Skills for Codex

217,996 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

howopen

19849

ospocc/agent-skill-howopen

Skill Claude CodeCodex

This skill allows the agent to perform an "Open Source Health Check" on the current project. It analyzes the technology stack, programming language distribution, and open-source licenses of dependencies.

not rated 1 8mo ago A 39 tokens original MIT

ralph

19850

javi22020/ralph

Skill Claude CodeCodex

Run an autonomous iterate-test-replan loop until a multi-step coding task is complete. Use this whenever the user asks Claude Code to work autonomously through a backlog, fix plan, or specification with minimal supervision — phrases like "ralph this", "loop until done", "keep iterating until tests pass", "work…

not rated 1 5mo ago C 142 tokens

idea-clarifier

19851

knack-run/knack-starter-pack

Skill Claude CodeCodex

Take a rough idea, brief, or project sketch and return a clear audience, a concrete pain point, an offer framing, and a ranked first-action plan. Triggers on "I have an idea for X", "help me think through X", "I want to build/launch/start X", "what should I do next with X", or any pasted brief that mentions an…

not rated 1 5mo ago A 123 tokens original MIT

pdw

19852

diablofong/product-dev-workflow

Skill Claude CodeCodex

Product Dev Workflow — a branch-per-task development assistant. Single slash command /pdw with seven sub-flows. Use /pdw alone to see the menu, or /pdw [sub] [args] for a specific flow. Sub-commands are init, talk, dev, hotfix, done, status. Also accepts natural language ("/pdw I want to build a login page") and…

not rated 1 5mo ago A 89 tokens original MIT

useforgekit

19853

Dragoon0x/useforgekit

Skill Claude CodeCodex

Generate optimal Claude Code configuration for any project. Creates CLAUDE.md, settings.json, skills, hooks, agents, and commands tailored to your stack. Run /forge to start.

not rated 1 5mo ago A 41 tokens

literature-search

19854

yojiro253-del/BioForge

Skill Claude CodeCodex

Search academic literature (Semantic Scholar) for synbio/microbiology papers, returning a ranked, citable list to feed into paper-extractor.

not rated 1 3mo ago A 33 tokens original MIT

electron-desktop-builder

19855

smartbrainactivity/electron-desktop-builder

Skill Claude CodeCodex needs its repo

Converts a web app (Express, React, Vite, Next.js) into an Electron desktop app. Use when starting a new Electron project from an existing web app, when setting up electron-builder for the first time, when creating main.ts/preload.ts boilerplate, when generating icon assets, or when configuring NSIS installers.…

not rated 1 6mo ago A 109 tokens original MIT

reasoning

19856

Firekid-is-him/Reasoning-Skill-Claude

Skill Claude CodeCodex

A reasoning framework that forces Claude to think beyond its training data, challenge its own answers, understand context before responding, and find paths around walls instead of stopping at them. Use this skill for every conversation — especially when a problem seems impossible, when the user is asking for something…

not rated 1 changed 24d ago A 90 tokens

git-commit-helper

19857

lc-rezende/AI-Custom-Skills

Skill Claude CodeCodex

Generate conventional commit messages without scopes based on staged changes. Use when the user asks for commit message help, has staged changes, or is about to commit.

not rated 1 6mo ago A 36 tokens original Apache-2.0

data-vis-coding-v2

19858

hsuan1012/Dataviz-Coding-Agent

Skill Claude CodeCodex

A workflow for building interactive data-visualization apps from CSV, JSON, or GeoJSON data using React, Tailwind, Chart.js, or D3.

not rated 1 1mo ago A 327 tokens

rigorous-review

19859

tkolleh/skills

Skill Claude CodeCodex

Rigorous, evidence-backed code review for high-stakes changes. Trigger on: rigorous review, thorough review, deep review, review this PR properly, review before merge, high-stakes review, "is this actually safe to merge", regulated or compliance code review, batch-review these PRs. Every finding carries quoted…

not rated 1 changed 15d ago A 144 tokens original MIT

reflect-and-improve

19860

aroyburman-codes/compound-product-management

Skill Claude CodeCodex

Use after completing significant work, recovering from errors, or at session breakpoints to review actions, synthesize learnings, and write persistent improvements to memory files. Reduces repeated mistakes and user friction over time.

not rated 1 7mo ago A 47 tokens original MIT

four-agent-pipeline

19861

whaojie797-design/Novera-AI-pipeline

Skill Claude CodeCodex

Orchestrates a four-agent coding pipeline (Specifier -> Coder -> Refactorer -> Architect) with steel-cage quality gates and automatic failure routing. Use when the user wants spec-driven development, says "run the four-agent pipeline", "compile this requirement into acceptance criteria", "multi-agent TDD", or wants AI…

not rated 1 2mo ago A 82 tokens original MIT

skill-ideation

19862

mcltyl/skill-ideation

Skill Claude CodeCodex

Generate agent skill ideas through problem-driven brainstorming. Situation-specific, narrow-but-universal. Triggers when user wants skill ideas or needs to expand their skill collection.

not rated 1 6mo ago A 37 tokens original MIT

audit-design-tokens

19863

humbleteam/audit-design-tokens

Skill Claude CodeCodex

Scans a codebase for design token drift - raw hex colors, off-scale spacing, near-duplicate colors, font sprawl, hardcoded z-index. Use when asked to "audit my design tokens", "find hardcoded colors in this codebase", "check for design token drift", or "clean up our CSS variables". Returns a severity-ranked report…

not rated 1 changed yesterday A 105 tokens original MIT

weakpass

19864

ibnaleem/weakpass-skill

Skill Claude CodeCodex

Search hashes through 25 billion leaked passwords using the Weakpass API (no API key required).

not rated 1 4mo ago A 22 tokens GPL-3.0

building-mcp-servers

19865

cyberreinxy/mcp-server-skill

Skill Claude CodeCodex

Use this skill whenever the user wants to design, build, harden, review, or debug an MCP (Model Context Protocol) server — including "build me an MCP server for X", connecting an AI agent/Claude to a database or API, adding tools/resources to an existing MCP server, reviewing a contributor PR against an MCP server, or…

not rated 1 1mo ago A 160 tokens original MIT

find-my-goal

19866

Kaiji-Z/find-my-goal

Skill Claude CodeCodex

A guide for turning a vague request containing “goal” or “目标” into a clear, checkable goal statement.

not rated 1 1mo ago A 194 tokens original MIT

project-to-resume

19867

ChenxDeng/project-to-resume

Skill Claude CodeCodex

A workflow for turning a completed project into a résumé project entry. It gathers the project's purpose, work, technology, and results, then writes versions suited to different job types.

not rated 1 4mo ago A 95 tokens original MIT

checkup

19868

tokyubevoxelverse/checkup

Skill Claude CodeCodex

Give a repository a full health exam — doc rot, dependency staleness, CI decay, git hygiene, dead links, docs contradicting code — and grade it. Use when the user wants to know what quietly rotted, or a prioritized maintenance list.

not rated 1 2mo ago A 55 tokens original MIT

new-project

19869

T4LEL/Claude-Arsenal

Skill Claude CodeCodex

Use when starting any new app, webapp, API, tool, or side project from scratch - when the user names an idea to build or says new project, scaffold, start a repo, set up a project. Produces a running, git-tracked, Claude-ready project skeleton.

not rated 1 2mo ago A 61 tokens original MIT

llm-council

19870

tony95253/llm-council

Skill Claude CodeCodex

A decision-review process that asks five independent AI agents to examine an important question from different viewpoints, then has a chair agent combine their conclusions. It is designed to reduce agreement bias, where an AI too readily supports the user's apparent preference.

not rated 1 3mo ago A 148 tokens original MIT

html-mockup

19871

humbleteam/html-mockup

Skill Claude CodeCodex

Builds a pixel-faithful single-file HTML mockup from a reference screenshot by counting colors, photos, items, and states before writing markup. Use when a user says "turn this screenshot into HTML", "build a mockup that matches this design", "code this screen exactly", or pastes an image and asks for a coded version.…

not rated 1 changed 4d ago A 92 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: