ツール

monday.com's official plugin in OpenAI's Codex marketplace: search boards, create and update items, assign owners, set timelines and post updates, for campaign schedules, approvals, project tracking and client management. Codex only; needs a monday.com account.

OpenAI's official Codex plugin for Outlook Calendar: summarizes your day, compares availability across people, preps meetings, explains busy and tentative states, and creates, reschedules or cancels meetings. Requires Codex with a ChatGPT sign-in and a Microsoft account.

OpenAI's official Codex plugin for Google Calendar: summarize today's schedule, compare availability across people, prep for meetings, and create, edit or delete events. Requires signing in to Codex with ChatGPT and authorizing your Google account.

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.

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.

Prepares meetings using past notes, requirements and decisions in Notion: picks a template by meeting type, drafts the agenda and pre-reads, and adds research. From OpenAI's official plugin repo (developer: Notion); needs the Notion MCP.

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.

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 No longer maintained.

Tests and debugs a locally running frontend with Codex's Browser plugin or Playwright: checks blank pages, framework and console errors, captures screenshots, re-verifies after fixes and writes a QA report. Maintained by OpenAI; formerly playwright-interactive in openai/skills.

OpenAI's official Codex plugin for adding the OpenAI Ads measurement pixel and optional Conversions API (CAPI) to a website, with local validation scripts plus key and deduplication guidance. Needs the site's source and an OpenAI Ads account; review manually before launch.

OpenAI's official Codex plugin that starts from a brief, product shots or references to generate marketing concepts, mood boards, product scenes, ad directions and social assets, compared and iterated on a reviewable board. Works with Figma and Canva.

Granola's official plugin in OpenAI's Codex marketplace: search past Granola meeting notes by topic, person, company or date, and cite the discussions and decisions when writing proposals, reports or analyses. Codex only; needs a Granola account already recording meetings.

OpenAI's official Codex plugin marketplace (openai-curated) with 60+ plugins such as Figma, Notion, GitHub, Stripe and Vercel, each bundling skills, MCP servers and app connections into one install.

Manage Kubernetes clusters in natural language: translates intent into kubectl operations and runs them, and can serve as an MCP server for other agents. Uses Gemini by default (API key required) and also supports OpenAI and local models. Maintained by Google Cloud.

Command-line email client supporting IMAP, SMTP, JMAP, Gmail and Microsoft Graph, with multiple accounts and --json output, so agents can check, search, compose and send mail. A first-run wizard auto-detects your mailbox settings.

Claude Code workspace for long-form SEO blogging: /research, /write, /rewrite and /optimize handle keyword research, drafting, refreshes and pre-publish checks, with SEO, metadata and internal-link subagents. Clone the repo and add brand voice; optional GA4, Search Console and WordPress.

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.

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.

Cuts long videos like podcasts, webinars, livestreams and interviews into captioned vertical shorts, with optional dubbing and publishing to TikTok, YouTube and more. Hosted version needs an API key (free tier is watermarked and time-limited), or self-host with Docker and your own keys.

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.

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.

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.