SkillAgentSearch skills...

The 15 Best OpenAI Codex Skills

Ranked by quality, maintenance and a safety scan of every file · Updated

Skills and AGENTS.md instructions for OpenAI Codex CLI and other agents that read the same files. We compared 424 OpenAI Codex Skills that pass our quality bar, 94% of which came up clean on our safety scan; these are the top 15, no more than three from any one repository.

  1. Use when creating new skills, editing existing skills, or verifying skills work before deployment

    Quality 97/100Safety scan clean★ 290,965Updated 46 days ago

    Why it is here: clean safety scan; 290,965 GitHub stars.

    npx skills add obra/superpowers --skill writing-skills
  2. 2

    publish

    by code-yeongyu

    Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re-reviews merged code unless the user explicitly asks. Argument: <patch|minor|major|explicit-semver>.

    Quality 100/100Safety scan clean★ 69,362Updated 45 days ago

    Why it is here: highest quality score in this list; clean safety scan; 69,362 GitHub stars.

    npx skills add code-yeongyu/oh-my-openagent --skill publish
  3. 3

    lcx-report-bug

    by code-yeongyu

    Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance,…

    Quality 100/100Safety scan clean★ 69,362Updated 45 days ago

    Why it is here: highest quality score in this list; clean safety scan; 69,362 GitHub stars.

    npx skills add code-yeongyu/oh-my-openagent --skill lcx-report-bug
  4. 4

    lcx-contribute-bug-fix

    by code-yeongyu

    Contribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Codex skills, or upstream Codex CLI bugs. LazyCodex-owned defects get a fork PR against code-yeongyu/oh-my-openagent (base dev, source-tree paths under packages/omo-codex/plugin, with the changelog fragment); upstream Code…

    Quality 99/100Safety scan clean★ 69,362Updated 45 days ago

    Why it is here: clean safety scan; 69,362 GitHub stars.

    npx skills add code-yeongyu/oh-my-openagent --skill lcx-contribute-bug-fix
  5. 5

    gpt-taste

    by nexu-io

    Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive sect…

    Quality 92/100Safety scan clean★ 97,896Updated 44 days ago

    Why it is here: clean safety scan; 97,896 GitHub stars.

    npx skills add nexu-io/open-design --skill gpt-taste
  6. Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.

    Quality 100/100Safety scan clean★ 48,926Updated 7 days ago

    Why it is here: highest quality score in this list; updated 7 days ago; clean safety scan.

    npx skills add sickn33/agentic-awesome-skills --skill ad-campaign-analyzer
  7. Install and use the official AI Headshot Generator package, pinned by digest, for paid hosted work on the Beatra service.

    Quality 100/100Safety scan clean★ 48,926Updated 7 days ago

    Why it is here: highest quality score in this list; updated 7 days ago; clean safety scan.

    npx skills add sickn33/agentic-awesome-skills --skill ai-headshot-studio
  8. Install and use the official Multilingual Voiceover package, pinned by digest, for paid hosted work on the Beatra service.

    Quality 100/100Safety scan clean★ 48,926Updated 7 days ago

    Why it is here: highest quality score in this list; updated 7 days ago; clean safety scan.

    npx skills add sickn33/agentic-awesome-skills --skill ai-multilingual-dubbing
  9. 9

    pathml

    by K-Dense-AI

    Supports local computational pathology research with PathML: slide loading and tiling, preprocessing and QC, h5path storage, multiplex quantification, spatial graphs, and bounded model inference. Use for whole-slide H&E, CODEX, Vectra, Mesmer, HoVer-Net, and HACTNet workflows.

    Quality 98/100Safety scan clean★ 46,441Updated 48 days ago

    Why it is here: clean safety scan; 46,441 GitHub stars.

    npx skills add K-Dense-AI/scientific-agent-skills --skill pathml
  10. Generate configurable chat motion overlays from a transcript or screenshot, including plain bubble scenes, app-style chat containers, optional device frames, preset or uploaded avatars, nickname display rules, and transparent-video-ready Remotion bundles

    Quality 87/100Safety scan clean★ 97,896Updated 44 days ago

    Why it is here: clean safety scan; 97,896 GitHub stars.

    npx skills add nexu-io/open-design --skill chat-motion-overlay
  11. Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags

    Quality 98/100Safety scan clean★ 39,920Updated 48 days ago

    Why it is here: clean safety scan; 39,920 GitHub stars.

    npx skills add wshobson/agents --skill block-no-verify-hook
  12. 12

    orca-cli

    by stablyai

    Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and Orca's embedded browser through the `orca` CLI

    Quality 81/100Safety scan clean★ 111,641Updated 7 days ago

    Why it is here: updated 7 days ago; clean safety scan; 111,641 GitHub stars.

    npx skills add stablyai/orca --skill orca-cli
  13. Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos.

    Quality 95/100Safety scan clean★ 39,348Updated 45 days ago

    Why it is here: clean safety scan; 39,348 GitHub stars.

    npx skills add github/awesome-copilot --skill acreadiness-generate-instructions
  14. Create Git branches following the Conventional Branch specification (feature/, bugfix/, hotfix/, release/, chore/, plus AI agent prefixes ai/, copilot/, cursor/, claude/, codex/)

    Quality 95/100Safety scan clean★ 39,348Updated 45 days ago

    Why it is here: clean safety scan; 39,348 GitHub stars.

    npx skills add github/awesome-copilot --skill conventional-branch
  15. 15

    add-codex

    by nanocoai

    Use Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, vault-only via the selected gateway.

    Quality 98/100Safety scan clean★ 31,069Updated 8 days ago

    Why it is here: updated 8 days ago; clean safety scan; 31,069 GitHub stars.

    npx skills add nanocoai/nanoclaw --skill add-codex

Side by side

#NameQualitySafetyStarsUpdated
1writing-skills97Clean290,96546 days ago
2publish100Clean69,36245 days ago
3lcx-report-bug100Clean69,36245 days ago
4lcx-contribute-bug-fix99Clean69,36245 days ago
5gpt-taste92Clean97,89644 days ago
6ad-campaign-analyzer100Clean48,9267 days ago
7ai-headshot-studio100Clean48,9267 days ago
8ai-multilingual-dubbing100Clean48,9267 days ago
9pathml98Clean46,44148 days ago
10chat-motion-overlay87Clean97,89644 days ago
11block-no-verify-hook98Clean39,92048 days ago
12orca-cli81Clean111,6417 days ago
13acreadiness-generate-instructions95Clean39,34845 days ago
14conventional-branch95Clean39,34845 days ago
15add-codex98Clean31,0698 days ago

How we rank

Only skills we have read make the list: the file itself was fetched, it has a real description, it scores at least 55 of 100 on quality, its source still exists, its repository has at least 20 GitHub stars, and our safety scan found nothing high-risk. The order then follows adoption (GitHub stars, on a log scale), how squarely it fits this topic, and its quality score (how substantial and well structured the file is and how recently it changed), moved up for a clean safety scan and for real installs through the SkillAgent MCP server, and down for safety notes. At most three come from any one repository, and tools sold on evading bot detection are never listed. We do not rank by install counts reported by a command-line tool: they are easy to inflate, and our research found repositories with no stars claiming hundreds of thousands of installs. The list is recomputed on every visit.

Questions

What is the best OpenAI Codex Skill?

writing-skills by obra ranks first: clean safety scan, 290,965 GitHub stars. The full ranking above lists 15 alternatives with their trade-offs.

How do I install one?

Each entry shows a one-line command. `npx skills add` installs a skill for Claude Code, Cursor, Codex, Gemini CLI and other agents that read skill files.

Are these safe to install?

Every file is scanned for instructions that work against you: hidden text, data sent to outside servers, disabled approval prompts, leaked keys. Skills with a warning are never listed here, and 94% of the 424 we compared for this guide came up clean. Read a skill before installing it all the same: it runs with your permissions.