frontend-engineering
Skill0 starsChanged 3 days agoMITView on GitHub
Implement frontend features reliably within the existing application architecture, conventions, and accessibility requirements.
14 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 versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- 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
- adtn0810/truestack★ 2same name
- juninmd/skills★ 2same name
- PhoenixNest/AGENT-GLOBAL-BASE★ 2same name
- rogue-dev-studio/ai-agents-rogue★ 2same name
- hamzzaqureshi/gravidex★ 1same name
4 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 repository34 other files it gives its agents.
- accessibilitySkill
- admin-panelSkill
- ai-agent-interfaceSkill
- ai-chat-interfaceSkill
- ai-dashboardSkill
- ai-engineeringSkill
- analytics-and-data-visualizationSkill
- animation-and-motionSkill
- api-engineeringSkill
- authentication-and-rbacSkill
- backend-architectureSkill
- component-engineeringSkill
- dashboard-designSkill
- database-engineeringSkill
- design-intelligenceSkill
- design-systemsSkill
- iconographySkill
- image-art-directionSkill
- integrations-and-webhooksSkill
- javascript-typescriptSkill
- performance-optimizationSkill
- premium-landing-pagesSkill
- python-engineeringSkill
- rag-and-knowledge-systemsSkill
- responsive-designSkill
- saas-dashboardSkill
- security-engineeringSkill
- super-admin-panelSkill
- testing-and-qualitySkill
- unslop-engineSkill
- ux-researchSkill
- visual-designSkill
- visual-regressionSkill
- website-architectureSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 13 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
13
Distinctive
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
- Distinctive: line 10
Use for user-facing web changes involving UI architecture, routing, state, forms, data loading, API integration, or frontend reliability.
- Distinctive: line 15
Do not introduce a new framework or state library for a small feature when the current stack already solves the problem.
- Distinctive: line 21
Read package scripts and lockfile, app entry points, routes, components, state/data patterns, API contracts, test setup, styling, and …
- Distinctive: line 30
Keep view rendering separate from side effects where the codebase does so.
- Distinctive: line 34
Use semantic HTML, labels, keyboard behavior, and visible focus.
- Distinctive: line 37
Add or update focused tests for behavior, not implementation details.
- Distinctive: line 38
Run the project's relevant lint, type-check, tests, and build.
- Very specific: line 43
Avoid any, unsafe casts, duplicated source-of-truth state, and success-shaped error fallbacks.
- Distinctive: line 46
Do not silently swallow exceptions or hide failed actions.
- Distinctive: line 47
Do not add a dependency without a concrete capability gap.
- Distinctive: line 51
Use typed results and explicit error handling at an API boundary:
- Distinctive: line 74
Use the project's runtime schema library for larger response contracts.
- Distinctive: line 85
Check correct behavior for success and failure, request races where applicable, keyboard and screen-reader semantics, responsive states, …
- Distinctive: line 91
Use the frontend execution guide for a feature spanning data flow, async state, or multiple UI states.
“Common” is measured: kept by at least 6 in 10 of the 10 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
When to use
Use for user-facing web changes involving UI architecture, routing, state, forms, data loading, API integration, or frontend reliability.
When not to use
Do not introduce a new framework or state library for a small feature when the current stack already solves the problem. Do not broaden a visual task into an unrelated application rewrite.
Inputs and assumptions
Read package scripts and lockfile, app entry points, routes, components, state/data patterns, API contracts, test setup, styling, and accessibility conventions before editing.
Workflow
- Trace the existing feature flow and define expected input, output, loading, empty, error, and success behavior.
- Choose the narrowest module boundary and use existing typed contracts.
- Keep view rendering separate from side effects where the codebase does so; centralize repeated business rules in an established domain layer.
- Handle async cancellation, stale results, errors, and duplicate submits according to existing patterns.
- Use semantic HTML, labels, keyboard behavior, and visible focus.
- Preserve responsive behavior; test long text, empty data, and narrow screens when the UI is affected.
- Add or update focused tests for behavior, not implementation details.
- Run the project's relevant lint, type-check, tests, and build.
Decision rules
- Respect the existing framework and package manager.
- Avoid
any, unsafe casts, duplicated source-of-truth state, and success-shaped error fallbacks. - Validate untrusted data at system boundaries.
- Do not silently swallow exceptions or hide failed actions.
- Do not add a dependency without a concrete capability gap.
JavaScript and TypeScript example
Use typed results and explicit error handling at an API boundary:
type UserSummary = { id: string; displayName: string };
async function loadUser(id: string): Promise<UserSummary> {
const response = await fetch(`/api/users/${encodeURIComponent(id)}`);
if (!response.ok) throw new Error(`User request failed: ${response.status}`);
const data: unknown = await response.json();
if (
typeof data !== "object" ||
data === null ||
!("id" in data) ||
typeof data.id !== "string" ||
!("displayName" in data) ||
typeof data.displayName !== "string"
) {
throw new Error("User response has an invalid shape");
}
return { id: data.id, displayName: data.displayName };
}Use the project's runtime schema library for larger response contracts.
Common failures
- Fetching the same data in multiple components with conflicting state.
- Ignoring rejected promises or returning fake defaults.
- Adding interaction handlers to non-semantic elements.
- Testing only the happy path or only snapshots.
Validation
Check correct behavior for success and failure, request races where applicable, keyboard and screen-reader semantics, responsive states, type safety, and project-standard tests/build.
Supporting guide
Use the frontend execution guide for a feature spanning data flow, async state, or multiple UI states; keep small changes within the established local pattern.
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.

