Herramientas

Anthropic's reference implementation for finding and fixing vulnerabilities: Claude Code skills for threat modeling, static scanning, triage and patching, plus an autonomous recon-to-patch pipeline (C/C++ memory bugs by default; needs Docker and gVisor). No longer maintained.

Command-line email client supporting IMAP, SMTP, JMAP, Gmail and Microsoft Graph, with multiple accounts and --json output, so agents can check, search, compose and send mail. A first-run wizard auto-detects your mailbox settings.

Open-source LLM evaluation platform: one opencompass command picks the model and datasets and runs the evaluation across hundreds of benchmarks. Works with local Hugging Face models and API models, with vLLM and LMDeploy for faster inference.

Hands your current browser session to the agent through a Chrome extension: read console logs and network requests, take screenshots, and run Lighthouse performance, accessibility and SEO audits without signing in again.

Converts and two-way syncs Jupyter notebooks with plain Python scripts or Markdown, so agents can edit research and teaching notebooks like ordinary text and diffs stay readable. Needs a local Python environment; install with pip.

Cleans a LaTeX project before arXiv submission: removes comments, auxiliary files and unused .tex files and images, and can compress images, so internal notes are not published with the source. From Google Research; installable with Homebrew on macOS.

Python library and CLI for extracting main web content: fetches pages, crawls via sitemaps and RSS feeds, strips headers, footers and other noise, and outputs TXT, Markdown, JSON, XML and more with metadata. Also processes downloaded HTML offline.

Anthropic's official OS-level sandbox CLI: restricts file and network access for agents, MCP servers and any command without containers, using sandbox-exec on macOS and bubblewrap on Linux. Currently a research preview.

Static security analysis for CI/CD config: finds template injection, credential leaks, excessive permissions and more in GitHub Actions workflows, also covers Dependabot and pre-commit configs, and auto-fixes some findings.

Lets coding agents control real Chrome with short Puppeteer scripts, with named pages that keep state across calls, accessibility-tree snapshots and screenshots for self-testing web changes. Install the dev-browser CLI globally first; macOS and glibc Linux only.

Lets agents build, run, test and debug iOS and macOS projects and control simulators and physical devices, with a CLI mode too. Formerly XcodeBuildMCP, now maintained by Sentry; macOS only, requires Xcode 16 or later.

Veteran suite of CSV command-line tools: in2csv converts Excel and JSON to CSV, csvcut, csvgrep and csvsort filter and sort, csvstat computes statistics, and csvsql runs SQL directly against CSV files.

Google's official skills for building ADK agents: dev workflow, scaffolding, the ADK Python API, evaluation with LLM judges and adaptive rubrics, deployment to Agent Runtime, Cloud Run or GKE, publishing and observability. Works with agents-cli; local dev needs only an AI Studio key.

250+ MCP tools for Ghidra: decompilation, cross-references, data-flow analysis, bulk renaming and commenting, P-code emulation and live debugging, with headless mode support. Requires Java 21 and Ghidra 12.1, and the plugin must be built and deployed first.

Language and toolset for double-entry bookkeeping in text files: bean-check validates the ledger, bean-format normalizes it, and Fava or beanquery handle reports and queries. Plain-text ledgers are easy for agents to generate and keep in version control.

Veteran command-line task manager with projects, tags, priorities, due dates and custom reports, JSON export, and a rich ecosystem of hooks and extensions, well suited for agents that record and track tasks.

Community-maintained MCP for Jira and Confluence: search with JQL/CQL and create or update issues, pages and comments. Supports both Cloud and Server/Data Center deployments; needs an API token or personal access token.

The .NET team's official skill collection, grouped into plugins: ASP.NET Core, Blazor, MAUI, EF Core data access, MSBuild troubleshooting, performance diagnostics, testing, and framework upgrades and migrations. Maintained by Microsoft; install via the Claude Code or Codex plugin marketplace.

Full-featured Jira CLI: filter, create, transition, assign and link issues and manage epics and sprints, with --plain text output that agents can read. Works with Cloud and self-hosted Jira; set up an API token and run jira init.

Classic plain-text double-entry accounting CLI: entries live in a text file and it produces balance, register, budget and other reports directly, with no database or hidden state, so agents can easily read and write ledgers, reconcile and report.

Reference for Vitest 5: config, CLI, the test, describe and expect APIs, hooks, mocking with vi, snapshots, coverage, fixtures, concurrency, filtering and tags, reporters, benchmarks, test environments, type testing and multi-project setups. Generated by Anthony Fu from the official docs.

Semi-automated research workflow for computer science and AI researchers: ideation, Zotero literature management, experiment analysis and reports, paper writing and polishing, and rebuttals, with optional Obsidian knowledge base. 40+ skills; also installable as a Claude Code plugin.

Semi-automated research assistant for CS and AI researchers that links ideation, Zotero literature management, experiment analysis and reporting, paper writing and reviewer responses, and keeps project knowledge in Obsidian. Branches for Codex and other agents exist.

12 LinkedIn writing skills: write posts, comments and replies in your voice without AI tone, plan a week of content and rewrite your profile, waiting for your confirmation before each post. Produces copy-paste drafts by default; optional Apify (reading posts) and Publora (auto-publish) API keys.