Everything for Claude Code

Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 370,790 indexed, measured the same four ways as everything else here.

migrate-spec

4777

danielvm-git/bigpowers

Skill Claude CodeCodex needs its repo

Detect GSD, spec-kit, or BMAD spec artifacts and transform them into bigpowers YAML layout (state.yaml, release-plan.yaml, epics/, requirements/, plans/, ADRs). Use when migrating foreign spec docs.

not rated 193 +15 2d ago A SkillSpector: warn 49 tokens original MIT

jacobian

4778

morluto/jacobian

MCP server Claude CodeCodexCursor +2

Executable mathematics and independent verification for AI agents. Runs locally from the jacobian npm package.

not rated 193 +3 yesterday A tokens not measured original MIT

Weaverse/weaverse

Skill Claude Code needs its repo

Use when releasing @weaverse/ npm packages, bumping SDK versions, publishing to npm, or shipping the Weaverse SDKs. Triggers on "release sdk", "release weaverse", "publish packages", "release core", "release schema", "bump sdk version", "ship sdks".

not rated 193 +103 changed 5d ago A SkillSpector: warn 70 tokens original MIT

czm15053/write-notes-like-deepseek

Skill Claude CodeCodex

Use when a change is non-trivial by DSH standards (behavior, architecture, cross-file contracts, process/tooling, testing strategy, or on-disk/wire/config formats), when choosing between technical alternatives, superseding a decision, or writing a postmortem. Records the why and rejected options in .agents/notes/ with…

not rated 193 +79 changed yesterday A 96 tokens

c4-model

4781

zekiriabd/SDD-Pro

Skill Claude CodeCodex

Interactively co-build a software architecture using Simon Brown's C4 model (Context, Container, Component, Code). The skill detects the usage mode (greenfield design, retro-documenting from code or prose, review/explanation, update), runs a structured framing dialogue, proposes incremental drafts, and iterates until…

not rated 193 12d ago A SkillSpector: warn 198 tokens original Apache-2.0

dataseo-seo-research

4782

egebese/dataseo-mcp

Skill Claude CodeCodex

Use DataSEO MCP for SEO research workflows including backlink analysis, keyword research, traffic checks, domain comparison, backlink opportunity discovery, AI search query planning, and SEO content briefs. Use this whenever the user asks to investigate a domain, compare competitors, plan SEO content, find backlink…

not rated 192 +1 2mo ago A 76 tokens

vibegit

4783

memovai/memov

Plugin Claude Code

Bundles 1 skill · 0 tokens together

AI-assisted version control using Memov. Automatically record prompts, responses, and code changes. View history, search semantically, and time-travel through your AI coding sessions.

not rated 192 +1 7mo ago A tokens not measured original MIT

release

4784

alexeykrol/claude-code-starter

Command Claude Code

A command for creating a release of the Claude Code Starter framework. A release is a prepared version of software that can be shared or deployed.

not rated 192 1mo ago A 12 tokens

context-sync

4785

Intina47/context-sync

MCP server Claude CodeCodexCursor +2

Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more. Runs locally from the @context-sync/server npm package.

not rated 192 +1 5mo ago A tokens not measured original MIT

drizzle-v1

4786

zhe-qi/clhoria-template

Skill Claude Code

A guide to using Drizzle ORM v1, a TypeScript tool for working with databases, to define and query links between tables. It covers the newer Relations Query v2 style and moving from older Drizzle versions.

not rated 192 +2 1mo ago A SkillSpector: pass 48 tokens original MIT

usage-limit-reducer

4787

Dubibubii/usage-limit-reducer

Skill Claude CodeCodex

Use when the user is hitting Claude usage limits, burning through tokens fast, running a long conversation, or asks how to use Claude Code more efficiently. Triggers on phrases like "hit my limit", "running out of tokens", "usage limit", "save tokens", "reduce usage", "am I wasting tokens", "this chat is getting…

not rated 192 +5 4mo ago C 115 tokens

openclaw

4788

dddabtc/winremote-mcp

Skill Claude CodeCodex

Control a Windows machine remotely via MCP protocol. 40 tools for desktop automation, system management, file operations, and more.

not rated 192 +1 1mo ago A SkillSpector: pass 0 tokens original MIT

soloncode-skin-skill

4789

opensolon/soloncode

Skill Claude CodeCodex

A tool that packages a visual theme for SolonCode Web UI as an installable ZIP file. SolonCode is a web-based coding interface, and a skin changes its colors, backgrounds, and overall appearance.

not rated 192 +1 today A SkillSpector: pass 78 tokens original MIT

squid

4790

iusztinpaul/squid

Plugin Claude Code

Bundles 15 skills, 5 agents · 915 tokens together

Opinionated engineering agent team with progressive-disclosure specs for Python / TypeScript / Go monorepos. Ships PA / SWE / Tester / PR Reviewer / On-Call sub-agents, /squid-plan / /squid-implement-task / /squid-implement-night pipelines, and a library of language/framework/infra specs that agents load on-demand.

not rated 192 +3 changed 10d ago A tokens not measured original Apache-2.0

zach-product-research

4791

zach22-1999/amazon-skills

Skill Claude Code

A Sorftime-based product research skill for finding Amazon market opportunities and deciding whether a new product is worth pursuing. Sorftime is a market-research data source for Amazon sellers.

not rated 192 +7 26d ago A SkillSpector: pass 89 tokens original MIT

mcp-slim-guard

4792

lennney/mcp-slim-guard

MCP server Claude CodeCodexCursor +2

76% fewer MCP tokens in our standard benchmark. Same upstream call. Exact recovery. Runs locally from the mcp-slim-guard npm package.

not rated 192 1mo ago A tokens not measured original MIT

blender-skills

4793

arjun988/blender-skills

Plugin Claude Code

Bundles 58 skills · 1,973 tokens together

Blender Skills pack with 94 specialized skills for technical art, genre/style direction, modeling, VFX, engine export, and Blender MCP production workflows.

not rated 192 +13 2mo ago A tokens not measured original MIT

mcp-server

4794

railwayapp/railway-mcp-server

MCP server Claude CodeCodexCursor +2

Official Railway MCP server. Runs locally from the @railway/mcp-server npm package.

not rated 192 3mo ago A tokens not measured original MIT archived

code-agent

4796

aws-samples/sample-strands-agent-with-agentcore

Skill Claude CodeCodex ✓ vendor

Autonomous coding agent. Delegate any task that involves understanding, writing, or running code — from a GitHub issue, a bug report, or a user request. It explores, implements, and verifies on its own.

not rated 191 yesterday A SkillSpector: warn 47 tokens original MIT

piyaz

4797

FrkAk/piyaz

Skill Claude CodeCodex

Use when the user wants to plan, decompose, track, or resume a multi-task project: scoping a new idea, importing or onboarding an existing repo or workspace, asking what to work on / what's next / what's blocked / where they left off, reporting task completion, dispatching work in parallel, or planning a draft task.…

not rated 191 +1 yesterday A 155 tokens AGPL-3.0

vault-setup

4798

earlyaidopters/second-brain

Skill Claude CodeCodex

Interactive Obsidian vault configurator. Asks the user to describe themselves in free text, then builds a personalized vault structure, CLAUDE.md, and slash commands directly in the current directory.

not rated 191 +1 6mo ago A 44 tokens

experiment-agent

4799

Imbad0202/experiment-agent

Skill Claude CodeCodex

Experiment executor and monitor for academic research. 2-agent system covering code experiments (ML training, statistical analysis, ETL, simulation) and human studies (surveys, field studies, interviews). 4 modes: run (execute + monitor code), manage (track human studies), validate (statistical interpretation +…

not rated 191 +3 4mo ago C 143 tokens

taiwan-legal-db

4800

lawchat-oss/mcp-taiwan-legal-db

MCP server Claude CodeCodexCursor +2

MCP server "taiwan-legal-db" as configured in lawchat-oss/mcp-taiwan-legal-db. Runs mcp_server.server with .venv/bin/python.

not rated 191 +2 yesterday A tokens not measured 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: