ui-guidance
Skill4 starsChanged 12 days agoMITView on GitHub
Baseline overlay for routine graphical UI and frontend changes that preserve the existing design language; use `ui-design-guidance` for redesign, polish-heavy implementation, or deep UX review. Compose with matching implementation guidance. Not for terminal UIs or pure plotting.
In this repository47 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agentic-sdlc-improvementSkill
- agentic-sdlcSkill
- agent-skill-generatorSkill
- agents-md-generatorSkill
- backend-guidanceSkill
- backend-systems-guidanceSkill
- bounded-delegationSkill
- chrome-devtools-axiSkill
- coding-guidance-bashSkill
- coding-guidance-cppSkill
- coding-guidance-goSkill
- coding-guidance-go-tuiSkill
- coding-guidance-pythonSkill
- coding-guidance-qtSkill
- context-engineeringSkill
- deepseek-harnessSkill
- design-md-authorSkill
- development-contract-processSkill
- development-contract-repo-overlay-templateSkill
- development-contract-systemSkill
- documenter-coauthoringSkill
- documenterSkill
- dream-thinkingSkill
- fuse-skillsSkill
- godotSkill
- go-testing-with-testifySkill
- jekyllSkill
- lighthouseSkill
- playwright-testingSkill
- project-config-and-testsSkill
- project-core-devSkill
- project-platform-diagnoseSkill
- project-release-maintainerSkill
- project-vendor-boundarySkill
- prompt-engineeringSkill
- recursive-thinkingSkill
- security-identity-accessSkill
- securitySkill
- setup-playwrightSkill
- story-clarifierSkill
- story-implementation-plannerSkill
- story-repo-scoutSkill
- story-to-plan-orchestratorSkill
- tester-mindsetSkill
- thinkingSkill
- ui-design-guidanceSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Use alongside the matching principle skill (for example, coding-guidance-cpp) when the change touches UI or frontend code.
- Very specific: line 21
Use this as the thin default overlay for ordinary UI work.
- Very specific: line 22
If the task is redesign-heavy, frontend-polish heavy, or needs a stronger UX review checklist, prefer ui-design-guidance.
- Distinctive: line 27
add a small control that matches nearby components -> use this skill
- Distinctive: line 56
Verify visual output manually or with snapshot tests if the repo supports them.
- Distinctive: line 58
If the repo does not document breakpoints, design tokens, or visual test tooling, derive them from nearby UI code and record the fallback …
- Distinctive: line 64
Design language check: before adding a new visual element, search the codebase for an existing element that serves a similar purpose.
- Distinctive: line 68
Evidence fallback: when the repo lacks UI docs, use the nearest existing component or screen as the baseline and name the files inspected.
- Distinctive: line 70
Accessibility bar: if the change adds interactive elements, verify keyboard navigation and screen reader labels.
- Distinctive: line 73
Layout stability: if the change affects layout, test at the repo's supported viewport sizes.
- Distinctive: line 87
when automated UI verification is absent, any implementation or review note you produce names the screenshots, snapshots, or manual checks …
≈ “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
UI/Frontend Guidance
This is a composable overlay, not a standalone workflow.
Use alongside the matching principle skill (for example,
coding-guidance-cpp) when the change touches UI or frontend code. Add
project-core-dev only when repository-specific completion checks still need
to be discovered or reported.
Choose the activity before applying the rules below:
- for implementation, make only the requested UI changes and validate them
- for review, inspect and report prioritized findings with evidence; do not edit files or require findings to be fixed unless the user also asks for remediation
Use this as the thin default overlay for ordinary UI work.
If the task is redesign-heavy, frontend-polish heavy, or needs a stronger UX
review checklist, prefer ui-design-guidance.
Routing examples:
- add a small control that matches nearby components -> use this skill
- fix spacing, labels, or responsive behavior within the existing visual language -> use this skill
- redesign a page, introduce a new visual direction, or perform a UX-heavy
release review -> use
ui-design-guidance - product-security or permission-sensitive UI flows -> use
securityfirst when the main risk is trust, identity, or authorization rather than presentation; addsecurity-identity-accesswhen the security scope centers on identity, sessions, recovery, or tenant authorization
When to use
The repo includes graphical UI or web frontend code — web views, desktop UI, embedded panels, or rendering layers.
Not for
Terminal UIs belong to their framework's guidance, including
coding-guidance-go-tui for Bubble Tea. Pure data visualization or plotting
without product-interface work is also out of scope.
Rules
- Preserve the existing design language unless the task explicitly calls for redesign. Do not introduce new color palettes, spacing systems, or component patterns without justification.
- Accessibility, layout stability, and responsive behavior are part of done — not follow-up work.
- UI changes must not bypass the repo's test and build hygiene.
- Verify visual output manually or with snapshot tests if the repo supports them.
- If the repo does not document breakpoints, design tokens, or visual test tooling, derive them from nearby UI code and record the fallback evidence in any implementation or review note you produce.
Decision Heuristics
- Design language check: before adding a new visual element, search the codebase for an existing element that serves a similar purpose. Match its spacing, color tokens, and component structure unless the task requires divergence.
- Evidence fallback: when the repo lacks UI docs, use the nearest existing component or screen as the baseline and name the files inspected.
- Accessibility bar: if the change adds interactive elements, verify keyboard navigation and screen reader labels. If the repo has no a11y testing, add manual verification to the review checklist.
- Layout stability: if the change affects layout, test at the repo's supported viewport sizes. If those are undocumented, test at the common breakpoints already exercised by nearby code or styles. Flag layout shifts that appear on resize or content change.
Validation
For implementation, a UI change is done when, in addition to the base implementation skill's validation:
- visual output matches the existing design language or the requested redesign
- interactive elements are keyboard-navigable and expose appropriate names, roles, or labels
- layout is stable across supported viewports
- when automated UI verification is absent, any implementation or review note you produce names the screenshots, snapshots, or manual checks used as evidence
For review, completion means prioritized findings name the affected interaction or screen, supporting evidence, likely user impact, and any validation gap. Open findings do not make the review incomplete.
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.

