Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 390,083 indexed, measured the same four ways as everything else here.
Scheduled KB maintenance — ingest meetings and Claude Code/Codex JSONL sessions, synthesize raw notes into existing topical docs (decisions, people changes, conventions), resolve conflicts, age out stale entries, fix frontmatter and links. Translates raw data into knowledge. Runs unattended; never asks for…
Create, update, export, and apply BlueKiwi design systems from the registry through MCP tools. Use when the user says "/bk-design", asks to create a design system, apply a registered design system, export a design system skill, or update brand/design tokens in BlueKiwi.
Collaborative ghostwriting for founders and experts. Extracts first-hand knowledge through structured interviews and transforms it into authentic, non-AI-sounding content. Use when user wants to write thought leadership, blog posts, founder stories, comparison pages, or says things like "help me write", "make this…
Skill "<kebab-case-name>" from jarvis823/skill-forge, covering when to invoke, what this repo does, house conventions (do this), code example from this repo and known drift (don't copy these).
Migra workflows de n8n/Make al ecosistema Claude Code. Analiza JSONs, mapea nodos, propone implementacion (skills, crons, web apps, dashboards) y detecta mejoras. Usa cuando el usuario pegue un JSON de n8n o mencione migrar automatizaciones.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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.
Detects correction or long-term note-taking scenarios, runs lightweight scholar preflight on fresh tasks, keeps the agent in an explicit closed loop until the user confirms completion, escalates into Ascended Mode after repeated failed corrections or manual trigger, archives detailed mistake / note entries into pro.
★not rated 23 6mo agoA
tokens not measured
originalMIT
Loop Review is a periodic quality audit of the KitchenLoop's recent output. It reads experience reports, inspects merged PRs and their code changes, optionally runs external auditors (Codex, Gemini), and produces a durable synthesis report with findings categorized by severity.
Use when a codebase has structural problems requiring systematic analysis before any changes — competing implementations, god modules, unclear boundaries, or deep technical debt. Trigger on: "refactor this service", "overhaul this legacy system", "too much technical debt", "architectural migration". Not for tactical…
A Chinese-language go-to-market guide for consumer electronics and cross-border e-commerce. Go-to-market work covers how a product is selected, priced, positioned, launched, sold, supplied, and eventually retired.
Use AgentDraw when the user wants to create a local editable diagram or visual explanation from a prompt, article, document, technical note, or review brief. Best for Mermaid-supported structured diagrams such as flowcharts/sequence/class/state diagrams, and SVG-based explanatory visuals such as article images…
A Chinese-language interactive story and chat skill based on the Overwatch character 小朱诺诺. It can start a dating-game-style story or a direct conversation.
Use this skill whenever the user asks to read, parse, or process one or more PDF files (.pdf). It converts the PDFs into Markdown using the MinerU (TextIn) API to handle long contexts, text, images, and tables perfectly, and then reads the resulting Markdown to fulfill the user's request. It also supports processing…
Expert Caido plugin development with comprehensive SDK documentation.
★not rated 23 11mo agoA
tokens not measured
originalCC0-1.0
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: