Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 375,367 indexed, measured the same four ways as everything else here.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
A tool for creating educational comics, including biography and tutorial comics. It supports different visual styles and plans comics as sequences of panels before generating the images.
A CapCut editing procedure that finds silent sections in a source video and cuts them from an existing CapCut project. CapCut is desktop video-editing software; the procedure also creates peak or applause candidates and a cut report.
Explore multiple strategies without consequences. Fork the workspace into parallel copy-on-write branches, run speculative attempts in each, commit the winner, and abort the rest — instantly.
A procedure for generating high-fidelity HTML prototypes of mobile app screens from a product requirements document or app idea. A prototype is an interactive model used to visualise how a product may work.
Set up an agent on web0 in one call. Tell it your payout wallet, the services you want to sell, and (optionally) a .null name — it returns a complete, validated setup your agent can act on immediately.
Distill any book into an executable Claude Code skill pack. Evaluates skillability, generates structured skills with modules/templates/examples, and supports multi-book synthesis. Use when you want to turn a book's methods into repeatable, actionable skills.
Implements a book order system with a Vite React storefront (React Router, TanStack Query) and an Express + Prisma + SQLite API: default pay-by-transfer flow with admin-reviewed payment proof, Cloudflare Turnstile on order submit, honeypot field, payment-proof upload with duplicate-image detection, 8-character receipt…
Create Harvard Business School-style case studies on financial market events, products, or investment decisions. Use when the user wants to write a teaching case about a financial event, market phenomenon, investment product, or corporate decision. Triggers on requests like "write a case about X", "create an HBS case…
Save a work checkpoint to preserve context for multi-session projects. Use when pausing work on a feature, completing a milestone, or before ending a session.
Add structured block comments to every significant code change documenting what was done, why, when, and related context. Use when writing new functions, refactoring existing code, adding features, or making any non-trivial modification. Activates automatically on code edits.
jusTokenMax — token-reduction toolkit for Claude Code. Compresses attachments (PDF→Markdown, images), verbose logs, and provides a code symbol index plus chat-branching workflows so the agent reads and writes fewer tokens.
A workflow for turning rough requirements, product documents, or competitor research into a concise product brief for coding agents such as Claude Code, Codex, or Cursor. It includes features, technical choices, prototypes, details, and testable acceptance criteria.
Use when building Slack agents/bots with eve (Vercel's filesystem-first agent framework), @vercel/connect, or eve/channels/slack. Covers defineAgent/defineTool patterns, Vercel Connect credential brokering, Slack channel setup, testing requirements, and quality standards.
Opt-in Ming-dynasty "imperial court" vibe-coding protocol for Codex & Claude Code. Use ONLY when the user explicitly says "Great Ming" or "登基" (first-time onboarding), or when the repo's AGENTS.md explicitly requests this style.
Persistent structured memory + telemetry + audit trail for Claude Code sessions. Use when the user wants automated capture, durable context, and standardized turn-by-turn logging.
★not rated 22 8mo agoA34 tokens
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: