Tools

A disciplined process for hard bugs and performance regressions: build a reliable reproduction loop, reproduce and minimize, form hypotheses, instrument to verify, then fix and add a regression test, redacting secrets in output. By Matt Pocock.

Forces red-green-refactor: write a test and watch it fail, then write the minimum code to pass. Any code written without a verified failing test gets deleted and redone. From the Superpowers workflow.

Resolves subscription billing issues: checks customer and subscription state, separates duplicate purchases, team seats and failed payments, restores self-serve before refunding, and drafts the reply. Needs Stripe or similar tools connected; refunds move real money, so review them.

Self-improving agent from Nous Research with built-in memory and a learning loop that turns experience into skills. Works with any model provider; the hermes command has a terminal UI, and a gateway connects it to Telegram, Slack and more and runs scheduled tasks.

Writes internal communications in familiar company formats: 3P updates, leadership reports, project status updates, company newsletters, FAQs and incident reports. Official Anthropic skill.

After giving advice, a draft or a data analysis, adds 2-3 targeted follow-up questions that prompt the user to check key facts, test the reasoning and fill in missing context. Fires at most once per conversation. Official Anthropic skill.

Drives local web apps with Python Playwright scripts to verify features, debug the UI, take screenshots and read browser logs. Includes helper scripts to start and stop dev servers. Official Anthropic skill.

Guides agents in building quality MCP servers: research the protocol and target API, design tools, implement with Python (FastMCP) or the TypeScript SDK, and write evaluation questions to test the result. Official Anthropic skill.

Reference for the Claude API and Anthropic SDK: model selection and pricing, streaming, tool use, prompt caching, Managed Agents and more, plus workflows for model migration and prompt audits. Official Anthropic skill.

Creates, reads and edits PowerPoint decks: applies templates and layouts, handles speaker notes and comments, and merges or splits slides. The official Anthropic skill behind Claude's document features; source-available, not open source.

Official Claude Code plugin for the prompts.chat library: search prompts and Agent Skills from your coding assistant, fill in variables and improve prompts with AI. Includes commands, subagents and a remote MCP; saving your own prompts needs an API key.

Toolkit for building Claude Code plugins: 7 skills on plugin structure, hooks, MCP integration, commands, subagents and skill writing, a guided eight-phase create command, and subagents for agent generation, plugin validation and skill review. Maintained by Anthropic.

Generates hook rules from a one-line description or by analyzing recent conversations. Rules are Markdown files with match conditions that block or warn on dangerous commands and unwanted patterns, and take effect without a restart. Official Anthropic plugin.

Six specialized review subagents that check comment accuracy, test coverage, silent failures, type design, code style and simplification opportunities. Run them individually or all at once. Official Anthropic plugin.

Scaffolds a Claude Agent SDK project in Python or TypeScript interactively with /new-sdk-app, then a verifier agent checks dependencies, config and code against official best practices. Maintained by Anthropic.

UI design knowledge base skill: looks up UI styles, palettes, font pairings, charts and UX guidelines by product type and generates a full design system, covering 22 stacks including React, SwiftUI and Flutter. Needs Python 3 locally.

UI/UX design knowledge base plugin with searchable UI styles, color palettes, font pairings, charts and guidelines for 20+ tech stacks; generates complete design system recommendations by product type. Needs Python 3 installed locally.

Skill pack from YC president Garry Tan: slash commands such as /office-hours, /plan-ceo-review, /review, /qa and /ship play CEO, engineering manager, designer, QA and release engineer. Needs Git and Bun; clone the repo and run ./setup as the README describes.

YC office hours skill from gstack: startup mode tests real demand, the narrowest wedge and future fit with six probing questions; builder mode brainstorms side projects, hackathons and open source. Ends with a design doc. Maintained by Garry Tan.

Local LLM inference engine in plain C/C++ with a command-line chat and an OpenAI-compatible HTTP server; pulls and runs GGUF models straight from Hugging Face. Supports Apple Silicon, CUDA, Vulkan and other hardware, plus low-bit quantization.

Multi-agent investment research framework where fundamental, sentiment, news and technical analysts, bull and bear researchers, a trader and risk managers debate a stock and produce a report and rating. Covers US, Hong Kong and A-shares. Needs Python and an LLM API key; not investment advice.

Minimal, extensible terminal AI agent that can write its own prompt templates, skills, extensions and themes. Offers print, JSON and RPC modes for scripting, plus a TypeScript SDK. Needs Node.js 22.19+.

Local MCP server built into Browser Use: lets agents navigate, click, type and extract page content, or hand multi-step tasks to the built-in browser agent. Bring your own OpenAI or Anthropic API key.

For fuzzy requirements: the agent asks one question at a time with its own guess, clarifying users, motivation, success criteria and constraints, and restates the intent for your confirmation before planning. Needs you answering live, so not for unattended runs. From Addy Osmani's agent-skills.