Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 266,914 indexed, measured the same four ways as everything else here.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Turn a raster logo (PNG/JPG/WebP/screenshot) into a clean minimal SVG with edge smoothness as the primary hard gate and IoU optimized as high as reasonably possible without a fixed global threshold, then into a choreographed logo animation delivered as standalone JS-rendered HTML, applying Disney's 12 animation…
Turn vague visual direction into a practical Chinese traditional color brief. Use when a user has mood words, client feedback, audience positioning, references, or an unclear Chinese traditional color direction that must become palette constraints before choosing colors.
Edit interviews, lessons, commentary, podcasts, and direct-to-camera recordings built around speech. Use it to remove dead air, filler words, false starts, repeated lines, and discarded retakes while preserving natural delivery and keeping captions aligned. When the user asks for visual enhancement, also use it for…
An AI image-design skill for creating posters, book covers, album covers, and similar artwork in a Mondo-inspired style. It can produce image prompts and generate designs in formats such as posters, social-media images, and covers.
Runtime integration skill for external agents connecting to Todo for AI over HTTP API Token / Agent Key, including auth, task lease, events, commit, and task logs.
A Chinese divination tool based on Qi Men Dun Jia, a traditional system for interpreting timing, directions, and events. It conducts a structured interview, calculates a chart with a script, and then explains the result.
Viking Search tuning for specified policy directions. Use this when the user provides specific queries, a type of query, or a business policy direction, and asks to boost, suppress, or fix a class of search results through request-parameter passthrough. You must only perform read-only baseline evaluation and…
★not rated 1.2k▲
+1
changed 3d agoASkillSpector: warn93 tokens
originalApache-2.0
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Reapply and repair Windows Codex Desktop after Store upgrades, including custom provider models hidden by Statsig availablemodels filtering, the dependent blue-purple Power slider and its Ultra toggle, Fast Mode request/UI gates, locale i18n, plugin UI gates, Chrome/browseruse gates, Goal command gates, Windows…
Conventions for building a narrated Remotion video where the audio drives the timeline. Covers timing.ts, beat-local time, gap-fill sequences, and the end-card pattern.
An academic-paper analysis workflow. It requires getting the full paper text and searching for publicly available source code before completing the analysis.
Run a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and merges results. Also use to check run status, costs, and to verify a finished run against its…
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Detects and fixes the…
A prompt-writing guide for producing hand-drawn and illustrated images in one of 18 defined styles or the 3.1 variant. It uses repository templates and a prescribed process to create the final prompt text or production instructions.
Use this agent to scan Swift code for camera, video, and audio capture issues including deprecated APIs, missing interruption handlers, threading violations, and permission anti-patterns.
★not rated 1.2k▲
+7 3d agoASkillSpector: warn39 tokens
originalMIT
Create, verify, repair, and close durable Codex goals with measurable outcomes, evidence gates, plan templates, blocker handling, completion audits, and goal-backed workflow repair.
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: