Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 378,676 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Clone repos using bare clones + git worktrees, develop changes, deliver via Pull Requests. Use this skill whenever the user asks you to clone, code, fix, edit, refactor, implement a feature, or open a PR on any repository — including PT-BR phrasings like "clonar repo", "refatorar", "abrir PR", "corrigir bug"…
vanzan01/claude-agent-sdk-starter
Skill Claude Code
Utilities for fetching and structuring AI news items for multi-agent pipelines. Use when gathering AI headlines, analyzing news, or crafting tweets in the ai-news-tweet app.
Skill Claude Code
End-to-end workflow for shipping a GitHub issue. Assesses complexity, builds a tailored workflow, and orchestrates skills from research through PR.
MCP server Claude CodeCodexCursor +2
An MCP server utilizing Zoo's various tools. Runs locally from the zoo_mcp Python package. Needs 1 environment variable to run.
eranshir/personal-voice-capture
Plugin Claude Code
Bundles 1 skill · 37 tokens together
A meta-skill that learns a person's writing voice from their own samples and iterative edits, then compiles it into a durable, reusable voice skill for future agents.
Skill Claude Code
Run the project's validation (/check), and on green stage + commit your changes using the project's /commit conventions; on red, report a blocker and note the Queen without committing. Use when the user asks to checkpoint, save progress, or commit safely mid-task.
MCP server Claude CodeCodexCursor +2
Scan, protect, and monitor APIs from AI coding tools. Device-level rate limiting. Runs locally from the scopeblind-mcp npm package.
carloscrcalderon/mcp_transporte_bogota
MCP server Claude CodeCodexCursor +2
MCP server "transporter-cc-mcp" as configured in carloscrcalderon/mcptransportebogota. Runs locally from the transporter-cc-mcp Python package.
MCP server Claude CodeCodexCursor +2
The trust and intelligence layer between AI agents and your database. Runs locally from the schemabrain Python package. Needs 1 environment variable to run.
BloomFilter-Labs/mcp-server-bloomfilter
MCP server Claude CodeCodexCursor +2
Service that lets AI Agents search, register, and configure domains. Runs locally from the @bloomfilter/mcp-server npm package. Needs 3 environment variables to run.
Skill Claude CodeCodex
Author, validate, test, deploy, inspect, roll out, and troubleshoot declarative services on Orion using orion-server and orion-cli. Use for Orion workflows, channels, connectors, packages, traces, or runtime operations; do not use for unrelated products also named Orion.
MCP server Claude CodeCodexCursor +2
Codebase memory for AI agents: an AST index plus agent-written notes that self-stale. Runs locally from the @cstart/coldstart npm package.
MCP server Claude CodeCodexCursor +2
Write-capable PDF toolkit MCP: 22 tools to read, create, render, encrypt, merge & fill PDFs. Runs locally from the @aryanbv/pdf-toolkit-mcp npm package.
Plugin Claude Code
Bundles 41 skills, 44 commands, 5 agents, 4 hooks · 3,458 tokens together
The /flow engine — one unified, PM-agnostic workflow system spanning capture → done. Manual stages and an autonomous loop seated on DorkOS Pulse.
Skill Claude CodeCodex
Use this skill to process one to 99 local exact 2:1 equirectangular panorama images with Realsee Argus, producing depth maps, a merged GLB point cloud, camera poses, optional intrinsics, and a validated local output index. Trigger for Argus panorama reconstruction, Argus ZIP input, or explicit Argus…
Command Claude Code
Release the hub last, after every sub-app is released and on npm; tag, GitHub release, CI publishes.
maxschottke-spec/seo-survival-kit
Plugin Claude Code
Bundles 18 skills, 6 commands · 2,412 tokens together
SEO recovery skills + orchestrator. Type /seo-rescue:rescue for the routing table. NEW in v0.5.4: Recovery Hardening — spec/schema/script reconciliation (score engine now matches its spec), stage state machine + quiet-death detection + pre-hit baseline selection (experimental N=1), knocking-at-the-door cohort finder…
Plugin Claude Code
D&D 5e game engine for Claude Code.
MetaBrain-Labs/ComfyUI-MCP-Server-TypeScript
Skill Claude CodeCodex
Enables AI agents to discover, inspect, and execute ComfyUI workflows for image and video generation through a structured MCP interface. Supports the full task lifecycle—from context loading and workflow discovery, to parameter mounting and task submission, and finally result retrieval and generated asset management.
geledek/enterprise-ai-transformation-skills
Plugin Claude Code
Bundles 16 skills · 2,364 tokens together
Sixteen installable skills for diagnosing, designing, governing, and scaling enterprise AI transformation. Distilled from 21 flagship sources (Stanford, MIT, McKinsey, BCG, Deloitte, PwC, Accenture, NIST, EU AI Act, IMDA, WEF).
Skill Claude CodeCodex
Provides base R programming guidance covering data structures, data wrangling, statistical modeling, visualization, and I/O — using only packages included in a standard R installation. Use when the user writes or debugs R scripts, works with vectors, matrices, lists, data frames, or factors, applies the apply family…
Skill Claude CodeCodex
Verifierar nya leverantörer, kunder eller samarbetspartners genom att kontrollera F-skattestatus hos Skatteverket, registreringsdata hos Bolagsverket, och eventuella betalningsanmärkningar via tillgängliga källor. Skydd mot att betala till bolag som tappat F-skatt (vilket gör dig skyldig för deras skatter och…
Skill Claude CodeCodex
A Chinese-language fitness coaching skill based on the free-exercise-db exercise knowledge base. It covers workout planning, exercise instruction, training-data analysis, nutrition guidance, and progression planning.
Plugin Claude Code
Bundles 21 skills, 5 agents, 1 hook · 1,388 tokens together
Scale-adaptive software development — TDD, verification, perspective-based review, interface design, and tool capabilities (browser automation, PDFs, YouTube transcripts, local-LLM and Codex delegation).
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: