frontend
Build and polish production-ready frontend interfaces using Emil Kowalski's design-engineering approach.
Skill by therapys
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/therapys-frontend
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, frontend, testing, data
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/frontend
What's inside
- Skill name
frontend- Description
- Build and polish production-ready frontend interfaces using Emil Kowalski's design-engineering approach. Use when creating or restyling web pages, components, or apps; reviewing UI polish; adding or fixing animations and transitions; choosing UI primitives; improving mobile touch behavior; or stress-testing layouts with real-world data. Covers HTML/CSS/JS, React, Vue, and other web frameworks.
- License
- MIT
- Instructions
- 46 lines in SKILL.md · view on GitHub
Files (11)
- LICENSE
- SKILL.md
- UPSTREAM.md
- RECIPES.md · references/animate/
- SKILL.md · references/animate/
- CATALOG.md · references/break-ui/
- SKILL.md · references/break-ui/
- SKILL.md · references/emil-design-eng/
- SKILL.md · references/mobile-native/
- performance-cheatsheet.md · references/
- SKILL.md · references/pick-ui-library/
SKILL.md (first lines)
# Frontend Design Engineering Build interfaces that feel right: purposeful motion, responsive controls, good defaults, and invisible correctness. This replaces the previous aesthetic-first frontend guidance with Emil Kowalski's approach. The code is the deliverable, not a mood board. ## Load the right guidance Paths are relative to this skill's directory, not the project's working directory. 1. **Always read [Design Engineering](references/emil-design-eng/SKILL.md)** before building, polishing, or reviewing UI. It defines the philosophy, motion decisions, component details, and Before/After/Why review table. 2. Load additional guides when relevant: | Task | Read | | --- | --- | | Build an animation, transition, or gesture | [Animate](references/animate/SKILL.md); its [RECIPES.md](references/animate/RECIPES.md) for matching components | | Choose accessible primitives or a frontend dependency | [Pick UI Library](references/pick-ui-library/SKILL.md) | | Mobile layouts, touch, safe areas, viewport, keyboard, PWA | [Mobile Native](references/mobile-native/SKILL.md) | | Stress-test realistic edge cases | [Break UI](references/break-ui/SKILL.md) and its [CATALOG.md](references/break-ui/CATALOG.md) | | Animation performance triage | [Performance Cheatsheet](references/performance-cheatsheet.md) | These are bundled reference guides, not independently installed slash commands. References to `emil-design-eng`, `animate`, `mobile-native`, `pick-ui-library`, or `break-ui` mean the local guides above. Other upstream skills mentioned in those guides are not bundled: do not claim to invoke them. For a motion review or audit, use the Design Engineering checklist and Animate's rules; for other missing workflows, say what's unavailable if it matters. The upstream "Initial Response" blocks and invocation metadata are for standalone skills. Here, follow the user's concrete request immediately; do not insert a canned introduction or wait for another question. The library guide may be read as a reference without a separate explicit invocation. ## Workflow 1. Inspect the existing UI, framework, dependencies, tokens, and project conventions. Identify audience, task, content, states, and constraints. Ask one focused question at a time only where a missing decision materially changes the implementation. 2. Preserve established visual identity and use existing tokens. Do not replace fonts, palettes, layout, or dependencies merely to look different. If a project has additional local design-system guidance, read it and treat its brand-specific layout, typography, surface, and motion rules as authoritative. 3. Choose accessible primitives before hand-rolling dialogs, menus, toasts, or focus management. Reuse installed equivalents; do not churn libraries without a request. Apply React-specific recommendations only in React projects. 4. Gate every animation by frequency and purpose before choosing tool, properties, easing, duration, interruption, and exit. No motion is a valid result. Use the cheapest tool that fits; ship reduced-motion behavior and touch-safe hover gating with it. 5. Implement working, semantic, responsive code. Cover loading, empty, error, disabled, and populated states as applicable. Preserve labels, contrast, visible keyboard focus, focus restoration, and keyboard operation. 6. Verify with available checks and browser tooling. Check narrow and wide layouts, supported themes, realistic content, rapid interruption, keyboard input, and reduced motion. Mobile emulation is not hardware verification. Say plainly which checks you could not run. ## Application guardrails - Use pointer-down for immediate visual feedback, not for committing actions. Keep semantic button/link activation so keyboard users work and pointer users can cancel a press. - Reduced motion must actually disable existing movement and transform transitions, not merely add a fade beside them. Preserve essential state changes and feedback. - Prefer transform/opacity for motion, but do not assume every CSS/WAAPI animation or clip-path is compositor-accelerated. Verify in the target browser; treat blur and layout animation as measured exceptions, not defaults. - Stress-test with plausible or schema-backed values. A dev-only fixture toggle must never ship to production. In a requested audit, report design tradeoffs before fixing; in a requested implementation, address unambiguous bugs within scope. ## Output Ship code in the project's files and summarize changes, checks, and any unverified behavior briefly. For UI reviews, use an actual **Before / After / Why** markdown table. For a dedicated worst-case audit, use Break UI's findings format. Do not claim visual or device verification you did not perform. Source and adaptation notes: [UPSTREAM.md](UPSTREAM.md).
From therapys/dotagents, MIT.
More from therapys/dotagents
- 0.626score
image-generation
therapys
Generate and download images through ChatGPT in the user's signed-in browser, using their ChatGPT subscription rather than API keys or API billing.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
hairline-create
therapys
Use when someone asks for a new Hairline figure, or runs /hairline-create with an idea.
SkillAFreshness: A★ 8Claude Code +9 - 0.592score
flesch-kincaid-proofreader
therapys
Measure and improve the readability of English copy with the Flesch–Kincaid grade-level test.
SkillBFreshness: B★ 8Claude Code +9 - 0.592score
signoz-investigating-alerts
therapys
Diagnose why a SigNoz alert fired by correlating the alert's own signal with neighbor signals (error rate, latency, throughput, CPU/memory), traces, and logs…
SkillBFreshness: B★ 8Claude Code +9 - 0.592score
posthog
therapys
Drive PostHog through the claude.ai `exec` connector — query analytics and entities (HogQL, insights, funnels, retention, web analytics), investigate LLM…
SkillBFreshness: B★ 8Claude Code +9 - 0.587score
autonomous-maintainer
therapys
Run the agent as an autonomous maintainer of a product — set it up once, then loop on small, verified, logged improvements while keeping the product…
SkillBFreshness: B★ 8Claude Code +9 - 0.587score
compress-skills
therapys
Compress one or more SKILL.md files so they consume less context on load while preserving 100% of their value — same triggers, capabilities, guardrails…
SkillBFreshness: B★ 8Claude Code +9 - 0.587score
extract-design-system
therapys
Reverse-engineer a project's real, shipped design language into a reusable design skill, so any agent can build or restyle pages that match it.
SkillBFreshness: B★ 8Claude Code +9 - 0.587score
ship
therapys
Take the current changes from a dirty tree to an open pull request — branch, commit, push, and open the PR.
SkillBFreshness: B★ 8Claude Code +9 - 0.587score
update-agents-md
therapys
Generate or refresh a repo's AGENTS.md (the source-of-truth agent context file) and its one-line CLAUDE.md pointer.
SkillBFreshness: B★ 8Claude Code +9 - 0.584score
gog
therapys
Use the gog CLI for safe Google Workspace automation: Gmail and email, Calendar and events, Drive files, Docs, Sheets, Contacts, Tasks, Chat, and other Google…
SkillBFreshness: B★ 8Claude Code +9 - 0.584score
teach
therapys
Teach the user anything so it actually locks in and is understood, not just memorized.
SkillBFreshness: B★ 8Claude Code +9
Signals
- Stars
- 8
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 13, 2026 (15 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/therapys/dotagents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from therapys
- 0.626score
image-generation
therapys
Generate and download images through ChatGPT in the user's signed-in browser, using their ChatGPT subscription rather than API keys or API billing.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
hairline-create
therapys
Use when someone asks for a new Hairline figure, or runs /hairline-create with an idea.
SkillAFreshness: A★ 8Claude Code +9 - 0.592score
flesch-kincaid-proofreader
therapys
Measure and improve the readability of English copy with the Flesch–Kincaid grade-level test.
SkillBFreshness: B★ 8Claude Code +9 - 0.592score
signoz-investigating-alerts
therapys
Diagnose why a SigNoz alert fired by correlating the alert's own signal with neighbor signals (error rate, latency, throughput, CPU/memory), traces, and logs…
SkillBFreshness: B★ 8Claude Code +9 - 0.592score
posthog
therapys
Drive PostHog through the claude.ai `exec` connector — query analytics and entities (HogQL, insights, funnels, retention, web analytics), investigate LLM…
SkillBFreshness: B★ 8Claude Code +9 - 0.587score
autonomous-maintainer
therapys
Run the agent as an autonomous maintainer of a product — set it up once, then loop on small, verified, logged improvements while keeping the product…
SkillBFreshness: B★ 8Claude Code +9
Cite this page
frontend skill. Agent Mart. https://agentmart.dev/skills/therapys-frontend (last updated 2026-10-24)