도구

OpenAI's official Codex plugin with about 50 skills that route questions to genetics, omics, pathway, protein structure, chemistry and clinical evidence sources, can split the work across parallel subagents, and synthesize sourced conclusions.

OpenAI's official Codex plugin with 18 skills to choose, design, build, test and export web charts, maps, dashboards, Gantt charts and UML, using D3, Vega-Lite and Three.js with attention to accessibility and responsiveness. Codex only.

Creates, edits and validates reproducible Python and SQL Jupyter notebooks: organizes cells as reports or tutorials, checks conclusions against actual output and reruns top to bottom before handoff. Maintained by OpenAI in the Data Analytics plugin of openai/plugins.

OpenAI's official data analytics skills: data quality assessment, KPI design, metric anomaly diagnosis, dashboards and analysis reports, market sizing and notebooks. Ships with a Codex plugin; some skills depend on its runtime.

Higgsfield's official Codex plugin: uses its remote MCP to generate images and video from text or photos, like product-shot video ads or animated stills, with built-in flows for faceless narration, voiceover and burned-in captions. Needs a Higgsfield account; billed in credits.

OpenAI's official Codex plugin for answering product and business questions with data: metric anomaly diagnosis, KPI design, market sizing, dashboards and reports, notebooks and data quality checks. Connects to data warehouses and BI tools.

Builds, refactors and debugs ChatGPT apps with the OpenAI Apps SDK: plans tools, scaffolds the MCP server and UI widgets, and checks the work against official docs. Maintained by OpenAI; formerly chatgpt-apps in openai/skills.

Scrapes web pages into Markdown or structured data, with full-site crawling, sitemaps, web search and interaction with dynamic pages. Maintained by Firecrawl; the cloud needs an API key (self-hosting is possible), and the keyless hosted endpoint only offers scrape, search and parse.

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.

Anthropic's reference implementation for finding and fixing vulnerabilities: Claude Code skills for threat modeling, static scanning, triage and patching, plus an autonomous recon-to-patch pipeline (C/C++ memory bugs by default; needs Docker and gVisor). No longer maintained.

Open-source LLM evaluation platform: one opencompass command picks the model and datasets and runs the evaluation across hundreds of benchmarks. Works with local Hugging Face models and API models, with vLLM and LMDeploy for faster inference.

Tw93's lean pack of engineering-habit skills: /think to pressure-test plans, /hunt for root causes, /check to review diffs, /ui for frontend interfaces, /write to polish Chinese and English prose, and more (8 skills). Works with both Claude Code and Codex.

Turns a theme, a line, an article or photos into a minimal, whitespace-heavy indie-zine portrait poster, and can distill reusable style rules and prompts from reference images, with built-in quality checks. Needs host image generation (e.g. Codex); otherwise outputs prompts only.

A more intuitive find-and-replace tool than sed: uses JavaScript/Python-style regex syntax, supports literal string mode and in-place file edits, which suits agents doing bulk text rewrites.

Turns any folder into a Markdown task board: Claude Code or Codex break work into tasks with acceptance criteria for review before coding, managed from the terminal or a browser board. Works without Git for personal plans too. Runs locally with no account; needs Node.js or Homebrew.

Hands your current browser session to the agent through a Chrome extension: read console logs and network requests, take screenshots, and run Lighthouse performance, accessibility and SEO audits without signing in again.

Converts and two-way syncs Jupyter notebooks with plain Python scripts or Markdown, so agents can edit research and teaching notebooks like ordinary text and diffs stay readable. Needs a local Python environment; install with pip.

Cleans a LaTeX project before arXiv submission: removes comments, auxiliary files and unused .tex files and images, and can compress images, so internal notes are not published with the source. From Google Research; installable with Homebrew on macOS.

Python library and CLI for extracting main web content: fetches pages, crawls via sitemaps and RSS feeds, strips headers, footers and other noise, and outputs TXT, Markdown, JSON, XML and more with metadata. Also processes downloaded HTML offline.

Anthropic's official OS-level sandbox CLI: restricts file and network access for agents, MCP servers and any command without containers, using sandbox-exec on macOS and bubblewrap on Linux. Currently a research preview.

Static security analysis for CI/CD config: finds template injection, credential leaks, excessive permissions and more in GitHub Actions workflows, also covers Dependabot and pre-commit configs, and auto-fixes some findings.

Has the agent scaffold a new Remotion video project with create-video after inspecting the current folder, open Remotion Studio for live preview before writing the composition, and follow the layout, multi-scene and timeline guides as needed. Official Remotion skill; needs Node.js and Git.

Remotion's official skill that teaches agents to make programmatic videos in React code, covering project setup, animation and typography, captions, map animations, media handling and rendering, and routes to each subtopic on demand.

Guides the agent through captions in Remotion videos: stores them as JSON using the Caption type from @remotion/captions, transcribes audio or video to generate them, imports .srt files, and displays and animates them in compositions. Official Remotion skill.