도구

Has the agent commit to a visual direction before building or redesigning an interface, making deliberate choices on color, type and layout instead of generic, templated AI UI. Official Anthropic skill.

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.

Has the agent settle on a clear aesthetic direction first, then write distinctive, production-ready frontend interfaces that avoid the generic AI look. Official Anthropic plugin.

Anthropic's terminal coding agent: understands your codebase, edits code, runs commands and handles git workflows, with plugins, MCP and a headless mode (claude -p). Sign in with a Claude account or set an API key.

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.

Builds multi-component web pages that need state or routing with React, Tailwind CSS and shadcn/ui, using bundled init and build scripts, then packs them into a single HTML file for a claude.ai Artifact. Official Anthropic skill.

Creates, edits and analyzes Excel spreadsheets: formulas, formatting, charts and data cleaning, plus conversion between CSV, TSV and other tabular formats. The official Anthropic skill behind Claude's document features; source-available, not open source.

Guides users through co-writing proposals, technical specs and decision docs in three stages: gather context, refine section by section, then test with a fresh session that lacks the context to catch what readers won't understand. 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.

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.

Recreates the deprecated Explanatory output style with a SessionStart hook: adds Insight notes before and after code that explain implementation trade-offs and codebase conventions. Official Anthropic plugin; uses extra tokens.

Learning mode: at key decision points such as business logic or error handling, asks you to write 5-10 lines of code yourself while explaining the trade-offs. Official Anthropic plugin built on a SessionStart hook; uses extra tokens.

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.

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.

A seven-phase feature development workflow: clarify requirements, explore the codebase with parallel subagents, design the architecture, implement, then run a quality review. Start it with /feature-dev. 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.

Git commit commands: /commit writes messages in the repo's style, /commit-push-pr branches, commits, pushes and opens a PR in one step (needs the gh CLI), and /clean_gone removes local branches deleted on the remote. Official Anthropic plugin.

Connects Claude Code to gopls, Go's official language server, for code intelligence, refactoring and analysis. Install gopls with go install and add Go's bin directory to PATH first. Official Anthropic plugin.

Connects Claude Code to Shopify's Ruby LSP for code intelligence and analysis of .rb, .rake, .gemspec, .erb and other files. Needs Ruby 3.0+; run gem install ruby-lsp first. Official Anthropic plugin.

Anthropic's official Telegram channel plugin (research preview): connects a Telegram bot to a running Claude Code session so you can message the agent and get replies from your phone, with pairing and allowlist access control. Needs Bun and a BotFather token; launch with --channels.

Creates or improves Agent Skills from scratch: writes eval cases to test them, runs benchmarks with variance analysis, and tunes descriptions for more accurate triggering. Maintained by Anthropic.