Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 381,614 indexed, measured the same four ways as everything else here.
Model multiplexer: keep an expensive orchestrator (Fable) but route subagent work to the cheapest model that can do the job (Opus, Sonnet, Haiku, or external models via Codex/Gemini CLIs).
★not rated 4 2mo agoA
tokens not measured
originalMIT
GHE (GitHub-Elements) - Automated project management for Claude Code using GitHub Issues as persistent memory with orchestrated DEV/TEST/REVIEW workflow.
★not rated 4 10mo agoA
tokens not measured
originalMIT
A review framework for Chinese-equity research and investment memos intended for an investment committee, the group that assesses proposed trades. It adds checks for sources, calculations, scenarios and conditions that could change the recommendation.
Semantic knowledge extraction and context enrichment for Claude Code - automatically analyzes codebases to provide intelligent coding context, architectural boundaries, and guardrails.
★not rated 4 8mo agoA
tokens not measured
originalApache-2.0
The heaviest command. Ingests Linear + Git across all configured repos + Slack (channels + DMs) — plus optional Notion and Intercom if your team uses them — deduplicates, and writes the consolidated state back into Linear (creating missing issues, updating statuses, reassigning based on git authorship). Then produces…
Standardizes Flutter UI reproduction from Figma designs. Provides a main orchestrator skill (5-phase workflow) and tool skills for token alignment, layout translation, asset handling, state scaffolding, and pixel-level visual verification.
Audit any repo for security holes — a web/app project, a Claude skill, a Claude Code plugin, an MCP server, or an agent. Catches the glaring stuff (exposed servicerole keys, RLS off, committed .env, secrets in the client bundle, allow read,write: if true) and the subtle stuff (IDOR, SSRF, prompt injection in a…
Opinionated design leadership in your terminal. 7 agents and 17 skills grounded in cognitive psychology, real research, and business outcomes. Built by a design leader, not a framework.
Spec-driven worldbuilding plugin. Eight commands guide you from emotional seed to stress-tested world bible — interviewing, researching, locking decisions, generating concept art, and writing to your vault.
This skill provides comprehensive WordPress development expertise including self-hosted setup with Docker and Nginx, theme development (block and classic), plugin development with security best practices, performance optimization, and security hardening. Use this skill when setting up WordPress environments…
137 episodes of Huberman Lab turned into an interactive health and science coach. 12 decision-making and tutor skills, 50+ protocol and framework guides, and 137 searchable transcripts — all from Andrew Huberman, PhD and guests including Matthew Walker, Anna Lembke, Peter Attia, Andy Galpin, and Robert Sapolsky.
Expert agent for creating comprehensive Architectural Decision Records (ADRs) with structured formatting optimized for AI consumption and human readability.
Assess AI-assisted delivery capability against a security-gated checklist; compute a gamified 0-100 Insight Score with run-over-run deltas and generate a project-anchored learning plan plus a coach-style HTML+MD report.
Use PROACTIVELY when user mentions: review, code review, audit, quality, assess, evaluate, critique, feedback, score, rate, check my code, how does this look, is this good, technical debt, code smell, best practices, clean code, code quality, maintainability, refactor review, PR review, pull request, merge request…
Omnimodal plugin for Claude Code: recognize and generate images, video, and audio through Qwen, Z.AI, or OpenAI-compatible APIs.
★not rated 4 9d agoA
tokens not measured
originalMIT
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: