TDD is the red → green loop. This skill is the reference that makes that loop produce tests worth keeping: what a good test is, where tests go, the anti-patterns, and the rules of the loop. Every section applies on every cycle: consult them before and during the loop, not after. When exploring the codebase, read GLOSSARY.md (if it exists) so test names and interface vocabulary match the project's domain language, and respect ADRs in the area you're touching. Tests…
Move issues on the project issue tracker through a small state machine of triage roles. If this repo treats external pull requests as a request surface (see the issue-tracker config), triage covers them too: a PR is an issue with attached code, using the same roles, same states, and same machine, with a few deltas marked "for a PR" below. Resolve a bare #42 to an issue or PR per the tracker config. Every comment or issue posted to the…
Additional context needed: performance constraints. Use motion to explain state, relationship, and hierarchy, or to create one authored moment the surface has earned. Decoration without purpose is animation debt. Inspect the existing motion language, interaction states, target devices, and performance budget. Find only the places where motion would: Ask only when a material constraint cannot be inferred. Do not animate a static area merely because it exists. Write a short plan before implementation: The focal moment must come from this…
Resolve one stable target, run two independent assessments, synthesize a design critique, persist a snapshot, and ask the user what to improve next. The chat response is the primary deliverable; the snapshot is an archive of that run. Every later command also accepts the resolved target directly and derives the same slug internally; never hand-write a slug. If this exits non-zero, skip persistence and trend for this run, but continue the critique. 3. Read .impeccable/critique/ignore.md if it exists. Drop matching…
This skill gives you the tools and permission to create design that earns to be called out-of-distribution craft: Whereas before, your design work would have been safe, timid and measured, you now approach every design task as an award-winning design director with impeccable understanding for what makes exceptional design work: production-grade code, peak creativity, a clear POV, deep understanding of the needs of the client and users, and exceptional craft. Core principles: - Go all out. No hedging, no shortcuts.…
Additional context needed: quality bar and shipping constraints. Polish is refinement, never concealed redesign. Preserve the incumbent visual world, content, behavior, and everything outside scope. If the concept itself is wrong, say so and recommend redesign or bolder instead of smuggling in a replacement. A detector result is defect evidence, not proof of quality. Inspect the rendered experience and real interaction path. Read DESIGN.md and representative tokens, shared components, patterns, and neighboring flows. If no formal system exists, use coherent…
Build icons that transform through actual shape transformation, not crossfades. Any icon can morph into any other because they share the same underlying 3-line structure. Every icon is composed of exactly three SVG lines. Icons that need fewer lines collapse the extras to invisible center points. This constraint enables seamless morphing between any two icons. Each line has coordinates and optional opacity: Icons needing fewer than 3 lines use collapsed lines—zero-length lines at the center: Each icon has exactly 3…
Review animation code for correct timing function selection based on interaction type. Ask: Is this motion reacting to the user, or is the system speaking?
Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
Expert heuristic evaluation of an interface. One job: find usability problems, score them against Nielsen's 10, and prioritize fixes. Do not redesign, rewrite code, or expand into visual polish / a11y deep-dives unless the user also asks. Anti-overlap rules: State the screen, flow, or feature under review. Narrow oversized requests to the highest-traffic complete task path and say so. Identify product type, primary user goal, platform conventions, and whether you can inspect source, a running UI, or both. Prefer evidence…
Apply psychology and interaction principles to a screen or flow. One job: explain and prioritize principle-level guidance. Do not run a Nielsen scorecard here — that belongs to ux-heuristics. Do not redesign or edit code unless asked. Anti-overlap rules: Default quick. State the screen/flow and primary task. Complete or simulate the primary path. Prefer evidence over speculation. Do not edit product code unless asked to implement.
One declaration that adapts on its own beats a set of breakpoints, and a CSS feature beats a script. Use JavaScript only where it makes a result nicer that already works without it. Each technique is a set of properties and values, so it works in any authoring system. Class names in the examples are placeholders. Write the declarations in what the project already uses, whether that is a stylesheet, Tailwind utilities or StyleX objects. Where that system has no…
Heuristic UX evaluation of screens, flows, and product interfaces using Nielsen's 10 usability heuristics as the sole scorecard. Use when the user asks for a UX audit, heuristic evaluation, usability review, Nielsen heuristics check, or says ux-heuristics, heuristic review, usability heuristics, or evaluate this flow against heuristics. For Laws of UX, progressive disclosure, Fitts/Hick/Peak-End, and related principles, use ux-principles instead.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
sanmidableSkill