Ferramentas

A complete development methodology for coding agents: brainstorm to clarify requirements, write an implementation plan, then build with subagents, with red-green TDD, systematic debugging and code review throughout. In the official Claude Code and Codex marketplaces.

From Microsoft: converts PDF, Word, Excel, PowerPoint, HTML and other files or URLs to Markdown so agents can read and search them. A single convert_to_markdown tool over STDIO or local HTTP.

Converts PDF, Word, Excel, PowerPoint, HTML, images, audio and more into Markdown that keeps headings, lists and tables, ready for LLMs to read and analyze. Maintained by Microsoft; requires Python 3.10+.

Download and run open models such as Gemma locally with one command. Provides a REST API and Python/JS libraries, and ollama launch can point Claude Code, Codex and other agents at local models.

Guides the agent through writing or improving a skill: clarify intent, draft SKILL.md, run scored evals with and without the skill, then tune the description so it triggers accurately. Official Anthropic skill.

Reviews pull requests with several parallel subagents, scores each finding by confidence to filter out false positives, and can post the results as PR comments. Official Anthropic plugin; requires a logged-in GitHub CLI.

Open-source browser agent project. Its browser-use CLI lets Claude Code, Codex and other agents drive your logged-in local Chrome with Python snippets, or connect to a cloud browser; also ships a Python agent library. The cloud browser needs an API key.

Controls your local Chrome over CDP to navigate, click, type, take screenshots and scrape data, reusing logged-in sessions. Official browser-use skill; install the browser-use CLI with uv first.

Gives agents long-term memory across sessions with a local knowledge graph of entities, relations and observations, stored in a local JSONL file you can query and edit. Official MCP reference implementation.

Injects up-to-date, version-specific docs and code examples for libraries and frameworks into the agent's context, so it stops using outdated or invented APIs. By Upstash; works anonymously, and a free API key raises the limits.

166 research skills maintained by K-Dense (formerly Claude Scientific Skills), spanning bioinformatics, cheminformatics, clinical research, materials and physics, including unified access to 78 public databases such as PubChem and UniProt. Works with Claude Code, Codex and Cursor.

Orchestrates subagents in-session to map the architecture, build a threat model and hunt for vulnerabilities. Every finding is independently verified before it goes in the report, which also comes as SARIF, and optional patch files are left for you to apply. Official Anthropic plugin.

Lets agents drive a real browser through the accessibility tree: navigate, click, fill forms and take screenshots, without needing a vision model. Maintained by Microsoft.

Skills from security firm Trail of Bits: 40+ plugins for code auditing, CodeQL and Semgrep static analysis, differential review, smart-contract and cryptography audits, fuzzing and more. Also installable as a Claude Code or Codex plugin marketplace.

Figma's official remote MCP: hands components, variables and layout from your designs to the agent to generate code, and can create and edit designs on the canvas. Needs Figma sign-in; Starter plans and View or Collab seats get only 6 read calls a month.

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.

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.

A complete harness for coding agents: dozens of subagents, nearly 300 skills, hooks, rules, memory and continuous learning, plus the AgentShield security scanner. Built mainly for Claude Code, with Codex support.

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.

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.

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.

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.

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.

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.