design-system-check
Skill1 starsChanged 28 days agoMITView on GitHub
How to make a UI change against docs/wiki/design-system.md — read token roles first, reference roles instead of raw values, and verify contrast/a11y/state assertions before completing the case. Preloaded into developer by /project:init on UI projects.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- product-llc/claude-skillstheir own version, first seen Oct 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- product-llc/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adversarial-reviewSkill
- clean-architectureSkill
- decision-recordingSkill
- dispatch-handoffSkill
- feature-branchingSkill
- finding-dispositionSkill
- git-recoverySkill
- gotcha-recordingSkill
- human-checkpointSkill
- plan-reviewSkill
- plan-writingSkill
- pr-createSkill
- simplicity-ladderSkill
- spec-writingSkill
- subagent-contractSkill
- subagent-dispatchSkill
- tdd-loopSkill
- update-toolkitSkill
- wiki-updateSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
If a task changes visual output and docs/wiki/design-system.md does not exist, stop and report: either the task is not a UI change or …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Checking a UI Change Against the Design System
docs/wiki/design-system.md asserts roles and contracts; the project's token file holds raw values.
Precondition
If a task changes visual output and docs/wiki/design-system.md does not exist, stop and report: either the task is not a UI change or design-system.md must be created first. Never invent tokens; record unknowns in open_questions or escalate.
Procedure
- Read before writing:
Design intention,Token binding, relevant token sections,State & feedback patterns,Accessibility contract, andComponent inventory(extend listed components via their entity page; spec unlisted ones with Behavior cases before building). - Reference roles, never raw values (write
accent, not hex). Every raw value in touched files must be:- replaced with an existing token reference,
- added as a new role in
design-system.mdand the token file in the same change, or - documented as a deliberate one-off under
design-system.md § Boundarieswith its reason.
- Sweep touched files for raw values (
#[0-9a-fA-F]{3,8}\b|rgba?\(|[0-9]+px|[0-9]+ms) and verify:- Colour pairings: measure actual contrast ratio and record in
Measured(never guess; use<TBD>if unmeasurable). - Interactive elements: visible focus, minimum hit target met, keyboard operable.
- Animations: respects
prefers-reduced-motion. - States (loading, empty, error, success, disabled): uses canonical pattern.
- Colour pairings: measure actual contrast ratio and record in
- Update
docs/wiki/design-system.mdin the same change (inventory status, new roles/steps/breakpoints, measured contrast ratios,updated).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

