rlaope/oh-my-hermes / .claude/agent-skills/omh-frontend
omh-frontend
Verified[omh] Building or polishing a web or terminal UI.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.8 KB |
| references/chart-styling.md | markdown | 5.5 KB |
| references/component-registry-adoption.md | markdown | 8.7 KB |
| references/design-system-contract.md | markdown | 15.4 KB |
| references/details.md | markdown | 7.0 KB |
| references/editorial-layout.md | markdown | 6.5 KB |
| references/forms-and-input.md | markdown | 8.5 KB |
| references/mobile-density-gate.md | markdown | 6.5 KB |
| references/reference-token-extraction.md | markdown | 4.1 KB |
| references/rendered-scene-craft.md | markdown | 3.9 KB |
| references/screenshot-loop.md | markdown | 5.8 KB |
| references/scroll-motion-libraries.md | markdown | 7.0 KB |
| references/taste-foundations.md | markdown | 13.1 KB |
| references/tui-craft.md | markdown | 7.2 KB |
| references/web-vitals-budgets.md | markdown | 3.6 KB |
| toolkit/LICENSE.upstream | other | 1.3 KB |
| toolkit/README.md | markdown | 9.5 KB |
| toolkit/examples/phone-clean.html | other | 1012 B |
| toolkit/examples/phone-overflow.html | other | 891 B |
| toolkit/scripts/phone_check.py | script | 28.7 KB |
| toolkit/upstream-manifest.json | config | 3.1 KB |
SKILL.md
View on GitHub---
name: "omh-frontend"
description: "[omh] Building or polishing a web or terminal UI."
license: MIT
compatibility: "Requires the omh CLI on PATH (pip install oh-my-hermes)."
metadata:
hermes:
tags: [workflow, oh-my-hermes, materials]
category: materials
phase: frontend-design
role: operator
quality_tier: frontend-design-gated
---
# Frontend
This is an OMH `frontend` workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
## Why This Exists
`frontend` gives OMH a first-class web UI creation and polishing workflow so Hermes can prepare high-quality layout, design-system, accessibility, performance, and visual-QA handoffs without becoming the hidden coding or browser runtime.
## Do Not Use When
- The user needs a broad premium-quality gate across web, deck, PDF, poster, or publishing outputs; use `omh-design-quality-gate`.
- The user wants a disposable wireframe or mocked interaction to settle one interaction question before planning; use `omh-decision-prototype`.
- The user only needs a file, deck, PDF, spreadsheet, HWP, or attachment package; use `omh-materials-package` or `omh-deliverable-package`.
- The user only needs an image card or infographic prompt; use `omh-image-cards`.
- The user asks to mark a UI as visually passed without fresh rendered evidence; use `omh-visual-qa` and keep PASS blocked until observed.
## Examples
Read `references/details.md` first.
## Completion Checklist
Read `references/details.md` first.
## Recovery Notes
- If the target surface is unclear, prepare the brief with a route/component gap instead of inventing pages.
- If no visual reference exists, set a domain-fit quality bar and request references only when the decision changes layout or brand direction.
## When to Use
Use when Hermes should shape or improve a web/frontend or terminal (TUI) surface before implementation: layout, design system, responsive states, accessibility, performance, motion, and anti-generic visual quality.
Strong routing signals: `frontend`, `front-end`, `front end`, `frontend skill`; all of them in `references/details.md`.
## Catalog Metadata
Category: `materials`
Phase: `frontend-design`
Quality tier: `frontend-design-gated`
Reasoning demand: `standard`
Quality bar:
- Name the product goal, audience, target surfaces, routes, states, and visual quality bar.
- Hold the named bar: what a senior product designer at a top-tier product company (the Linear/Stripe/Supabase class) would sign off on — technically clean but flat output fails it. Load `references/taste-foundations.md`, name one primary taste direction, and reject the anti-slop patterns it lists.
- Name the model's own default aesthetic before inheriting it — the editorial prior of cream grounds, serif display faces, and muted terracotta accents suits editorial, portfolio, and hospitality briefs and is a failure mode on dashboards, developer tools, fintech, and data-dense UIs. Treat a generic negation ("don't make it look AI", "make it minimal") as unactionable: an override counts only when it carries concrete tokens, a hex palette and a typeface stack recorded in DESIGN.md. Run the review prompts in `references/taste-foundations.md` over framework blue, glass and gradient surfaces, default UI typefaces, bounce easing, blanket shadows, eyebrow/title/description stuffing, uniform column grids, and CJK body under the 14px Korean floor.
- When the target surface is a terminal UI (TUI), load `references/tui-craft.md` and hold the same bar there: default widgets are scaffolding, not finished UI; borders spent sparingly with spacing and a muted-color ladder doing the hierarchy; one named terminal aesthetic; verification rendered at 80x24 and 120x40 minimum with the pasted output as the screenshot-equivalent.
- Use references and domain fit to avoid generic AI-looking frontend output; when the user supplies a visual reference, load `references/reference-token-extraction.md` and extract tokens into the contract instead of eyeballing.
- Prepare a concrete design-system contract before implementation handoff: load `references/design-system-contract.md` and write DESIGN.md before the first component — no component code before the contract exists. A new DESIGN.md is Google's DESIGN.md format (YAML token front matter, its sections in its order) plus OMH's own sections; a file in OMH's earlier numbered layout stays valid and is converted only when the user asks. When Hermes' bundled `design-md` skill is available, author, lint, diff, or export a file in the format through it, never a file in the earlier layout; lint is evidence only from a run that executed, otherwise `not_observed`.
- Query the local design reference data before fixing tokens: `omh design data --kind palette|font|ux --context <product context>` returns curated palettes, font stacks with CJK notes, and UX guidelines offline. Those rows inform DESIGN.md; the contract, not the query, still gates the code.
- Scroll-driven motion is a decision with a bill: load `references/scroll-motion-libraries.md`, take the native path (CSS `scroll-behavior`, scroll-driven animations, `IntersectionObserver`, scroll-snap) unless one interpolated scroll position feeds several consumers, and when a library is chosen (Lenis is the reviewed record) name its reduced-motion branch, anchors, nested scroll, teardown, and INP budget in the contract.
- Copied component source is the project's to fix: before adopting from a shadcn-style registry, load `references/component-registry-adoption.md` (license, dependencies, reduced motion, ARIA, keyboard/touch, token mapping, one hero effect per view). Theme charts through tokens, not config literals: load `references/chart-styling.md`.
- A 3D or canvas scene (WebGL, a three.js-style engine, a voxel world) is judged on its first frame: load `references/rendered-scene-craft.md`, boot on the view the scene's own title and copy promise, light it with a warm-or-cool key, a sky fill, explicit tone mapping, shadows, and fog, and make every small animated object read as what it is. A clean console is not a finished scene.
- For first-time UI creation, name the initial generation branch, reference direction, reusable primitives, state coverage, and required visual QA path.
- Cover responsive layout, empty/loading/error states, hover/focus/active states, CJK text, accessibility, and performance expectations.
- For a new page or a redesign, load `references/editorial-layout.md` before choosing the layout.
- For a surface people use on a phone, load `references/mobile-density-gate.md`; measure with `toolkit/scripts/phone_check.py` (setup in `toolkit/README.md`: `skill_view(name='omh-frontend', file_path='toolkit/README.md')`) when a browser is available, otherwise the measurement is `not_observed`.
- When the surface reads or writes remote data, load the `omh-frontend-refactor` skill's `omh-frontend-refactor/references/state-discipline.md` (sections 1 and 4-6) before writing the component: server state lives in a query cache, each mutation names the query keys it invalidates, and an optimistic write ships with its rollback.
- When the surface has a form, a text composer, or a dialog, load `references/forms-and-input.md` before writing it: labelled controls, errors shown after the user commits a value, server field errors mapped onto their fields, one submit in flight, an Enter-to-send that waits for IME composition, and focus returned when a dialog closes.
- Check the browser-support target before using a newer platform feature: a feature newer than the target (by default, anything only Baseline Newly available) needs feature detection plus a fallback, or a deliberate target change; suggest recording the target in the repository's agent instruction file (`omh-agent-instructions` owns that file).
- State performance as a budget, not an adjective: load `references/web-vitals-budgets.md`, name one metric with its published bar (LCP, INP, CLS), the device and network class it is judged on, the route and load shape, and the baseline captured under that same profile - before the change. A budget chosen after seeing the result describes what happened instead of gating it.
- Attribute before optimizing: name the LCP element and its dominant phase, the interaction that produced the worst INP and where the time went, or the node that shifted and what moved above it. A list of optimizations with no attribution is folklore, and a change that improved a different element than the one attributed did not fix the metric.
- Keep field and lab apart: a p75 claim needs field data, a lab audit is a diagnostic sample on one device profile, and a lab pass is never a statement about real users.
- While building, look at each change that affects what renders: after it, capture the affected surface and read the capture before the next change, for a 3D or canvas scene the default camera and each declared preset; a change not looked at is not done (`references/screenshot-loop.md`, section `During implementation`).
- After implementation lands on a web surface, load `references/screenshot-loop.md` and require the screenshot iteration loop live-environment-first: capture the running UI at 1440/768/375px, compare against the supplied target or DESIGN.md, list every difference triaged Blocker/High/Medium/Nit with its capture attached, fix, and recapture until the difference list is empty.
- Judge each capture against the reference at the size and density people will see it (the real viewport, the real icon size such as a 24 px toolbar slot), not only a large render; exercise an interactive result with the actions it supports before calling it done.
- Prefer native UI controls, stable dimensions, and realistic content over decorative cards, blobs, and placeholder-heavy screens.
- When the handoff asks for component or interaction tests, read `../omh-verification-gate/references/test-authoring.md` and name the seam each test drives: assert through what a user perceives (role, accessible name, visible text) across the frontend_component_state_inventory/v1 states, never class names or component-internal state, and fake only at the boundaries the shared page lists (network, clock, randomness).
- Keep implementation, browser verification, accessibility/performance checks, visual QA, and deployment as observed-only evidence.
Required inputs:
Read `references/details.md` first.
Expected outputs:
- frontend_design_brief/v1
- frontend_initial_generation_contract/v1 when greenfield
- design_system_contract/v1
- design_reference_selection/v1
- reference_packet/v1 when supplied
- frontend_route_state_matrix/v1
- frontend_component_state_inventory/v1
- frontend_implementation_handoff/v1
- accessibility_performance_expectations/v1
- visual_qa_required/v1
- observed_browser_evidence/v1 when observed
Artifact expectations:
Read `references/details.md` first.
Safety rules:
- Do not claim implementation, browser verification, deployment, Lighthouse, accessibility pass, or visual QA from a prepared frontend brief.
- Reject generic AI-looking UI: one-note palettes, weak hierarchy, cramped cards, ungrounded gradients, decorative filler, and placeholder-heavy copy.
- Require a design-system contract before broad visual changes.
- For greenfield UI, require an initial generation contract before implementation handoff so the first generated screen has tokens, references, primitives, states, and QA expectations.
- Require fresh rendered evidence after the last UI edit before PASS.
- Do not hand off a smooth-scroll integration without its reduced-motion branch, keyboard/anchor/nested-scroll behavior, and teardown named; a `respectReducedMotion` option covers the library own scroll, never the animations the project wrote.
- Do not hand off a copied registry component or text effect without its license read at the source and its reduced-motion branch; decorative duplicates and split characters are `aria-hidden`, and a marquee gets a pause reachable by keyboard and touch.
- Do not report a Core Web Vitals number without the device class, route, and load shape it was measured under; a figure from a different profile than the baseline is not a comparison.
- For Korean/CJK text, clipped glyphs, awkward line breaks, orphan particles, tiny copy, and overflow block visual QA.
- Do not call external design, image, browser, LLM, or network services from OMH core.
## Runtime Evidence
Use the current host's own tools and subagent/task mechanism when available;
otherwise run the same lanes sequentially or name the unavailable capability.
A prepared plan, handoff, checklist, or skill installation is not execution,
review, CI, merge-readiness, or merge evidence. Record actual tool results, or
`not_observed` / `not_available`, in the record; never invent dispatch or host
accounting.
Treat supplied context as advisory, not proof of hidden memory reads or writes.
State scope, constraints, verification, and the stop condition before work.
Reply in the user's own words and the host's own voice: the host's persona owns
reply language, tone, speech level, and sentence endings, progress updates
included (where it sets no language, use the one the user wrote in), and OMH
shapes structure and content only; OMH's record terms
(surface, lane, wrapper, handoff, evidence boundary, not_observed) stay in
records and tool calls, never in the sentence the user reads unless they ask
about one; and when a real unresolved user decision or a useful briefing discussion
remains, offer one specific, content-linked question. Completed work needs no question;
omit unrelated non-action footers and generic offers to continue.
Supporting paths are relative to this skill directory; sibling skill paths are
relative to its parent. Resolve them from the host-provided skill base directory
(`{baseDir}` on hosts that provide it), never a hardcoded install location.
A named workflow not installed here is unavailable, not permission to emulate
its host-specific capabilities. Verify through the real surface before done.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |