Инструменты

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

12 LinkedIn writing skills: draft posts, comments and replies in your voice without obvious AI tone, optimize your profile and plan a week of content, with your approval before anything goes out. Also usable in Claude desktop/web (paid plans); optional Apify token to read posts, Publora to publish.

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.

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.

Lets agents operate Home Assistant: control devices, query state and history, create and debug automations and edit dashboards, with 80+ tools. Community-maintained (unofficial); requires your own Home Assistant instance, and running via uvx needs a long-lived access token.

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.

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.

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.

Converts AsciiDoc, a Markdown-like plain-text markup, into HTML5, DocBook and man pages, and with official extensions into PDF and EPUB, suited to technical books, textbooks and large manuals. Ruby-based; install with Homebrew on macOS.

From Callstack: lets coding agents drive and verify iOS, Android, HarmonyOS and desktop apps through accessibility snapshots, with taps, form filling, screenshots, logs and performance sampling, plus a built-in MCP server. Requires Node.js 22.12+.

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.

Gives agents Exa web search and page content fetching, with an optional multi-step research agent and advanced filtered search. Maintained by Exa; the hosted service works anonymously with limits, and signing in or adding an API key raises them.