Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,788 indexed, measured the same four ways as everything else here.
Agent Browser Runtime for browsing, observing, and interacting with web pages via Chrome DevTools Protocol (CDP). Use this skill when Claude needs to: (1) navigate to and browse websites, (2) extract page content, text, or links from any URL, (3) fill forms or type into input fields, (4) click buttons or links on a…
MCP server for self-hosted Nutrient Document Engine: extract, edit, redact, and annotate documents. Runs locally from the @nutrient-sdk/document-engine-mcp-server npm package. Needs 5 environment variables to run.
★not rated 62 5d agoA
tokens not measured
originalMIT
MUST BE USED for any UI work. Invoke this skill before generating, modifying, or reviewing any code that renders, styles, or wires up a user-facing interface — including markup, components, templates, styles, and the JavaScript/TypeScript that drives them. This skill encodes the accessibility (WCAG 2.2 AA)…
Guide for writing Terrarium tasks. Use this skill when the user wants to create a new task.py, define checkers, use capabilities (email, calendar, workspace, postgres, notion, googlesheets), design multi-stage agent workflows, or integrate their own scenario into Terrarium. Activate whenever someone mentions writing…
Alignment conversation starting from a user's rough idea. Co-decides with the user whether the idea should be acted on directly in the current session, or fixed into a formal Task by producing four documents in .task/ for independent dispatch. Handles lightweight 'do it now while we talk', heavyweight 'define…
Build, validate, or repair Adaptive Card layouts, actions, forms, and delivery wrappers for Microsoft Teams. Use when Teams is the target host, including bot, webhook, Graph, and MessageCard migration tasks. Exclude Windows/custom card hosts and Teams text-only formatting.
Drive a browser from an OpenClaw machine. Companion to the browser-harness skill — explains the OCM-specific bridge proxy, the readiness check you must run first, and how pairing works. Start here before writing any browser code.
Use when handing off an in-progress session to another agent or a future session — ending a session with unfinished work, "pick up where I left off", passing a task to a fresh agent/another window/codex, running low on context, or persisting intent + learnings before context is lost. Covers both dropping a baton…
Create publication-grade scientific figures and analysis deliverables from tabular data. Use when the user provides Excel, CSV, or similar structured data and wants charts, plotting, exploratory analysis, figure polishing, statistical annotations, captions, or a report suitable for a paper, thesis, dissertation, lab…
Search your conversation history using ripgrep. Use when you need to find previous messages, file edits, tool calls, or decisions from earlier in the session.
Use this skill when the user wants to test a business idea, strategy, or initiative against real-world risk. Triggers include: 'test my idea', 'what are the riskiest assumptions', 'help me validate this', 'run EMT on this', 'extract assumptions', 'assumption mapping', 'what could go wrong with this plan', 'pressure…
Autonomously research an ML task and run MANY bounded experiments to find the best config — a fixed-budget edit→train→eval→keep-or-discard loop in the spirit of karpathy/autoresearch, wrapped in the ml-intern orchestrator model and fanned out with a Claude Code dynamic workflow. Runs LONG: an iterative generational…
Use for configuring, reusing, building, or diagnosing named QEMU build directories under source-root builds/, including target-specific, debug, sanitizer, and trace configurations. Use for the QEMU source tree only; kernel and U-Boot builds belong to qemu-kernel-build and qemu-uboot-build.
Write and read content in a Roam Research graph correctly. Roam's markdown differs from standard markdown, and its MCP tools render block metadata (headings, block references, view types) into a wire format you must handle when writing content back. Use this whenever creating, editing, searching, or organizing content…
Walk through the .NET AI Workshop as an attendee to validate that the READMEs, commands, and code snapshots still work. USE FOR: testing the workshop, testing a specific Part, dry-running the labs, verifying a README against its snapshot, reconciling or refreshing code snapshots, producing a workshop test report. DO…
Help the user design, write, compile, and install a Silo extension from a natural-language description. The extension follows the same format as any publishable Silo extension and can be shared via npm or a tarball URL when ready.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: