Everything for Codex

Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 265,202 indexed, measured the same four ways as everything else here.

claude-api

985

Prismer-AI/PrismerCloud

Skill Claude CodeCodex

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…

not rated 1.5k +86 1mo ago A SkillSpector: warn 193 tokens original MIT

liyue-aigc/female-portrait-director

Skill Claude CodeCodex

Generate, visually expand, optimize, diagnose, and route structured AI image prompts for adult female portraits. Use for lifestyle, curve-focused, fashion, oriental, fantasy, realism, beauty, CCD, low-key cinematic, studio, sport, travel, and e-commerce portrait requests; onboarding or usage help; parameter…

not rated 1.5k +26 1mo ago A 112 tokens original MIT

articraft-authoring

987

mattzh72/articraft

Skill Claude CodeCodex

Use when creating, editing, checking, or finalizing Articraft articulated-object records in the local library.

not rated 1.5k +4 1mo ago A SkillSpector: pass 28 tokens original Apache-2.0

trace-and-isolate

988

rohitg00/skillkit

Skill Claude CodeCodex

Applies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use when a bug is hard to locate, code is not working as expected, an error or crash appears with unclear cause, a regression was introduced between recent commits, or you need to narrow down which component…

not rated 1.5k +8 3mo ago A SkillSpector: pass 120 tokens original Apache-2.0

burp-scan

989

six2dez/burp-ai-agent

Skill Claude CodeCodex needs its repo

Burp Suite scanning via MCP tools — passive traffic analysis, active payload testing, OOB verification, and vulnerability reporting using Burp's proxy, HTTP sender, Collaborator, and scanner APIs. Use when the user has Burp Suite running with the AI Agent MCP server and wants to scan, test, or analyze web traffic…

not rated 1.5k +8 8d ago C SkillSpector: warn 87 tokens original MIT

task_automation

990

siddsachar/row-bot

Skill Claude CodeCodex

Design effective automated workflows using scheduled tasks, prompt chaining, and delivery channels.

not rated 1.5k +3 today A SkillSpector: pass 19 tokens original Apache-2.0

integration-review

991

google/adk-docs

Skill Claude CodeCodex ✓ vendor

Reviews an ADK integration documentation page (a Markdown file under docs/integrations/) or an integration pull request for correctness, structure, style, working code, valid links, and catalog conventions. Produces a prioritized review report, a recommended decision (approve, request changes, or close PR), a…

not rated 1.5k +5 today A SkillSpector: pass 110 tokens original Apache-2.0

gh-stack

992

github/gh-stack

Skill Claude CodeCodex ✓ vendor

Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh stack; or when a stack is…

not rated 1.5k +28 today A Socket: passSnyk: pass 80 tokens copy · 97% MIT

new-tool

993

dirac-run/dirac

Skill Claude CodeCodex

Create a custom Dirac tool from user-provided or model-derived requirements.

not rated 1.5k +7 2d ago A SkillSpector: pass 17 tokens original Apache-2.0

arcads-external-api

994

krusemediallc/arcads-claude-code

Skill Claude CodeCodex

Creates and retrieves AI video and image-related assets via the Arcads external API (Seedance 2.0, Sora 2, Veo 3.1, Kling, Grok Video, Nano Banana, b-roll, scene, script/actor flows). Loads prompts from the bundled prompting guide and model library, respects HTTP Basic auth from ARCADSAPIKEY, and polls assets/videos…

not rated 1.5k +17 2mo ago A SkillSpector: warn 133 tokens original MIT

icm-architect

995

RinDig/icm-architect

Skill Claude CodeCodex

Design any process, idea, problem, or body of knowledge into an ICM (Interpretable Context Methodology) workspace — folder structure as agent architecture — or restructure an existing folder, repo, or vault into one. Use when the user wants to (1) turn a recurring workflow into an agent-runnable folder pipeline, (2)…

not rated 1.5k +52 16d ago A 218 tokens original MIT

AMAP-ML/LongHorizon-Harness

Skill Codex

Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout. Use when the user wants an AI coding agent to set up dependencies, download WeaveBench assets, prepare the 120G VM, configure Qwen/Anthropic-compatible APIs, run smoke tests, launch full or subset evaluations, inspect logs, or summarize scores for…

not rated 1.5k +21 21d ago A SkillSpector: pass 81 tokens original MIT

openonion/connectonion

Skill Claude CodeCodex

Create robust browser automation skills for sites like LinkedIn, X/Twitter, YouTube, Stripe, or other logged-in web apps by saving page context, analyzing HTML/CSS, writing skill-local JS extract/verify scripts, and using CSS selector actions with screenshot verification.

not rated 1.5k +2 today A SkillSpector: warn 61 tokens original Apache-2.0

provision-with-maas

998

NVIDIA/deepops

Skill Claude CodeCodex needs its repo ✓ vendor

Provision or reinstall bare-metal servers and test VMs through Canonical MAAS, map deployed machines into DeepOps Ansible inventory with MAAS tags, validate access, or release them safely. Use when operating DeepOps with a MAAS-owned machine lifecycle.

not rated 1.5k +1 today A SkillSpector: pass 57 tokens original BSD-3-Clause

minutes-mirror

999

silverstein/minutes

Skill Codex

Self-coaching analysis of your own behavior across meetings — talk-time ratio, filler words, hedging language, monologue length, energy patterns, and (when meetings are tagged via /minutes-tag) what your behavior in winning meetings looks like vs losing ones. Use this whenever the user says "how did I do", "review my…

not rated 1.5k +6 yesterday A SkillSpector: warn 171 tokens original MIT

flutter-it/get_it

Skill Claude CodeCodex

Architecture guidance for Flutter apps using the flutterit construction set (getit, watchit, commandit, listenit). Covers Pragmatic Flutter Architecture (PFA) with Services/Managers/Views, feature-based project structure, manager pattern, proxy pattern with optimistic updates and override fields, DataRepository with…

not rated 1.5k 6mo ago A SkillSpector: warn 103 tokens original MIT

lime-governance

1001

limecloud/lime

Skill Codex

Govern Lime legacy cleanup, fact-source convergence, current/compat/deprecated/dead classification, and guardrails.

not rated 1.5k +1 2d ago A 27 tokens

[object Object]

1002

team-reflect/reflect-open

Skill Claude CodeCodex

Read, search, and open notes in the user's "{{GRAPHNAME}}" Reflect graph via the reflect CLI. Use when the user asks about their notes, daily notes, journal, or anything they may have written down in Reflect.

not rated 1.5k +11 yesterday A 51 tokens original MIT

linear-server

1003

inkline/inkline

MCP server Claude CodeCodexCursor +2

Linear's hosted MCP server: lets the agent read and update issues, projects and cycles. Remote server at mcp.linear.app.

not rated 1.5k 2d ago A tokens not measured

gog-workspace

1004

AtomicBot-ai/Atomic-Chat

Skill Claude CodeCodex

Use the gog CLI for Google Workspace tasks across Gmail, Calendar, Drive, Docs, Sheets, Contacts, and related services. Use when the user asks to check email, search Gmail, inspect calendar events, find Drive files, read Docs or Sheets, or manage Google Workspace data through gog.

not rated 1.5k +31 yesterday A SkillSpector: warn 68 tokens

clawteam

1005

win4r/ClawTeam-OpenClaw

Skill Claude CodeCodex

Multi-agent swarm orchestration. USE THIS (not delegatetask) when the user says team/swarm/multi-agent/clawteam/parallel-agents/agent-team, or asks for multi-perspective analysis (stocks, research, code review, strategy). Spawns N Hermes workers in tmux windows with git worktree isolation, file-based inboxes, and a…

not rated 1.5k +4 2mo ago A SkillSpector: warn 103 tokens original MIT

ros-mcp-server

1006

robotmcp/ros-mcp-server

MCP server Claude CodeCodexCursor +2

Connect AI Language Models with Robots on ROS using MCP. Runs locally from the ros-mcp Python package.

not rated 1.4k +11 today A Socket: warn tokens not measured original Apache-2.0

superlog

1007

superloglabs/superlog

MCP server Claude CodeCodexCursor +2

Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents. Remote server at api.superlog.sh.

not rated 1.4k +6 today A tokens not measured original Apache-2.0

beui

1008

starc007/ui-components

Skill Claude CodeCodex

Pick and install beUI (@beui) animated React components from the shadcn registry. Use when building motion UI, agent/chat interfaces, toasts, docks, bottom sheets, drawers, popovers, sliders, loaders, 404 pages, or any beui.dev component. Maps user intent to exact @beui install slugs instead of inventing custom…

not rated 1.4k +31 changed today A Socket: passSnyk: warnSkillSpector: warn 78 tokens original MIT

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: