explore-code
15,943Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the research
paper-context-resolver
15,935Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow re
ai-research-reproduction
15,934RigorPilot reproduce-mode orchestrator for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minima
run-train
15,933Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively f
safe-debug
15,933Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint
repo-intake-and-plan
15,932Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the READM
explore-run
15,931Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researche
env-and-assets-bootstrap
15,931Rigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first
minimal-run-and-audit
15,931Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from th
obsidian-vault
15,824Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize note
git-guardrails-claude-code
15,622Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wan
edit-article
15,475Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improv
Setup Pre-Commit Hooks
15,151Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-comm
writing-shape
15,061Take a markdown file of raw material and shape it into an article through a conversational session - drafting candidate openings, growing th
scaffold-exercises
15,040Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold e
writing-fragments
15,035Grilling session that mines the user for fragments - heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) -
writing-beats
14,999Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write onl
browser-act
14,653Browser automation CLI for AI agents. NEVER run browser-act commands directly via Bash - always invoke this skill first. Use browser-act whe
migrate-to-shoehorn
14,648Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests,
UI/UX Pro Max - Design Intelligence
13,413UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines
Fun Brainstorming
13,315Invoke before any creative or architectural work - feature design, component creation, or behavioral changes. A streamlined brainstorming pr
supabase
12,993Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Q
Design Engineering
12,303This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make softw
browser-act-skill-forge
11,575Explores websites via browser-act automation and packages discoveries into callable Skill packages (SKILL.md + scripts) - execute reliably a