Audit a codebase for handcrafted code that duplicates functionality already available in the project's dependencies. Reads package.json, launches parallel exploration agents, verifies replacement feasibility, and produces a structured refactor plan. Audit only -- does not execute changes.
Run the marketplace validation script to check plugin integrity. Use when finishing plugin work, after adding or modifying plugins, or before committing plugin changes.
Use when the user asks for an extensive, maximum-quality, whole-codebase review or audit and wants a consolidated findings report (read-only, default). Add --autopilot to run a fully autonomous performance pipeline: read Supabase signals, deep-dive via dynamic workflows, refine fixes with a headless Codex pass, apply…
Python data validation using type hints and runtime type checking with Pydantic v2's Rust-powered core for high-performance validation in FastAPI, Django, and configuration management. Use when working with API request/response validation, settings management, ORM model validation, data parsing and serialization, or…
Audits Claude Code context consumption across agents, skills, commands, hooks, MCP servers, and the CLAUDE.md/MEMORY chain. Identifies bloat and redundancy, then produces prioritized token-savings recommendations. Backs the /context-budget command.
SEO audit and implementation specialist for Next.js, Remix, and React SPAs. Use this skill whenever the user mentions SEO, meta tags, structured data, sitemaps, robots.txt, Open Graph, Twitter cards, JSON-LD, hreflang, image alt attributes, or crawlability. Also trigger when the user says their site doesn't rank…
Pre-install security advisor. Activate when the user mentions installing a Claude Code plugin, MCP server, or any third-party agent tool. Offer to run an Assay scan against the target before they install.
Modify an existing Claude Code skill to add Agent Junction awareness — registration, peer discovery, and message exchange. Injects junction blocks at appropriate points in the skill workflow. Primary use case is junction-enabling handover skills. Triggers on phrases like "inject junction", "junction-enable this…
A Chinese fortune-telling server covering birth-chart readings, divination, fortune slips, name scoring, name suggestions, and a programmer-themed almanac. It produces traditional ink-style HTML reports.
Generate AI music tracks via the Lacuna Music API. Use when the user wants AI-generated music, BGM, jingles, soundtrack stingers, lofi/synthwave/orchestral/any-genre tracks, vocal songs from custom lyrics, or any on-demand audio generation. Triggers on phrases like "generate music", "make me a track", "compose a…
Use for the user's personal learning record and coaching data managed by devcoach. Trigger when: (1) the user mentions devcoach in any form — setting it up, redoing onboarding, resetting topics, or reviewing/rebuilding their profile or notebook; (2) the user asks about their own learning or skill level — what they…
Use this skill when creating, redesigning, critiquing, reducing, polishing, hardening, or making design decisions for a user-facing interface, brand surface, product UI, component, dashboard, flow, app shell, onboarding, empty state, or visual system. Applies Mies van der Rohe-inspired restraint, the Interface Craft…
Use when testing or running an app while a VPN/proxy tunnel is up and the app's own outbound calls must leave via the real ISP connection instead of the tunnel - geo-locked or domestic APIs, payment/SMS gateways, bank endpoints, or any service that rejects the VPN's exit IP. Gives the app under test a LAN-direct…
Research, audit, optimize, and safely operate App Store advertising through apple-ads-mcp. Use for Apple Ads readiness, inventory, keyword opportunities, reports, named optimization policies, shared budgets, and explicitly authorized lifecycle changes; do not use for App Store Connect metadata or Apple Maps ads.
Orchestrate a software task end-to-end in Claude Code. Use this whenever the user describes building, fixing, reviewing, planning, or shipping something in a project — e.g. "build the X MVP", "add feature Y", "review this PR", "diagnose this bug", "plan this out" — and especially when resuming work after a context…
Create social media campaigns by scanning a project's brand identity, researching competitors, building strategy, and generating visual content with AI. Use when the user mentions social media, marketing, campaigns, brand content, Instagram/Twitter/LinkedIn/TikTok posts, content calendars, promotional visuals, product…
Write, review, and optimize professional prompts for large language models. Use this skill whenever the user asks to write, draft, design, improve, fix, debug, review, or optimize a prompt, system prompt, prompt template, meta-prompt, or agent instructions; asks why a prompt "isn't working" or gives inconsistent…
Connect Google's Chrome DevTools MCP to AdsPower antidetect browser profiles. This lets AI coding agents (Claude Code, Cursor, Codex CLI) control fingerprint-isolated browser sessions through natural language.
★not rated 4 3mo agoA0 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: