Skill Claude CodeCodex
Name unfamiliar UI components from descriptions, screenshots, live pages, or DOM/code clues; return ranked aliases, prompt-ready wording, and authoritative links without using namethatui.com. Skip implementation of already-named components.
Skill Claude CodeCodex
Create sleek, low-noise infographic prompts and render workflows with Nano Banana 2 for posts, decks, reports, and explainers. Trigger on infographic, Nano Banana 2, Gemini image, executive visual, blog diagram, or presentation visual. Do NOT use for logos, memes, or raw dashboards.
Skill Claude CodeCodex
Turn supplied websites, apps, images, media, documents, code, or mixed references into a self-contained replication prompt for a fresh session. Default to a website/web app unless another target is named. Skip implementation, rendering, and summaries.
Skill Claude CodeCodex
Run ambitious one-shot websites, web apps, games, simulations, clones, motion pieces, or benchmarks through fresh isolated subagents. Use for one-shot web artifacts, catalogue ideas, or parallel model/harness variants.
Agent
Index completed experiment runs without rewriting their artifacts.
Agent
You are an independent, read-only critic for one website experiment. Judge the built artifact, not the builder.
Agent
You own exactly one website experiment in an isolated initial or recovery context.
Skill Claude CodeCodex
Answer product, PM, stakeholder, or non-engineer questions about app behavior by inspecting code and returning a share-ready plain-English answer. Trigger on product question, PM question, stakeholder answer, how a feature works, or why the app behaves that way. Do NOT use for code changes.
Skill Claude CodeCodex
Turn supplied resources into practical reading notes: topics, interesting ideas, research leads, open questions, and homework todos. Use for articles, PDFs, docs, webpages, videos, transcripts, slides, meetings, books, RFCs, or talks. Do NOT use for code review or exhaustive transcripts.
Skill Claude CodeCodex
Create evidence-backed repository intent docs for AI coding agents, including certainty levels, evidence anchors, open questions, and review workflow. Trigger on document repo intent, REPOINTENT.md, or what this repo is for. Do NOT use for ordinary README polishing.
Skill Claude CodeCodex
Create or improve concise, useful, agent-safe repository READMEs. Use for new README drafts, rewrites, quickstarts, local setup, getting started, contributor docs, or README reviews. Do NOT use for API reference, full product docs, changelogs, or landing pages.
Skill Claude CodeCodex
Prefer ripgrep (rg) for text search, recursive codebase search, filename discovery with rg --files, and machine-readable search output. Trigger on search, grep, ripgrep, rg, find files, or look for pattern. Do NOT use for full-file reads or JSON queries better handled by jq.
Skill Claude CodeCodex
Audit and scaffold .github/workflows/copilot-setup-steps.yml for GitHub Copilot cloud agent environments. Use for missing or broken setup workflows, runner/firewall/dependency/LFS/proxy issues, or Copilot setup repair. Do NOT use for generic GitHub Actions.
Skill Claude CodeCodex
Run /scaffold-hooks to audit, create, or refresh shared repository hooks for Claude Code, Codex, GitHub Copilot, Devin CLI, and OpenCode, together or individually. Skip Git hooks and Husky.
Skill Claude CodeCodex
Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls. Trigger on prompt injection, tool permissions, approvals, AI data handling, RAG poisoning, observability, or safety CI. Do NOT use for non-AI appsec.
Skill Claude CodeCodex
Audit real codebases for SEO: metadata, rendering, crawlability, canonicals, schema, OG/social previews, i18n, sitemaps, robots, internal links, and AI-era search readiness. Trigger on SEO audit, schema, canonical, hreflang, sitemap, title/meta, or AI Overviews. Do NOT use for ads or link building.
Skill Claude CodeCodex
Rewrite or audit ASD-STE100 procedures, descriptions, and safety instructions while preserving technical meaning and exact literals.
Skill Claude CodeCodex
Create, harden, and curate production-grade installable skills and skill libraries. Use for API/CLI/reference skills, invocation design, progressive disclosure, evals, placement, promotion, renames, deprecation, or catalog/router consistency. Skip trivial one-file utilities.
Agent
Analyze a skill and user feedback, fix the target with the smallest coherent change, and distinguish local corrections from reusable lessons. Read the complete in-scope package, repository policy, evals, wrappers, publication surfaces, and any reviewer report before proposing changes.
Agent
Audit a skill or skill-library change against its actual repository contract. Read every in-scope canonical skill, support artifact, wrapper, eval, policy file, catalog, registry, router, installer surface, and dependent before judging it.
Skill Claude CodeCodex
Explain this fixture repository's established installable-skill layout. Use only for repository-layout orientation.
Skill Claude CodeCodex
Diagnose a failed release from logs, status output, and repository state.
Skill Claude CodeCodex
Validate and publish an authorized release after resolving its repository and environment.
Skill Claude CodeCodex
TODO: describe when this package-checking skill should trigger.