Explore skills

Reads an entire file and produces a structured content map showing sections, entities, claims, and gaps. Use when needing to understand a file before editing, checking conversion completeness, or when user says "what is in this file", "content map", "deep read", "read the whole thing", or "check completeness". Does NOT modify files — read-only analysis only.

Write, review, or rewrite user stories. Use this skill whenever the user (or a subagent you spawn) is asked to draft, improve, refine, split, rewrite, or review user stories, convert functional requirements into stories, or groom a backlog — even if they don't explicitly mention "user stories". Applies anywhere stories are being produced, including prompts like "turn these requirements into ticket

Systematically interrogates a worldbuilding decision, lore proposal, or science derivation through exhaustive questioning until all implications, contradictions, and dependencies are resolved. Use when stress-testing a new concept, validating a proposed rule, or when user says "grill me", "stress test this", "what are the implications", "does this break anything", "think through this with me", "ch

Example skill demonstrating all skill patterns and best practices. Use when user asks for "skill examples", "skill patterns", or wants to learn about skill development.

Configure, adjust, debug, and verify React Flow workflow nodes. Use when working on custom node components, especially for node handles, multi-channel connections, edge ids/styles, NodeResizer behavior, drag handles, nodrag/nowheel areas, and markdown scroll containers.

Use this skill whenever the user wants to build, train, evaluate, or iterate on a supervised machine learning or deep learning model. Triggers include: any mention of training or fitting a model with labeled data, dataset preparation, hyperparameter tuning, cross-validation, model checkpointing, experiment tracking, overfitting, loss curves, metrics, or prediction visualization. Also trigger when

Product discovery framework based on Teresa Torres'' "Continuous Discovery Habits". Use this skill whenever the user is doing product discovery work — even if they do not explicitly say "OST," "Teresa Torres," or "discovery." Triggers include: (1) building, critiquing, or restructuring an opportunity solution tree, (2) identifying, organizing, or prioritizing customer opportunities, (3) designing

Run a pre-deploy browser audit of a live, preview, or local web page for accessibility, SEO, Lighthouse quality, and critical UX issues. Use when asked to audit a page/site before deployment, check WCAG 2.2 AA, WAI-ARIA, Lighthouse, accessibility, SEO, contrast, keyboard navigation, focus states, semantic HTML, forms, alt text, headings, ARIA attributes, best practices, or browser-visible web qual

Use this skill when creating, auditing, or redesigning a public GitHub repository so the repository is easy to understand, trust, share, install, and contribute to. Use together with github-repo-product-naming whenever naming, renaming, positioning, repo slug, About description, or product identity matters.

Maps a research paper or scientific concept onto the universe's physics, showing the chain from real principle to canon formalization. Use when incorporating a new finding, grounding a concept in real science, or when user says "integrate this paper", "map this onto our physics", "ground this concept", or "formalize this research". Does NOT search for papers — use /researching-papers for that.

Write, review, or rewrite user stories following Apprendere's agile practices guide. Use this skill whenever the user (or a subagent you spawn) is asked to draft, improve, refine, split, rewrite, or review user stories, convert functional requirements into stories, groom a backlog, translate a Confluence requirements page into stories, or create/update stories in Jira — even if they don't explicit

Audit a page for WCAG 2.1 AA accessibility issues. Traces the render chain, checks structural/semantic HTML, contrast indicators, ARIA, and outputs a prioritized report.