frontend-engineering
Skill2 starsChanged 2 months agoMITView on GitHub
Use when building, styling, fixing, or reshaping an interface, component, page, or frontend interaction. Use ui-ux-review for a read-only assessment of existing UI.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- juninmd/skillstheir own version, first seen Nov 8, 2026
- hamzzaqureshi/gravidextheir own version, first seen Nov 8, 2026
- rogue-dev-studio/ai-agents-roguetheir own version, first seen Nov 1, 2026
- DevelopersGlobal/ai-agent-skillstheir own version, first seen Oct 25, 2026
- PhoenixNest/AGENT-GLOBAL-BASEtheir own version, first seen Oct 20, 2026
- TylerAkins/ai-agent-skillstheir own version, first seen Oct 15, 2026
Used with
Projects with it also use observability, api-design and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
OpenAISkillobservability
Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.
Also in 3 projects that use this
MicrosoftSkillapi-design
Guide for designing and documenting RESTful APIs. Use when asked to design an API, create endpoints, or document an API.
Also in 4 projects that use this
Microsoft AzureSkillgit-workflow
Squad branching model: dev-first workflow with insiders preview channel
Also in 3 projects that use this
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- DevelopersGlobal/ai-agent-skills★ 216same name
- magnus919/agent-skills★ 172same name
- d-padmanabhan/agent-engineering-handbook★ 17same name
- vekzz-dev/opencode-skills★ 4same name
- JimmyVGDY/codex-long-term-assistant-skills★ 3same name
- juninmd/skills★ 2same name
- PhoenixNest/AGENT-GLOBAL-BASE★ 2same name
- rogue-dev-studio/ai-agents-rogue★ 2same name
- hamzzaqureshi/gravidex★ 1same name
- TylerAkins/ai-agent-skills★ 1same name
3 more not listed
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 repository13 other files it gives its agents.
- architecture-planningSkill
- backend-engineeringSkill
- code-reviewSkill
- database-api-evolutionSkill
- deployment-safetySkill
- design-researchSkill
- excalidraw-diagramsSkill
- execution-loopSkill
- explain-with-diagramsSkill
- hyperframes-videoSkill
- systematic-debuggingSkill
- test-verifySkill
- ui-ux-reviewSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use semantic elements and appropriate labels.
- Distinctive: line 18
Keep component responsibilities clear and avoid unnecessary derived state, render side effects, data waterfalls, and unbounded DOM lists.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Frontend engineering
Build the requested experience within the product's design language and actual frontend stack. Inspect the changed route, shared components, tokens, state/data conventions, assets, and build configuration first. Reuse working patterns; do not upgrade frameworks or introduce a component library as a side effect.
For a new interface or requested redesign, choose a visual direction tied to the product, audience, and content. Set a coherent type scale, spacing rhythm, hierarchy, and restrained color system. Put emphasis where the user's primary task needs it. Avoid decorative cards, gradients, motion, or oversized headings that obscure the information. Preserve existing visual identity on a narrow fix.
Model the user journey and its states: initial, loading, empty, success, validation error, service failure, disabled, and permission-limited where relevant. Keep input during recoverable errors. Prevent duplicate submissions when they create duplicate effects. Make optimistic updates reversible and stale responses harmless. Match local, shared, and server state ownership to the application's existing architecture; do not impose a framework-specific state ladder.
Use semantic elements and appropriate labels. Support keyboard navigation, visible focus, sensible tab order, and focus management for dialogs and route changes. Check contrast, zoom/reflow, reduced motion, and accessible error feedback in the affected UI. ARIA should supplement native semantics when needed.
Check that users can find the requested actions, identify the entity they are editing, and distinguish an unsaved preview from persisted settings. Compare initial defaults with validation rules and existing saved state; explain real state differences instead of dismissing a contradictory UI as user error. Exercise save and reload when persistence matters. Preserve existing capabilities during simplification. If the user requests a preview for approval, prepare it before implementing that design; do not impose this gate on other UI work.
Keep component responsibilities clear and avoid unnecessary derived state, render side effects, data waterfalls, and unbounded DOM lists. Confirm compiler and framework capabilities before using version-specific APIs or adding manual memoization. Profile a reported slowdown with systematic-debugging before optimizing it.
Use existing repository checks and test-verify for the changed behavior. When browser access is available, exercise the actual flow, inspect loading/error behavior, check console/runtime errors, and view relevant mobile and desktop widths. Review screenshots against the intended hierarchy and layout; a passing build does not prove visual quality. Use available accessibility tooling plus a keyboard walkthrough where the interaction warrants it.
Report what the user can now see or do, the checks actually performed, and concrete limitations such as an unavailable backend or browser. Do not claim screenshots, live integration, or accessibility conformance that was not established.
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.

