115 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 115 plugins that match these filters.
pm-claude-skillsmohitagw15856/pm-claude-skills2
awesome-journal-skillsbrycewang-stanford/Awesome-Journal-Skills2
claude-code-plugins-plusjeremylongshore/tons-of-skills-marketplace1
aiwgjmagly/aiwg1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceLLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.4
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
Multi-agent collaboration — spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any task that benefits from diverse solutions. 7 slash commands (/hub-init, /agenthub:spawn, /hub-status, /agenthub:eval, /agenthub:merge, /agenthub:board, /hub-run), agent templates, DAG-based orchestration, LLM judge mode, message board coordination.
A second brain for Claude Code + Obsidian inspired by Karpathy's LLM Wiki gist. Turn any LLM CLI into a disciplined wiki maintainer: incrementally ingest sources into a persistent, interlinked markdown vault; update entity/concept/source pages; flag contradictions; maintain index and append-only log. Knowledge compounds instead of being re-derived by RAG on every query. Ships 3 sub-agents (wiki-ingestor, wiki-librarian, wiki-linter), 5 slash commands (/wiki-init, /wiki-ingest, /wiki-query, /wiki-lint, /wiki-log), 8 Python tools (stdlib only: init_vault, ingest_source, update_index, append_log, wiki_search BM25, lint_wiki, graph_analyzer, export_marp), 8 reference docs, full vault templates (CLAUDE.md, AGENTS.md, cursorrules, 5 page templates), and a worked example vault. Cross-tool compatible with Claude Code, Codex CLI, Cursor, Antigravity, OpenCode, and Gemini CLI.
Complete OpenRouter integration skill pack with 30 skills covering LLM routing, model selection, cost optimization, and multi-provider orchestration. Flagship+ tier vendor pack.
Static lint for Claude Code plugins and skills, with experimental LLM scoring for skills
AI/ML engineering skills for shipping AI features responsibly: Model Card, AI Eval Plan, RAG Design Doc, Agent Spec, Dataset Datasheet, AI Feature PRD, LLM Cost & Latency Budget, Prompt Optimizer, Eval Rubric Designer, RAG Architecture Review, LLM Guardrails Spec, Agent Design Review, and Model Selection Advisor.
Operate AI agents and LLM features in production: prompt regression suites, model migration plans, context-engineering reviews, agent incident postmortems, and observability specs — plus the pm-ai evaluation and cost skills they build on.
Twelve ICLR-specific skills for ML conference submission strategy, grounded in official ICLR 2026 CFP, Author Guide, Reviewer Guide, Code of Ethics, Code of Conduct, and LLM-use policy.
academicTwelve ICML-specific skills for ML conference submission strategy, grounded in official ICML 2026 author instructions, CFP, Peer Review FAQ, review instructions, and LLM-review policy.
academicTools, skills, and CLI extensions for designing and productionizing LLM inference pipelines. Pattern-guided, slim by default, eval-first.
Agent frameworks, prompt engineering and structured generation.
researchAdd Arize AX observability to LLM applications — auto-instrumentation, trace export, dataset management, experiment workflows, prompt optimization, deep linking, and migrations from Langfuse, LangSmith, and Braintrust via the ax CLI.
Clinical AI model research engineering: choose a paper-grounded architecture, scaffold a reproducible PyTorch training repo, validate the model's split and validation design, document it (Model Card / Datasheet), and evaluate models or LLMs/MLLMs on clinical tasks. Integrates MONAI / nnU-Net, never replaces them.
Unified AI-native Vibe Coding plugin: PRD generation, digging analysis, screen-spec (IA / User Flow / Wireframe HTML / Dev Handoff), team-based parallel implementation, quality-gated auto-commit, 20 design styles, frontend (React/Next.js), backend (NestJS/Prisma), mobile (React Native/Expo), AI integration (STT/LLM), DevOps (Docker/CI-CD). 11 agents, 5 commands, 8 skills, team knowledge wiki (auto-collect + recall for WIGTN repos).
Cut LLM API spend via model routing, prompt caching, prompt compression, and per-feature cost observability. Use when AI costs are too high, choosing between models, or launching an AI feature without cost architecture. NOT for RAG design or prompt quality (separate skills).
Assisted retrospective: after a session, calibrates what Claude contributed vs what the developer drove. LLM-assessed 4-frame analysis with explicit rubric, zero dependencies.
GABBE ai skills (11): AI and agent engineering: multi-agent systems, agent UIs and protocols, context engineering, RAG evaluation, LLM-as-judge and reasoning patterns.
Claude API and SDK documentation skill for building LLM-powered applications
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
