvault Skill

    1★ repo

    Commandline tools for Teamvault

  • Intelligo export pdf

    intelligogroup/Intelligo-agents-plugins/skills/intelligo-export-pdf Skill

    1★ repo

    Guided PDF export from Intelligo — walks the user through scope and content options before calling exportPdf. Trigger whenever the user wants to download, export, or get a PDF of a report or project in Intelligo, or says things like "download this report", "export to PDF", "get me the PDF for this project", "download all profiles", "export the report for [name]", or anything implying they want a PDF out of Intelligo. Always use this skill instead of calling exportPdf directly — it ensures the right scope and options are chosen first.

  • Test bot

    meetstream-ai/claude-plugin/skills/test-bot Skill

    1★ repo

    Send a single test bot to a live meeting and stream every webhook event to the terminal in real time. Used to validate end-to-end MeetStream configuration before shipping. Use when the user says "test my MeetStream setup", "send a test bot", "validate my webhook", "watch bot events live", "debug a bot run", or "make sure everything works".

  • Home server

    birdcar/claude-plugins/plugins/home-server/skills/home-server Skill

    no license1★ repo

    Personal Claude Code plugin marketplace

  • Drive

    dmitrykrivaltsevich/claude-skills/skills/drive Skill

    no license1★ repo

    Yet another set of claude skills

  • Sdp

    SeuPut0705/seudesign/skills/sdp Skill

    1★ repo

    Executable system design skill for Claude Code & Codex — design docs, architecture audits, mock interviews, capacity estimation

  • Skill curator

    cskwork/skill-curator/skills/skill-curator Skill

    1★ repo

    Agent Skills librarian for LLM coding agents: inventory, validate, deduplicate, archive, and restore SKILL.md packages across Claude Code, Codex, Cursor, Gemini CLI, and OpenCode

  • Prune low value tests

    neocybereth/skills/skills/prune-low-value-tests Skill

    no license1★ repo

    Portable agent skills for Codex and Claude Code

  • Astrolabe common

    astrolabe-apps/astrolabe-common/skills/astrolabe-common Skill

    no license1★ repo
  • Docent

    calumjs/docent/skills/docent Skill

    no license1★ repo

    Turn any GitHub repo into a public-facing, self-maintaining website

    The same file is in 1 other repository

  • Sway skill

    milojarow/sway-skills/skills/sway-skill Skill

    1★ repo

    Expert Claude Code skills for sway window manager — config, keybindings, IPC, outputs, inputs, bar, swaylock, swayidle, swayr, swaybg, swayimg

  • Git worktree

    gosu-code/claude-plugin/plugins/gosu-mcp-core/skills/git-worktree Skill

    1★ repo

    Gosu Claude Code Plugins & Marketplace

  • Connect mcp setup

    cloudblue/agent-skills/core/skills/connect-mcp-setup Skill

    1★ repo

    A curated collection of AI skills, prompts, and workflows for interacting with our MCP servers.

  • Ui design principles

    cyface/cyface-claude-plugin-marketplace/plugins/ui-design-principles/skills/ui-design-principles Skill

    no license1★ repo

    Cyface Claude Code plugin marketplace

    The same file is in 1 other repository

  • Governance awareness

    germpharm/charter-cowork-plugin/charter-governance/skills/governance-awareness Skill

    1★ repo

    Charter Governance plugin for Anthropic's Claude Cowork. AI governance infrastructure: ethical constraints, audit trails, attribution stamps, human approval gates.

  • Paper report

    Lslightly/conf-abstract/plugins/conf-analysis/skills/paper-report Skill

    no license1★ repo
  • Loopd init

    shmor3/MrSkills/plugins/loopd/skills/loopd-init Skill

    1★ repo

    Claude Code + Codex plugins — loopd: multi-loop parallel development orchestration

  • Linq reputation

    linq-team/linq-ai/skills/linq-reputation Skill

    1★ repo

    Linq plugin for AI coding agents — rules, skills, and MCP for building iMessage, RCS, and SMS on Linq

  • It council

    rogercg/council-ti/plugins/it-council/skills/it-council Skill

    1★ repo
  • Rednote writer

    xueyouluo/rednote_mining/skills/rednote-writer Skill

    no license1★ repo

    小红书笔记数据自动挖掘Skill

  • Architect web

    Jktfe/flowspec-claude-code-plugin/skills/architect-web Skill

    1★ repo

    Create and manage FlowSpec data architecture projects via the web app at flowspec.app using Chrome browser tools. For users without the desktop app. Generates JSON locally and uses light browser automation to import into the web editor. Requires the Claude in Chrome extension.

  • Fireclaude

    sannidhyas/fireclaude/skills/fireclaude Skill

    1★ repo

    Scrape web pages, batch-scrape URL lists, search the web, map sites, crawl documentation, and extract structured JSON via a self-hosted Firecrawl — with local SearxNG for web search and local Ollama (llama3.2:3b) for LLM extract. Use when the user needs to fetch live web content as markdown, convert URLs to a dataset, build a research corpus from websites, extract structured data matching a JSON schema, discover pages on a site, or run a web search without external API keys. Also triggers on: 'scrape this URL', 'build dataset from these sites', 'crawl docs', 'search the web', 'get markdown of X', 'extract these fields from a page'. No external API key, no rate limits.

  • Apply

    slowloris-98/HireShire-plugin/skills/apply Skill

    no license1★ repo
  • Agent debate

    JoaquinCampo/agent-debate/skills/agent-debate Skill

    1★ repo

    Use when the user wants two AI agents to debate or discuss something together, or presents a hard "X vs Y" architecture tradeoff. Default pair is Claude vs Codex; supports claude-codex, codex-claude, claude-claude, codex-codex. Triggers: "have them debate", "ask Codex too", "discuss with another agent", "two Claudes debating". Skip simple lookups and code edits.