ツール

CLI and library for evaluating and red-teaming LLM apps: compare prompts and model outputs in bulk, scan for security vulnerabilities and plug into CI/CD, with evals running locally. Now part of OpenAI and still open source under MIT.

160+ specialized Claude Code subagents, packaged as plugins in 10 categories such as core development, languages, infrastructure, testing and security, and data and AI, so you install only what you need.

Distills a colleague, friend or public figure's chats, documents and public material into a persona profile packaged as a callable skill, for handoffs and preserving know-how. Collects material from Lark, DingTalk, Slack and more. Mind privacy and consent when using others' data.

All-in-one toolchain for web projects: fast formatting and linting with 500+ rules for JS, TS, JSX, JSON, CSS and GraphQL. Formatting is highly compatible with Prettier, and check --write applies all fixes in one pass.

Define cloud infrastructure in general-purpose languages like TypeScript, Python and Go, then preview and deploy with pulumi up to AWS, Azure, GCP, Kubernetes and 300+ other providers. Open source and maintained by Pulumi.

Every's compound engineering workflow: brainstorm, plan, execute, simplify and review, then capture what was learned as docs for future work. Includes 36 skills and supports Claude Code, Codex and a dozen other hosts.

Declarative diagram scripting language: describe architecture diagrams, flowcharts and sequence diagrams in concise text with automatic layout, then render with the d2 command to SVG, PNG, PDF or PPTX. Lets agents produce diagrams you can version-control.

Open-source Zapier alternative with a built-in MCP server: agents can build and test automations in plain language, manage tables, or call hundreds of apps like email, spreadsheets and chat. Use the cloud or self-host, enable the MCP server in settings and connect via OAuth.

Removes image backgrounds with one command: single images, whole folders or watched directories, mask-only output and switchable models like U2Net and SAM. Can also run as an HTTP server or process video frames with FFmpeg. Default models run locally.

Adds a structured dev process to Claude Code: 30 /sc slash commands for brainstorming, implementation, testing, troubleshooting and research, 20 domain expert subagents and 7 behavior modes, with optional MCPs like Context7. Installs via pipx; a marketplace version is in progress.

Community-maintained modern replacement for ls (successor to exa) with colored output, tree view, Git status and file icons, plus .gitignore filtering for quickly scanning directory structures.

SEO audit plugin covering technical SEO, E-E-A-T content quality, Schema markup, Core Web Vitals, local and e-commerce SEO, and GEO for AI search. Parallel subagents audit and return a prioritized action list. Needs Python 3.10+; Playwright optional for SPA rendering and screenshots.

Skyvern's official MCP: drives a browser with vision LLMs to complete multi-step tasks like filling forms, downloading files and web research. Connect to Skyvern Cloud (OAuth or API key), or self-host Skyvern and run it as a local process.

Lets agents look up docs, properties and workflow templates for n8n's 2,000+ nodes and build and validate workflows; with an n8n API key configured it can create and update workflows in your instance directly.

SEO analysis skill pack: 26 sub-skills and 19 subagents run full-site audits in parallel, covering technical SEO, E-E-A-T content quality, Schema, AI search optimization (GEO) and local SEO. Full features require installing it as a plugin and running /seo setup.

Compiles Markdown chapters into an online book with a table of contents, full-text search and themes, good for manuals, lecture notes and course material; agents can edit chapter files and rebuild to preview. Maintained by the Rust team; install a prebuilt binary or via cargo.

Google's official skill library and plugin marketplace: nearly 150 skills focused on Google Cloud (GKE, BigQuery, Cloud Run, IAM and more), plus 17 product plugins pairing skills with MCP for Cloud SQL, Spanner, AlloyDB, BigQuery, GCS and others.

Google's official skill library, focused on Google Cloud: 100+ skills for gcloud, Cloud Run, GKE, BigQuery, IAM, monitoring and logging, and the Well-Architected Framework, plus Ads and Analytics.

Manages BigQuery datasets, tables and jobs with the bq and gcloud CLIs, runs SQL queries and loads data, with references for client libraries, MCP and Terraform. Google's official skill; requires a Google Cloud project.

Scripts terminal sessions in .tape files and records them to GIF, MP4 or WebM, great for CLI demos and docs; text snapshot output also enables terminal integration tests. By Charm; requires ttyd and ffmpeg.

Industrial-grade open-source speech recognition toolkit from Alibaba's ModelScope, with an agent-friendly funasr command that turns audio into text, JSON or SRT subtitles in one step, with speaker diarization and timestamps. Strong on Chinese. Requires PyTorch.

Command-line tool for bulk-downloading galleries and posts from many image hosts and social platforms, with flexible file naming and config, and yt-dlp integration for video. Main development has moved to Codeberg; the GitHub repo stays in sync.

AI2's tool for converting PDFs and scans to Markdown with a vision LLM, handling equations, tables, handwriting and multi-column layouts, suited to bulk digitizing papers and archives. Local runs need an NVIDIA GPU with 12GB+ VRAM; otherwise use a paid OpenAI-compatible remote endpoint.

Pressures the agent with big-tech PUA and PIP-style rhetoric plus structured debugging steps and initiative checks, pushing it to change approach after failures and show evidence before claiming done. Modes include always-on, encouragement and P9 lead. Works with Claude Code, Codex and more.