도구

ByteDance's open-source, general software engineering agent: trae-cli edits files and runs commands from natural language, supports multiple model providers and MCP, and records full execution trajectories. Transparent design suits agent research and customization. Needs your own model API key.

MySQL terminal client with smart autocompletion and syntax highlighting, also compatible with MariaDB and TiDB. Supports --execute and batch mode with CSV or table output, so agents can run SQL directly.

Pipes live streams from Twitch, YouTube and many other platforms to a local player, or saves them to video files with --output or --record, for keeping and re-editing replays of your own or partners' streams. Viewing needs a player like VLC. Only record content you have rights to.

Scans files and directories for personal data such as names, emails and credit card numbers using Presidio Analyzer, with configurable entity types, confidence thresholds and ignore rules. Needs Python 3.10+ and a spaCy language model.

Fast, memory-efficient image processing library with a vips CLI for batch resizing, cropping, rotating, format conversion (WebP, AVIF, HEIC, TIFF and more) and thumbnails, handling very large images smoothly. Good for design and media teams processing assets in bulk. Install with Homebrew on macOS.

MiniMax's official prompt skill for the Hailuo H3 video model: rewrites video ideas into H3's structured prompt format for text-to-video, first/last frame and full-reference modes, covering visuals, sound effects and music. Docs only; generate videos on Hailuo web, the MiniMax API or a local model.

Publishes SQLite databases as browsable, queryable web pages and JSON APIs, with SQL queries, metadata and plugins, and deploys to Cloud Run and other platforms with datasette publish. Great for data exploration and data journalism. Needs Python 3.10+.

Hugging Face's official skills: manage Hub models and datasets with the hf CLI, fine-tune language and vision models, run model evaluations, and build Gradio apps deployed to Spaces. Needs an HF account; cloud training on HF Jobs requires a paid plan.

Teaches agents the Hugging Face Hub CLI hf: search and download models, manage datasets, Spaces, Buckets and repos, and run Jobs and inference endpoints. The skill content is generated from your local CLI, so install hf first. Maintained by Hugging Face.

Lets agents fine-tune language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, supporting SFT, DPO, GRPO and reward models, and convert results to GGUF for local use. Requires an HF Pro or higher paid plan. Maintained by Hugging Face.

Lets agents work with the Hugging Face Hub through the hf CLI: search and download models and datasets, manage repos and Spaces, and run training and evaluation jobs on cloud GPUs, with more workflow skills installable as needed. Maintained by Hugging Face.

The official MCP debugging tool: connect to any MCP server through a web UI, CLI or terminal UI to list and call its tools, resources and prompts. CLI mode outputs JSON, suited to scripts and CI smoke tests.

Writing agent for novels, scripts, interactive fiction and long-form translation, with CLI, TUI and web workspace. Tracks worldbuilding, characters and foreshadowing, reviews and revises drafts, and works as a skill for other agents. Needs Node.js 22.16+ and a model API key such as Kimi or DeepSeek.

Builds a scroll-scrubbed fly-through 3D world landing page for any brand: generates scene stills with Higgsfield and seamless camera clips via Monid (Seedance 2.0, paid per clip) or Higgsfield credits, then wires a vanilla JS scrub engine. Needs Higgsfield CLI and ffmpeg.

Publication-quality matplotlib plotting skill from a Yale PhD student: bar charts, trends, heatmaps and multi-panel figures with consistent fonts, colors and export settings, plus real plotting scripts from papers published in venues like Nature Machine Intelligence. Needs Python.

Reads the exact position of every character, line and table cell in digital PDFs: the CLI exports layout-preserving text or CSV/JSON details, and the Python API extracts tables and form fields, ideal for invoices, statements and reports. Runs locally with Python; scans need OCR first.

Batch-translates text in manga, posters and screenshots with one command: detects text, runs OCR, erases the original and typesets the translation back into the image. Japanese-focused, with 20+ languages supported. Install from source (Python 3.10+); offline models, DeepL or LLM APIs.

Universal psql-style SQL command line: one tool to connect to PostgreSQL, MySQL, SQLite, SQL Server, Oracle and dozens of other SQL and NoSQL databases, with support for copying data between databases.

Open-source research agent: one command runs literature reviews, deep research, paper reviews, paper-code consistency checks and replication plans, searching arXiv, PubMed and more with sources recorded. Good for grad students writing reviews. Run feynman setup to sign in to a model provider.

Processes CSV, TSV, JSON and other structured data like awk, sed, cut, join and sort, but by field name, for cleaning, aggregation, format conversion and pretty-printing. The command is mlr; written in Go with no runtime dependencies.

Linter and formatter for 20+ SQL dialects that auto-fixes most issues and handles Jinja templating and dbt projects (dbt needs a plugin), suited to warehouse code review and CI.

NVIDIA's open-source LLM vulnerability scanner that probes for prompt injection, jailbreaks, data leakage, hallucination and harmful content, supporting OpenAI, Hugging Face, Bedrock and most REST-accessible models. Scanning cloud models needs their API keys.

Official AWS MCP for managing FHIR health data in AWS HealthLake: CRUD, advanced search, full patient records, and import and export, with a read-only mode to prevent changes. Needs an AWS account, a paid HealthLake data store and local AWS credentials; clinical conclusions need professional review.

Distributed data integration tool and Apache top-level project with 160+ connectors for batch, real-time and CDC sync. Define jobs in config files and run them on the built-in Zeta engine or on Flink or Spark. Requires Java.