Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 388,436 indexed, measured the same four ways as everything else here.
Reviews written content (blog posts, articles, documentation, marketing copy) against a quality checklist and provides structured feedback. Use when the user asks to review, critique, edit, or improve any written content.
Alex Hormozi framework for creating lead magnets, free offers, CTAs, and trust funnels. Triggers on: create a lead magnet, free offer, mini offer, headline/name, CTA, engaged leads, funnel strategy, how do I get more leads, what should I give away.
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.
Generate on-brand paid-ad creative variations from your brand context plus cross-industry inspiration, with on-image CTA text rendered inline by an image-to-image model. Brand-agnostic — onboards new users via 7 conversational questions on first run, then reads voice/visual/playbook context from a workspace-local…
Given a seed paper, model, method, or architecture, trace and analyze what later research did with it — which papers cite it, which actually extend or improve on it versus merely mention it, and how the notable follow-ups compare. Use this whenever the user points at a specific paper/architecture/model (by name or…
Bootstrap and maintain the team's "GitHub issues as agent memory" pattern in a repo: one pinned "Project log" issue that is a numbered decision register + current-state summary any agent reads at session start, plus a session-start / session-end ritual and a small label vocabulary (decision, needs-decision…
Use Context Router when a task requires project context, feature-specific retrieval, memory recall, strict run workflow slices, or session continuation.
Analyze deal stage based on LaunchDarkly's Customer Engagement Process (CEP). Compares completed and missing activities against stage criteria to recommend the correct opportunity stage.
Install or maintain market-brief, a scheduled Codex/Claude task that scans Discord and WeChat investing chats, writes an hourly report, pushes it to WeChat, and optionally runs an inbound WeChat listener with MCP tools. Requires chatlog, wxstore, and discord-selfbot MCP servers.
Build an offline evaluation set so you can compare LLM prompts and models quantitatively. Invoke when building or iterating on any LLM-powered feature.
Senior VBA code review specialist. Use after writing or modifying VBA to review for security, quality, performance, and best practices before committing or releasing.
Quick honest terminal distribution plots (sparkline histogram + box-and-whisker) of numeric data. Use when the user wants a fast in-terminal look at the distribution/spread of some values (e.g. coherence/alignment scores across models) — "histogram of these", "show me the distribution", "plot these numbers", "box plot…
Main-agent planning trio (/ac:plan, /ac:execute, /ac:wisdom) with autonomous execution mode plus setup, init, commit commands and skill, agent, command, rule, CLAUDE.md creator skills. Two hooks back the workflow: SessionStart for twin-skill and resume, PreCompact for state preservation.
★not rated 2 6mo agoA
tokens not measured
originalMIT
Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md + experimentallog.md). TRIGGER when the user says…
Generate and maintain a comprehensive code-context.md file that captures deep codebase understanding — models, routes, components, stores, architecture, data flows, and key patterns. Commands - init, update, uninstall.
★not rated 2 6mo agoC44 tokens
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: