17,576 tagged codex, measured the same way as everything else here.
Browse within: claudecode 304agentic-ai 238coding-agents 208claudecode-skills 186skills 179agent 170ai-coding 170openai 143ai-tools 141awesome 141awesome-list 141codex-plugins 141copilot 138cli 102
SoujiOkita98/industry-map-maker-skill
Skill Claude CodeCodex
Maintain a single-file interactive industry map (index.html) with evidence-tiered relationships, clean visual hierarchy, strong logo quality, USD-normalized market text, and publish-ready repository hygiene.
Skill Codex
Run a skeptical Claude review over the current diff or branch range.
hzijad/playwright-agent-skills
Skill Claude CodeCodex
Conducts rigorous authoring and review of Playwright E2E tests. Enforces accessibility-first locators, web-first assertions, strict isolation, and DAMP architecture. Use when generating, refactoring, or reviewing any Playwright test code.
Skill Claude Code
Generic, board-driven implementation pipeline: polls a GitHub Project on a schedule, ARMS an item the moment a human drags it into the configured trigger column, then advances it one stage per tick — each stage a Bridge primitive (skill / workflow / agent / cmd) — and STOPS at a human-gated draft PR. The engine is…
Hermon2026/haowei-relationship
Skill Claude CodeCodex
A dialogue procedure for making relationship decisions, with an opening protocol, five entry points, choice text, and a conversation record.
Skill Claude CodeCodex
A safety-focused workflow guide for editing talking-head and screen-recording videos in ChatCut. It routes short requests such as cleaning speech, reviewing mistakes, or resuming an edit to ChatCut's official capabilities and sets conservative defaults.
Skill Claude CodeCodex
Use the local stata-cli command for Stata work on this machine. Trigger this skill when the user wants to bootstrap an AI-ready Stata workspace, write or debug .do files, inspect .dta data, export CSVs, or needs Stata syntax/package guidance while staying inside the local stata-cli workflow.
Skill Claude CodeCodex
Spawn N peer agents on genuinely independent subtasks, wait for every result, then merge. Use when subtasks do not read each other's outputs and the wall-clock saving is worth N× the token cost.
iola1999/codex-control-chrome-mcp
Skill Codex
Use Codex Control Chrome MCP to control the user's normal Chrome profile through the Codex Chrome extension. Use when a task needs existing Chrome tabs, cookies, logged-in sessions, installed extensions, CDP commands, page inspection, navigation, screenshots, network/console events, or browser automation from an MCP…
Skill Claude CodeCodex
Delegate bounded work from Claude Code to the user's existing official DSH Web Host while preserving typed supervision, task cursors, follow-up, and safe cancellation.
Skill Claude Code
Read-only session orientation. Full/quick views show Jira, PRs, beads and working-copy state; resume mode gives a compact local resume-or-next recommendation without loading a handoff or claiming work.
Skill Codex
Plan, install, inspect, update, or roll back Rootloom Personal Core in a user's Codex home. Supports Skills-only, guidance, and the recommended personal preset. Use when the user explicitly asks for a Rootloom setup plan, installation, configuration, bootstrap, repair, audit, status, update, reduction, rollback, or…
Skill Claude CodeCodex
A skill for writing four Chinese résumé summary lines tailored to a specific candidate, job description, company, and publicly available company information. A résumé summary is the short introduction recruiters read near the top of a résumé.
Skill Claude CodeCodex
A workflow that turns personal notes from books into organised notes, practical AI skills, and a matching README.
Skill Claude CodeCodex
A Chinese-language writing and editing guide focused on producing grounded, personal long-form articles. It helps shape an idea through questions, research, a defined main argument, and a confirmed outline.
Skill Claude Code
A small test skill used to verify that skill conversion supports parameters, scripts, and file references.
Skill Codex
Scaffold or repair the Orient docs system (STATE.md, decisions/, architecture.md) in this repo. Run once per project.
Skill Claude CodeCodex
This skill should be used when the user asks to "start a new story", "initialize a story project", "create a story", "new book", "set up a story", or wants to begin a new fiction writing project from scratch.
Lombiq/Orchard-Core-Agent-Skills
Skill Claude CodeCodex needs its repo
Evidence-first Orchard Core theming skill for shapes, alternates, placement, Razor/Liquid templates, content model access, assets/resources, and recipes. Use for theme adjustments, shape overrides, template discovery, content item/field access, placement.json rules, and recipe authoring in Orchard Core projects.
adonis-cyril/codex-automation-audit
Skill Codex
Audit recent Codex automation and personal skill runs, compare task behavior with prompts and local docs, then prepare numbered patch-ready recommendations without changing files during the scheduled run.
Skill Codex
A method for turning dense information into one self-contained HTML webpage. HTML is the format used to build webpages, and a self-contained file can be opened by double-clicking it without extra software or setup.
Skill Claude Code
Seed, audit, adopt, and progressively evolve an agent-native repository with risk-triggered specs, durable decisions, resident governance skills, capability state, deterministic gates, and safe upgrades. Use when initializing or upgrading a repository, when an unmanaged repository grows complex, or when delivery…
Skill Claude CodeCodex
Use when you want to make something measurably better and let the agent do the trial-and-error for you — for example "make this faster", "how can I improve this?", "reduce cost/memory", "increase test coverage", or "make this search return better results" (also tuning an LLM training run). You don't need to know the…
936220035/execution-prompt-builder
Skill Codex
Turn rough ideas or incomplete requests into self-contained prompts that another execution agent can run. Automatically select suitable expert roles and independent work methods, show the selection so the user can change it, ask one high-value clarification question at a time, incorporate project and user context, and…
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: