4,956 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
trailofbitstrailofbits/skills3
team-devbostonaholic/team1
recouprecoupable/skills1
katalon-true-platform-marketplacekatalon-labs/true-skills1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceOrchestrates specialized agents to autonomously implement entire features end-to-end
A record label inside Claude. Let your agents create content, plan releases, reach new fans, and uncover opportunities across your catalog. Make music videos and cover art, research artists, discover talent, and build campaigns. Start with a song, an artist, or an entire catalog.
Agent-neutral AI testing skills for Katalon True Platform covering the full software testing lifecycle: test planning, test design, test management and requirement traceability, test review, manual and automated execution with AI, failure analysis and release readiness, and test maintenance - operated through the Katalon MCP.
Trading skills for the NinjaTrader MCP: market-structure analytics, pre-trade sizing, live position health, trade replay, coaching debriefs, alert composition, correlation-based hedging, event watch, and charting.
financeCLI toolbox for Observability-Driven Development (ODD): coding agents observe local runs on an OpenTelemetry/Grafana stack - or remote ones on any OpenTelemetry backend - and feed the next spec-driven improvement loop.
observabilityYour coding agent already plans and swarms — Wicked Garden is the curated toolkit for what it can't: proof-not-claims gates, code links grep can't see, deterministic refactor, cross-session memory, multi-model second opinions (fallback seats labelled). Don't fight the harness; fill its gaps. The gate needs wicked-vault (a self-contained infra peer, installed directly) and re-derives through garden's built-in engine; estate/bus are opt-in layers (wicked-testing and wicked-brain are retired — QE ships in-catalog as the qe domain, memory lives in wicked-estate).
Complete system: 15 problem-shaped skills backed by 97 genius agents, 86 skills total, 30 commands, 71 tools, 36 hooks, authoritative coding-standards rules, goal-driven and autonomous build loops, and the shared Claude Code and Codex gates
Common Narrative workflows backed by the narrative-mcp server — starting with Rosetta Stone attribute mapping generation, evaluation, and improvement.
Superpowers core skills plus a conservative ML-research layer (verification rungs, experiment design, result review). Fork of obra/superpowers.
Complete toolkit: all 52 skills covering development, documentation, git, github, jira, code review, testing, refactoring, CI/CD, image generation, framework documentation injection, product specs, multi-agent orchestration, open-source launch prep, skill creation and improvement, and more
Development skills: feature implementation, bug fixing, testing, refactoring, CI/CD generation, framework documentation injection, project planning, image generation (Codex imagegen), database migrations, Docker setup, environment setup, visual regression checks, i18n checks, release shipping, and open-source launch prep
Specialty skills: Browser automation (agent-browser), turning docs sites, PDFs, folders and YouTube videos into grounded agent skills (anything-to-skill), third-party skill discovery (find-skills), specification-driven skill creation with eval system and description optimization (create-skill v2.0), CLAUDE.md rule creation (create-rule), evidence-based improvement of existing skills (improve-skill), measured token-waste audits of AI coding setups (optimize-ai-setup), and model-tiered multi-agent orchestration (orchestrate)
Fastest ledger for agents. Built for businesses, finance teams, and accountants. IFRS-first, multi-currency, multi-user by default. Invoicing, bills, payments, quotes & orders, bank reconciliation, fixed assets, inventory, expense claims, tax, reports, and period close, all available for read and write. MCP tools load only when needed, so your agents stay lean and fast. Skills add migration from Xero, QuickBooks, Sage, and MYOB, close playbooks, financial calculators, Singapore Form C-S, and Jaz Kit for running many organizations. Works with Claude Code, Codex, Copilot, Cursor, and any MCP-compatible agent.
Rdzen weryfikacyjny instaluj-zawsze (11 skilli): routing zadania, ocena wejscia, grounding cytatu, ekstrakcja cytatow, sylogizm/subsumpcja, czerwony zespol, jednoprzebiegowy atak przeciwnika, test zimnego czytelnika (pierwsze wrazenie sedziego), wiernosc deliverable, ocena outputu, paczka audytowa AI Act art. 12. Neutralny jurysdykcyjnie, bez konektorow, bez wlasnych polaczen wychodzacych.
Wyszukiwanie i pobieranie zrodel prawa PL/UE (9 skilli): SAOS, EUR-Lex, katalog zrodel krajowych, hierarchia zrodel (routing autorytetu przed odpowiedzia), struktura wyroku (streszczenie ekstraktywne), grounding cytatu decyzji UODO (uodo-grounding-pl), webwright (orzeczenia spoza MCP przez Playwright), praca z konektorem Repertorium: zasady (repertorium-zasady-pl) i memo z przypisami ze zrodel (memo-z-repertorium-pl; konektor Repertorium podlacza sie osobno). Niesie konektory MCP saos/krs/eu-sparql (read-only, publiczne API). Wymaga node/npx.
Operacje na dokumentach (12 skilli): konwersja PDF/Office->Markdown (markitdown, opendataloader-pdf), redlining .docx z Track Changes (redline-docx-pl), anonimizacja i pseudonimizacja PII (let-it-be), metodyka terminow procesowych z bramka czlowieka (terminy-procesowe-pl), lista kontrolna klauzul umownych (klauzule-kontraktowe-pl), cztery kalkulatory procesowe z zywymi parametrami (kalkulatory-procesowe-pl), groundowana ekstrakcja konceptow prawnych warstwa LLM z zakotwiczeniem cytatu do zdania zrodlowego (doc-intel-llm-tier-pl, wymaga contextgem + modelu lokalnego/EOG; backend chmurowy tylko za jawna flaga), audytowalny kontrakt wyjscia OCR {block_type,bbox,text,confidence} z confidence-gatingiem human-in-the-loop, flagami PII pod redakcje i prompt-kontraktem vlm-html dla dowolnego VLM, OCR skanow na CPU (LiteParse) i lokalnym podzialem teczki na pisma (doc-intel-contract-pl, normalizacja zero-dep stdlib). walidacja podpisu elektronicznego w PRZYCHODZACYM PDF - czy plik zmieniono po p
Turn the current project website into a short, polished, shareable launch video using HyperFrames.
Diagnose and fix Claude in Chrome MCP extension connectivity issues
Interprets Culture Index survey results for individuals and teams
Produces CVSS v4.0 vector strings from plain-text vulnerability descriptions by systematically evaluating base metrics. Use when scoring a vulnerability, generating a CVSS vector, or estimating severity.
