도구

Guides you through creating a plugin from scratch or customizing an existing plugin's connectors, skills and settings for your team's tools and workflows, producing an installable plugin package. Maintained by Anthropic; runs in Cowork mode in the Claude desktop app.

Support for small merchants: reads customer emails, checks orders and refunds in Stripe, PayPal, Square or Shopify, and drafts replies in the owner's voice per your refund policy; can refund via Stripe or Square after explicit approval. Works with pasted emails too. Official from Anthropic.

All-in-one plugin for small business owners: 44 skills covering cash flow and bookkeeping, collections and taxes, customer acquisition and marketing, customer feedback, inventory, hiring and contract review. Anything touching money or customers needs your approval. Official from Anthropic.

Generates a full campaign plan from a marketing goal: objectives, audience, key messages, channel strategy, a week-by-week content calendar and success metrics, plus budget allocation if you give a budget. Suited to launches, acquisition and brand campaigns. From Anthropic's marketing plugin.

Generates project or team status reports with an executive summary, overall red/yellow/green status, key metrics, risks and open decisions, turning scattered project tool activity into a report for leadership. From Anthropic's official operations plugin.

Anthropic's official business operations plugin: vendor evaluations, process docs (flowcharts, RACI, SOPs), change requests, capacity planning, status reports and runbooks. Works without external tools and does more with ITSM and project management tools connected.

Compliance skill from Anthropic's official operations plugin: maps controls, owners and evidence for SOC 2, ISO 27001, GDPR, HIPAA and PCI DSS, schedules audits, runs gap analyses, and outputs audit-readiness checklists and evidence collection plans. Have legal or compliance experts review.

Designs multi-email marketing sequences for onboarding, lead nurturing, win-back and launches, with full copy for each email, timing, branches and exit conditions, benchmarks and A/B test ideas. No email tool required. Part of Anthropic's official marketing plugin.

Everyday software engineering plugin: standup summaries, code review, structured debugging, architecture decision records, incident response and pre-deploy checks. Official from Anthropic, built mainly for Cowork but also usable in Claude Code.

Collects reviews and complaints from Google, Yelp, Facebook and more, groups them by theme with quotes, and drafts replies in the owner's voice that post only after approval; also finds lapsed customers and drafts win-back messages. Official Anthropic small-business plugin.

Turns processes that live in people's heads into SOPs: flowcharts, a RACI matrix (responsible, accountable, consulted, informed), detailed steps and exceptions, ready for handoffs, audits and onboarding. Describe the process or paste existing notes. Official from Anthropic.

Calls Codex from Claude Code for read-only or adversarial code reviews, or delegates tasks to Codex to run in the background. Maintained by OpenAI; needs a ChatGPT account (the free tier works) or an API key.

React and Next.js performance rules from Vercel's engineering team: 70 rules ranked by impact covering request waterfalls, bundle size, server performance and re-renders, for writing, reviewing and refactoring. Maintained by Vercel.

Vercel's official skill that pulls the 80+ rules of Vercel's writing handbook online to review docs and copy for voice, structure, content types, code examples and formatting, listing issues as file:line.

Vercel's guide to React composition patterns: replaces boolean prop sprawl with compound components, lifted state and clean Context interfaces, including React 19 API changes. Useful for refactoring component libraries and reviewing component architecture.

Vercel's official cost and performance skill: gathers production metrics, usage and project config, investigates only the routes and files the metrics point to, and returns ranked, doc-backed recommendations. Supports Next.js, SvelteKit and Nuxt; needs Vercel CLI v53+ logged in and linked.

Runs commands and scripts in a sandbox, indexes large tool outputs for full-text search and returns only results to the context window to save tokens; after compaction it can retrieve edits and task state. Supports Claude Code, Codex and more. Needs Node.js 22.5+.

Vercel's official deployment skill: checks the git remote, project link and CLI login, then deploys a preview (default) or production via git push or vercel deploy. When login isn't possible in a sandbox, it can create a claimable preview link.

Processes large tool outputs in a sandbox and returns only the results to context; logs session events in SQLite with FTS5 so work continues after context compaction. Supports Claude Code, Codex and a dozen other clients. ELv2 licensed.

Adds a workflow layer to OpenAI's Codex CLI: requirement clarification, plan review, persistent goals, parallel multi-agent teams and tmux session management, with project state in .omx/ and a bundled Codex plugin. Community project; needs a signed-in Codex CLI, macOS or Linux recommended.

Installs ready-made subagents, slash commands, hooks, MCP configs and skills for Claude Code with one npx command, browsable online at aitmpl.com. Also includes session analytics, health checks and other helpers.

Daemonless, rootless container and pod manager with a Docker-compatible CLI for building, running and pushing OCI images. On macOS and Windows it runs inside a podman machine VM.

Runs the cognee memory engine as an MCP server whose remember, recall and forget tools write documents and conversations into a knowledge graph and vector store for cross-session retrieval. Start it with Docker or uv first; needs an LLM API key by default, or connect to Cognee Cloud.

Fast vulnerability scanner driven by YAML templates: uses a community template library to detect known vulnerabilities over HTTP, DNS, TCP, SSL and more, supports custom templates and plugs into CI/CD. Use only on targets you're authorized to test.