Data and AI plugins

hardness1020/awesome-prompt-skill

Plugin Claude Code

Bundles 1 skill · 114 tokens together

Expert guidance for designing, optimizing, evaluating, and securing prompts and system prompt architectures for LLMs.

matterhornso/subscribetome

Plugin Claude Code

Bundles 4 commands, 4 hooks · 53 tokens together

AI API key & subscription manager. Out-of-band key entry, OS-keychain storage, and a PreToolUse hook that injects real keys into commands so the model only ever sees placeholders.

Blakeem/AI-Prompt-Guide-MCP

Plugin Claude Code

Lists 1 plugin

Plugin marketplace listing 1 plugin: ai-prompt-guide.

uwuclxdy/claudix

Plugin Claude Code

Bundles 1 skill, 1 command, 4 hooks · 64 tokens together

Local semantic search plugin for Claude Code — indexes your repository and exposes hybrid vector+BM25 search via MCP, slash commands, and grep interception.

AleksandarBisevac/claude-plugins

Plugin Claude Code

Bundles 2 skills, 20 commands, 4 agents, 6 hooks · 1,785 tokens together

Manifest-driven, model-aware, test-driven audit/fix pipeline. Ships /audit:status|next|run|phase|review|resume|report (execution), /audit:init (multi-agent manifest generation with an approval gate — decline parks phases as proposals), /audit:propose (list/materialize/drop parked phase proposals), /audit:task (task…

fschmutz/claude-usage-panel

Plugin Claude Code

Bundles 1 MCP server

Ask Claude for your plan usage: a getusage MCP tool returning session, weekly, and per-model limits from the official Anthropic usage endpoint.

choiyounggi/dev-loop

Plugin Claude Code

Lists 1 plugin

Marketplace for dev-loop — a wiki-grounded implementation loop plugin for Claude Code (loop-orchestrator + dev-llm-wiki, merged).

dinglebear-ai/axon

Plugin Claude Code

Bundles 26 skills, 1 command, 1 agent, 1 MCP server · 919 tokens together

Self-hosted RAG engine in Rust: crawl, scrape, ingest, embed, and query any source, with hybrid retrieval and cited LLM synthesis over MCP, CLI, and REST.

tkpratardan/lemma

Plugin Claude Code

Bundles 10 skills, 6 hooks, 1 MCP server · 302 tokens together

Senior data-scientist mode for AI agents, plus live-notebook tools. Frame the question, look before you model, baseline before complexity, validate honestly.

Rebell-Leader/SpatialAI_MCP

Plugin Claude Code

Bundles 4 skills, 1 MCP server · 223 tokens together

Domain skills + MCP validation tools for OpenProblems spatial transcriptomics benchmarks (SpatialData/zarr, Viash, the iST preprocessing pipeline).

an8079/take-skills

Plugin Claude Code

Lists 1 plugin

An intelligent development workflow featuring Socratic interviewing, dual-agent debate, expert team coordination, and RAG system design. Built on Claude Code for seamless AI-assisted development.

bengous/claude-code-plugins

Plugin Claude Code

Bundles 5 commands · 169 tokens together

Prompt tooling for Claude Code: write and audit prompts (meta-prompt, prompt-coach, prompt-health) and introspect how the harness executes them (dump-system-prompt, explain-workflow).

OleanderHQ/claude-plugin

Plugin Claude Code

Bundles 7 skills, 1 MCP server · 385 tokens together

The all-in-one data stack for agents. Your data jobs deserve to run on the right tool. Whether you're bringing existing infra, or exploring our open source deployments, oleander empowers your entire data stack to work together as a team.

GaZmagik/claude-prompt-improver

Plugin Claude Code

Bundles 1 hook

Automatically improves prompts for better Claude responses with configurable AI models.

napalmpapalam/skills

Plugin Claude Code

Bundles 1 hook

Brief English-grammar coaching on every prompt via a UserPromptSubmit hook.

ramonclaudio/skills

Plugin Claude Code

Bundles 2 skills, 18 commands, 1 MCP server · 536 tokens together

Wraps the qmd MCP server so Claude can search indexed reference repos (Convex, Expo, Next.js, etc) with hybrid BM25 + vector + reranking. Ships a search SKILL that teaches Claude how to compose typed sub-queries with intent, plus an /qmd:add SKILL that clones and indexes a GitHub repo end-to-end.

Jerry0022/dotclaude

Plugin Claude Code

Bundles 1 skill · 96 tokens together

Local LLM integration for Claude Code — delegates mechanical coding tasks to a local AnythingLLM Desktop workspace to save tokens without sacrificing quality.

promptctl/laws

Plugin Claude Code

Bundles 5 skills, 3 hooks · 505 tokens together

Universal architectural laws for code work, medium-scoped quality skills (code / prose / prompt), and skill-router hooks that route to the right one at session start, re-engage the laws on every message, and refuse a second medium skill in one session.

zilliztech/zilliz-plugin

Plugin Claude Code

Bundles 21 skills, 2 commands · 993 tokens together

Manage Zilliz Cloud clusters and Milvus vector databases from Claude Code using the zilliz-cli.

aahlijia/dekko

Plugin Claude Code

Bundles 5 skills, 3 commands, 1 MCP server · 594 tokens together

Adds a /map command that programmatically scans the repository: every code file, function, parameter, type, return type, and the call relationships between functions. Writes MAP.md and map.json without spending model tokens on parsing.

nikolay-e/diffctx

Plugin Claude Code

Bundles 2 commands, 1 MCP server · 28 tokens together

Selects the minimum code an LLM needs to review a git diff.

bethanychamberlain/claude-skills-librechat

Plugin Claude Code

Bundles 2 skills · 127 tokens together

LibreChat RAG, file handling, and tool configuration.

Zachariah9420/embedded-systems-architect

Plugin Claude Code

Bundles 1 skill · 274 tokens together

Evidence-driven embedded systems & edge-AI development skill: vendor-doc intake, cross-layer feasibility reasoning, model deployment compatibility, performance estimation, and hard-gated flashing/recovery guidance.

infiniV/ultra-ml-intern

Plugin Claude Code

Bundles 4 skills, 2 commands, 2 agents, 1 MCP server · 806 tokens together

Paper-grounded ML research and open-problem attack for Claude Code. Crawls arXiv and citation graphs, reads whole papers in parallel subagents, mechanically verifies every quote, archives a model's real code locally and grounds later sessions in it, and runs falsifiable attacks on hard unsolved problems.