Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,392 indexed, measured the same four ways as everything else here.
GDvega/super-android-kotlin-firebase-skill
Skill Claude CodeCodex
Use for creating or reviewing a Compose Material 3 design system whose tokens, components, previews, accessibility and performance rules fit the app context after build/tests pass.
Skill Codex
Repository-agnostic Neneko CR workflow for triaging, reviewing, fixing, reporting, approving, and optionally merging GitHub pull requests across any project. It separates external-PR review from own-PR maintenance, checks current-head CI and review threads, verifies problem necessity and solution fit, requires an…
Skill Claude CodeCodex
Lifecycle-driven QA workflow — from requirements analysis to test reports, with state tracking and impact analysis.
alibaba-quark-scanking/alibaba-quark-scan-qoder
Skill Claude CodeCodex
An image-enhancement service for cleaning and improving pictures, such as documents, ID photos, exams, and contracts. It can remove visual distractions and produce clearer images.
Skill Codex
Use when a learner wants to understand, practice, or build durable skill in a technical or analytical subject instead of outsourcing the thinking to an agent.
Soda1412/video-link-analysis-skill
Skill Codex
A source-analysis workflow that turns a video link into a traceable Markdown research note. It separates what the video says from the author's opinions, the analysis, and any outside fact checks.
Skill Claude CodeCodex
Roll randomized D&D content properties (statblocks, items, spells, feats, scenarios, shops) using weighted chance tables. Use when a DM or designer wants serendipitous mechanical inspiration without generating full finished content.
Skill Claude CodeCodex
How to build an AI agent that actually works — start with a decision-map that forces a singular outcome (or splits into multiple agents), design one in-session, then optionally fan out parked agents in parallel after confirm. Locks Task · Context · Memory · Eval. Use when designing, building, reviewing, or debugging…
Skill Claude CodeCodex
A checker for posts on Xiaohongshu, a Chinese social-content platform, that looks for wording and topics that may violate content rules or reduce reach.
HCW-AI2006/explain-engineering-plainly
Skill Codex
Translate engineering-heavy progress updates, completion reports, errors, code-review findings, implementation summaries, and technical explanations into concise, accurate plain language centered on what happened, what it means for the user, evidence, limitations, and next action. Use when the user asks for…
john-data-chen/hermes-agent-backup
Skill Claude CodeCodex
Batch package upgrades across multiple repos: pnpm up --latest, version caps, Expo mobile, branch+PR workflow.
Skill Codex
Use when the user wants to use an LLM coding agent such as Codex or Claude Code to run a reproducible machine learning workflow on tabular CSV data, including data profiling, leakage checks, binary classification baselines, evaluation metrics, threshold reports, model cards, and final reports.
Skill Codex
Explore, debug, audit, compare, record, and test live websites with deterministic Playwright scripts and QE workflows. Use for requests to map a site, find broken pages or links, reproduce browser bugs, discover hidden or role-gated features, audit accessibility/performance, compare crawls, design or review test cases…
meirdick/growth-product-context
Skill Claude CodeCodex
Discovers user journeys by scanning Laravel routes, controllers, and models, then proposes a product context with AARRR pirate metrics event names. Use when the user asks to map user journeys, define product context, create PRODUCT.md, discover what to track, set up analytics events, or define their funnel. Also…
gutouy/seedance25-prompt-optimizer
Skill Codex
A prompt-writing tool for Seedance 2.5, a system that generates or edits videos from written instructions and reference media.
Skill Claude CodeCodex
Reconstruct what a Steel customer organization was actually doing in its browser sessions, and whether it succeeded, from warehouse records plus raw session logs in object storage. Produces an evidence-backed report: inferred tasks, per-session outcomes, what blocked them, agent-quality problems, and what Steel itself…
kuliantnt/docx-batch-variable-replacement
Skill Claude CodeCodex
A document-processing tool that copies a Word template and replaces specified placeholders or details in each generated file.
Skill Codex
Use this skill when the user is unsure which local Codex skill to use, asks for skill recommendations, wants a guided route through available skills, or wants to turn a vague task into the right skill invocation. It maps the user's task to one or more installed skills and gives a copy-ready next prompt.
Skill Claude CodeCodex
Research GitHub demand signals, active issues, and trend velocity before committing to a product direction.
toronet-guidl/toronet-agent-skills
Skill Claude CodeCodex
Integrate ToroNet into frontend or backend apps. Use when the user wants ToroNet network configuration, contract reads with ethers.js or wagmi, wallet-based writes, or server-side writes through the ToroNet keystore API.
Skill Codex
Invoke only when the user explicitly mentions $crux. When invoked, analyze papers, coach research, or support consequential decisions by finding the variable that could change the outcome, separating evidence from rhetoric, and controlling how much help to reveal. Do not activate for ordinary paper, research, or…
Skill Claude CodeCodex
Reduce terminal context usage by summarizing tests, builds, Git commands, linters and other verbose command output.
Skill Codex
Design new linear or filled SVG icons and cohesive icon sets through a mandatory raster-first workflow. Use when Codex must invent an icon concept, create branded UI icons, make matching navigation or feature icons, or extend an existing icon family. Always generate PNG concepts with ImageGen first, then invoke the…
Skill Codex
Use when WP-CLI, MySQL, Composer, or PHP must run inside the environment of a site managed by LocalWP on macOS. Guides agents to run the zero-config localwp-wpcli.sh helper script to execute commands in the correct site environment automatically.
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: