Skill Codex
Review one project for code elegance, beauty, developer joy, clarity, language conventions, naming, and locality. Evaluate the maintenance experience. Do not use this skill for defect, security, small-change, or visual UI reviews. Do not combine it with deep-codebase-review unless the user requests both skills.
Skill Codex
Review an entire repository, its architecture, technical debt, or a substantial branch. Produce findings about boundaries, lifecycle, concurrency, duplication, tests, plans, and maintenance. Do not use this skill for small changes, narrow defects, or visual UI review. Do not use it for repository guidance or an OpenAI…
Skill Codex
Design or implement an HTML-first web interface. Use native browser features, progressive enhancement, server-rendered updates, and minimal JavaScript. Do not use for visual design, framework architecture, games, or browser debugging.
Skill Codex
Create a visual system for a new or redesigned user interface. Generate exactly three image concepts and stop for user approval. After approval, create an HTML and CSS style guide with a representative demo. Do not use when the user supplies an approved design, requests a small edit, or skips visual exploration.
Skill Codex
Plan, audit, or complete an upgrade from Django 5.x to Django 6. Verify runtime and dependency compatibility, deprecations, settings, databases, migrations, tests, and deployment. Do not use for general Django work, earlier upgrades, frontend styles, or unrelated maintenance.
Skill Codex
Build Django performance regression tests with pytest-benchmark. Use for ORM, views, schema, transactions, or database backend behavior. Match the production database engine and topology. Do not use for one-time profiling, browser rendering, application performance monitoring, or non-Django services.
Skill Codex
Integrate or refactor Tailwind CSS and DaisyUI in a Django application. Define the asset pipeline, file ownership, theme tokens, migration process, and verification. Do not use for one template edit, non-Django work, visual design, or backend-only work.
Skill Codex
Create, update, validate, or review a site-root llms.txt file. Use this skill only when the request includes llms.txt. Do not use it for robots.txt, sitemaps, SEO metadata, READMEs, OpenAPI documentation, or AGENTS.md.
Skill Codex
Help coding agents find a repository's purpose, architecture, constraints, workflows, validation, and authoritative sources. Use this skill when essential knowledge is unavailable, obsolete, or not enforced. Do not use it for general code review, marketing documents, product documents, or narrow implementation work.
Skill Codex
Build or debug asynchronous OpenAI Responses API workflows in Django. Use this skill for background requests, signed webhooks, response correlation, persistence, and HTMX status polling. Do not use it for generic OpenAI calls, non-Django consumers, other webhook providers, or frontend-only polling.
Skill Codex
Configure or troubleshoot npm package publication with GitHub Actions and npm Trusted Publishing. Use this skill for JavaScript or TypeScript packages. Also use it for the npm package in a mixed-language repository. Do not use it for applications or repositories without an npm package. Do not use it for generic CI…
Skill Codex
Configure or troubleshoot PyPI publication for PDM packages with GitHub Actions and Trusted Publishing. Use this skill for the Python package in a mixed-language repository. Do not use it for applications or repositories without a Python distribution. Do not use it for generic CI, containers, or token uploads unless…
Skill Codex
Review an OpenAI Agents SDK design, prototype, evaluation system, or deployment plan for production readiness. Assess architecture, tool safety, approvals, failures, evaluations, observability, rollout, cost, privacy, and human control. Do not use this skill as the source for current SDK syntax. Do not use it for…
Skill Codex
Create, update, or validate Codex skill icons. Use this skill for the small SVG, the 100x100 PNG, and the icon fields in agents/openai.yaml. Do not use it for app icons, favicons, badges, unrelated artwork, or skill work that does not include an icon.
Skill Codex
Design, implement, or review typed LLM output. Use constrained generation, validation, limited retries, and explicit failure handling. Use this skill when extracted, classified, or generated objects enter application code. Do not use it for ordinary prompts, unstructured chat, validation without an LLM, or API-key…
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: