도구

Applies Anthony Fu's conventions for JavaScript and TypeScript projects: file organization, explicit imports, Vitest style, @antfu/ni, @antfu/eslint-config with antislop, Knip, tsdown and a single ci script, mirroring the antfu/starter-ts template for new projects.

Reference for Nitro v3, the server toolkit behind Nuxt: file routes with H3 v2 handlers, route rules, caching, KV storage, tasks, WebSockets and OpenAPI, plus deploy presets and v2 migration notes. Generated by Anthony Fu from the official docs.

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.

Reference for pnpm 12: CLI, pnpm-workspace.yaml settings, monorepo workspaces, catalogs, overrides, patches, supply-chain settings such as build approval, task orchestration, CI setup and migration from npm, Yarn or older pnpm. Generated by Anthony Fu from the official docs.

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.

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.

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.

draw.io's official MCP: opens XML, CSV or Mermaid diagrams generated by the agent directly in the draw.io editor, good for flowcharts and architecture diagrams. A no-install remote version can also render diagrams inline in the chat.

Turns any codebase into an interactive browser course: real code with plain-language explanations, animations, hover glossaries and scenario quizzes. Built for people who build software with AI but can't read code, and useful for intro programming classes. Needs only an agent and the repo.

Turns a repeatable agent task into a repo-local skill plus a GitHub Actions workflow that runs a coding agent (Claude Code, Codex, OpenCode or CodeLayer) on a schedule, with a prompt, memory file and one-open-PR bound. Reads the repo first, then walks you through cadence, scope and validation.

Interviews you to design an agentic control loop for your codebase in control-theory terms: a set point, a sensor built from existing tooling, a controller that picks small low-risk changes, and a coding agent that opens PRs. Builds each part to run locally before wiring a scheduled CI workflow.

Explains the current topic visually with the smallest view that makes the point: pseudocode, call trees, component or file trees, Mermaid diagrams or diffs, and a focused HTML diagram or short deck when the idea is too dense. Invoked manually.

Rewrites a CLAUDE.md so Claude Code follows it better: keeps project identity and map bare at the top, wraps task-specific rules in narrowly conditioned <important if> blocks, cuts snippets and lint-enforceable rules, and keeps every command.

Creates or updates a pull request description that explains why the change exists in one sentence, flags up to three things to note, and outlines the implementation with diff-style file, component and call trees. Uses the GitHub CLI; runs only when invoked by name.

Community Playwright browser automation MCP from ExecuteAutomation (not Microsoft's official one): navigate, click, fill forms, screenshot and scrape page text, plus send HTTP requests, assert network responses and record actions into test code, with 143 device emulations built in.

Excalidraw's official MCP App: streams hand-drawn-style architecture diagrams and flowcharts into the conversation, with full-screen editing. Remote endpoint at https://mcp.excalidraw.com; requires a client that supports MCP Apps, such as Claude or ChatGPT.

GitHub's official gh extension for writing Actions workflows in Markdown that AI agents execute, compiled into standard Actions. Choose engines like Copilot, Claude Code or Codex; runs in a read-only sandbox by default. Requires gh.

macOS screen capture, accessibility-tree inspection and native UI automation, served over MCP so agents can see the screen and click, type and operate menus. Requires macOS 15+ with Screen Recording and Accessibility permissions granted.

macOS screenshot and UI automation CLI: capture the screen, read the accessibility tree for structured UI elements, then click, type, and switch windows and menus. Also runs as an MCP server for Claude Code and Codex. Needs macOS 15+ with Screen Recording and Accessibility permissions.

LM Studio's official CLI: list, load and unload local models, start and stop the local API server, and check status and logs; ls, ps and other commands support --json output for scripts and agents. Requires the LM Studio desktop app.

Detects shot changes in video and splits long footage into scenes, exporting cut lists and per-scene thumbnails, useful for shot analysis, organizing footage and finding edit points. Runs locally; needs Python 3.10+, plus FFmpeg or mkvmerge for splitting.

Lingo.dev's official CLI: lingo push sends JSON, YAML, Markdown, PO, XLIFF, Android/Xcode strings and other files from your repo to its LLM localization engine, and lingo pull brings translations back; CI-ready. Needs a Lingo.dev account; usage-based pricing with a free sandbox.

Mistral's official open-source terminal coding assistant: uses Mistral models to read and write code, run commands and search the codebase, with multiple agent profiles and subagents, plus Skills, MCP and a --prompt scripting mode. Needs a Mistral API key.

From Callstack: lets coding agents inspect, operate and verify apps on iOS, Android and HarmonyOS simulators and real devices, reading accessibility snapshots, taking screenshots and recordings, and capturing logs and performance data. Ships both a CLI and a built-in MCP server.