Everything for Claude Code

Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 371,324 indexed, measured the same four ways as everything else here.

ynab-mcp-server

11449

oliverames/ynab-mcp-server

Plugin Claude Code

Bundles 1 MCP server

YNAB MCP connector for budgets, transactions, categories, scheduled transactions, accounts, months, payees, and budget review workflows.

not rated 34 +1 changed 13d ago A tokens not measured original MIT

factory-evidence

11451

nicolasmelo1/software-factory

Skill Claude CodeCodex

Create or run the proof behind a software-factory L3 gate and seal evidence that survives re-verification. Use when a feature needs its first gate, when a gate is red for missing or stale evidence, or when asked to prove a change actually works end to end.

not rated 34 +1 changed 23d ago A SkillSpector: pass 59 tokens original MIT

ace-rtl

11452

NVlabs/ACE-RTL

Skill Claude CodeCodex

Consolidated ACE-RTL skill for running an iterative generator-reflector-coordinator RTL agent on CVDP. Use for CVDP official repo setup with native or Docker environments, no-cheating benchmark runs, role-based external LLM routing, unique outputs logging, task-driven CVDP prompt guidance, and real pass-rate reporting.

not rated 34 +1 7d ago A 72 tokens

outlook-mcp

11453

mpalermiti/outlook-mcp

Skill Claude CodeCodex

Production-grade MCP server for personal Outlook (Outlook.com / Hotmail / Live). 70 typed Graph tools across mail, calendar, contacts, to-do, drafts, attachments, folders, threading, batch ops, delta-sync. Granular permissions, OS-keyring auth, /$batch-optimized triage and bulk read. Built for agents that need real…

not rated 35 +2 changed 3d ago A 93 tokens original MIT

fixing

11454

nearform/lastlight

Skill Claude CodeCodex

Diagnose why a PR's CI failed — compare the CI definition against the sandbox, classify the failure, and make the minimal repair. Use when a PR is red and you must work out why before changing anything.

not rated 34 +2 today A SkillSpector: warn 46 tokens original MIT

kb-ingest

11455

waylondev/kb-pilot

Skill Claude Code

Use when the user wants to add a Markdown document to the knowledge base, ingest a whole directory of .md files, or initialize the knowledge base from a Git repo. Triggers on "ingest this doc", "add to knowledge base", "import these markdown files", "set up the knowledge base from this repo" — even when the user…

not rated 34 27d ago A 94 tokens

uptimepage

11456

uptimepage/uptimepage

MCP server Claude CodeCodexCursor +2

Monitor uptime and incidents, run checks, and publish status updates from your Uptimepage org. Remote server at mcp.uptimepage.dev.

not rated 34 +1 today A tokens not measured AGPL-3.0

image-prompt-reverse

11457

luozhilzh/image-prompt-reverse

Skill Claude CodeCodex

A skill that turns an image or a rough idea into structured prompts for AI image generators such as Midjourney, DALL·E, Stable Diffusion, and Flux.

not rated 34 +3 1mo ago A 135 tokens original MIT

series-bible

11458

pixellion2262-fwtk2/series-bible

Skill Claude CodeCodex

A planning tool for building a consistent content series, such as a YouTube channel, newsletter, or short-video programme. A series bible is a reference document covering its audience, voice, recurring topics, formats, rules, and future ideas.

not rated 34 2mo ago A 89 tokens original MIT

okrs-draft

11459

pixelcat6092-xxm6j/okrs-draft

Skill Claude CodeCodex

A drafting tool for OKRs, a planning method that pairs broad objectives with measurable key results. It is designed for small product and engineering teams, with English, Chinese, or bilingual output.

not rated 34 1mo ago A 113 tokens original MIT

vetto-sandbox

11460

shleder/vetto

Skill Claude CodeCodex

Enforce zero-daemon Landlock/Seatbelt security boundaries, network isolation, and subagent capability controls when executing untrusted commands or running subagents. Use when running terminal commands, testing untrusted scripts, isolating AI subagent workflows, or performing read-only session recovery for Codex and…

not rated 36 +8 today A SkillSpector: pass 67 tokens original Apache-2.0

memory-kit

11461

awrshift/agent-memory-kit

Plugin Claude Code

Bundles 10 skills, 4 agents, 4 hooks · 1,943 tokens together

Persistent memory for your agent as plain files in your folder: a hot cache injected every session and held under three size caps, per-session handoffs, and promotion into knowledge articles and rules only on your yes. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second…

not rated 35 changed yesterday A tokens not measured original MIT

coingecko

11462

coingecko/skills

Skill Claude CodeCodex

Use this skill for any request involving cryptocurrency market data, coin prices, trading volume, market cap, OHLC charts, historical data, exchanges, derivatives, NFTs, DeFi, on-chain token data, liquidity pools, DEX data, or anything powered by CoinGecko or GeckoTerminal APIs. Trigger this skill whenever the user…

not rated 34 +1 1mo ago A 124 tokens original MIT

jlink-mcp

11463

cyj0920/jlink_mcp

MCP server Claude CodeCodexCursor +2

A local MCP server that connects an AI assistant to a J-Link hardware debugger used for embedded development.

not rated 34 5mo ago A tokens not measured original MIT

orders-domain

11464

mrlm-xyz/demo-claude-marketplace

Skill Claude Code

Project-knowledge skill for orders-api. The order lifecycle, invariants, and money handling specific to this codebase. Loads when working on order logic in this service.

not rated 34 +1 25d ago A SkillSpector: pass 37 tokens original Apache-2.0

context7

11465

whtoo/How_to_implment_PL_in_Antlr4

MCP server Claude CodeCodexCursor +2

Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.

not rated 34 4mo ago A tokens not measured original BSD-3-Clause

katok

11466

changeroa/lazykatok

Skill Claude CodeCodex

Search local KakaoTalk keyword, BM25, and EmbeddingGemma vector indexes through the katok CLI, list rooms, export chunks or transcripts, extract attachments, and prepare guarded message sends only after explicit user confirmation.

not rated 34 +1 6d ago A 48 tokens copy · 100% MIT

playwright

11467

jujunjun110/claude-looper

MCP server Claude CodeCodexCursor +2

Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.

not rated 34 7mo ago A tokens not measured copy · 72% MIT

example-skill

11469

xcota/pos

Skill Claude Code

Example module showing the format. Use when: testing /enable-modules, learning to author a module.

not rated 33 14d ago A 25 tokens original AGPL-3.0

vorim

11470

Vorim-AI-Labs/vorim-openclaw-skill

Skill Claude CodeCodex

AI agent identity, permissions, trust scores, and audit trails via Vorim AI. Gives your OpenClaw agent a cryptographic identity so every action is verified, permissioned, and logged.

not rated 33 2mo ago A 42 tokens original MIT

surrealdb

11471

24601/surreal-skills

Skill Claude CodeCodex

Expert SurrealDB 3 architect and developer skill (tracks v3.1.4+). SurrealQL mastery, multi-model data modeling (document, graph, vector, time-series, geospatial), schema design, security, deployment, performance tuning, SDK integration (JS, Python, Go, Rust, Java, .NET, C, PHP, Swift, Kotlin, Ruby), Surrealism WASM…

not rated 33 +1 3mo ago A 204 tokens original MIT

algorand-x402-python

11472

algorand-devrel/algorand-agent-skills

Skill Claude CodeCodex

Builds x402 HTTP-native payment applications on Algorand using Python. Covers clients (httpx, requests), servers (FastAPI, Flask), facilitators, Bazaar discovery, and the x402-avm library. Use when implementing x402 payment flows in Python, creating payment-gated APIs, building x402 facilitators, or integrating the…

not rated 33 changed 18d ago A SkillSpector: pass 82 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: