ui-verify
Run evidence-based verification for recent frontend/UI changes using the repository's existing checks, Storybook, Playwright and accessibility tooling.
Skill by hersti
Chalk Labs
Need help deploying ui-verify?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/hersti-ui-verify
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
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. 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/ui-verify
What's inside
- Skill name
ui-verify- Description
- Run evidence-based verification for recent frontend/UI changes using the repository's existing checks, Storybook, Playwright and accessibility tooling. Use when the user explicitly asks to verify, validate, QA, test, or prove UI work is complete.
- License
- MIT
- Instructions
- 16 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Verify UI work Verification is risk-based, not ritual. 1. Identify changed UI scope and concrete claims needing evidence. 2. Prefer existing project scripts before adding tooling. 3. For reusable components, inspect relevant Storybook stories, interaction states and a11y evidence. 4. For end-to-end behavior, run existing Playwright tests when present. 5. For exploratory coding-agent browser work, use `playwright-cli` if it is installed/available; otherwise do not pretend Playwright Test's CLI is the same agent CLI. Skills-less `playwright-cli --help` discovery is acceptable. 6. Run axe where configured and manually check keyboard/focus/reduced-motion/zoom when automation cannot prove the behavior. 7. Inspect runtime/console errors attributable to the changed flow. 8. If a check fails, report it as failed. If verification was requested without implementation, do not silently rewrite the product. Finish with **verified / failed / not checked**, including commands and browser flows actually exercised. Never imply untested coverage.
From hersti/ui-engineering, MIT.
More from hersti/ui-engineering
- 0.529score
ui-design-direction
hersti
Context-aware design-direction skill for substantial frontend/UI work across marketing sites, editorial surfaces, product apps, dashboards, admin tools…
SkillBFreshness: BClaude Code +9 - 0.529score
ui-setup
hersti
Prepare the current frontend repository for the UI Engineering workflow.
SkillBFreshness: BClaude Code +9 - 0.529score
ui-doctor
hersti
Diagnose whether the current repository is ready for the UI Engineering workflow without changing files.
SkillBFreshness: BClaude Code +9 - 0.529score
ui-engineering
hersti
Orchestrates substantial frontend and UI work with audit-first context, product-aware design direction, shadcn-aware component engineering, Storybook state…
SkillBFreshness: BClaude Code +9 - 0.524score
ui-motion
hersti
Motion-design and animation-engineering guidance for web UI.
SkillBFreshness: BClaude Code +9 - 0.524score
ui-shadcn
hersti
Project-aware shadcn/ui component engineering for React web projects.
SkillBFreshness: BClaude Code +9 - 0.519score
ui-react-engineering
hersti
React and Next.js engineering guidance for frontend UI implementation.
SkillBFreshness: BClaude Code +9 - 0.519score
ui-design-system-audit
hersti
Read-only design-system extraction and consistency audit for an existing frontend.
SkillBFreshness: BClaude Code +9 - 0.519score
ui-storybook
hersti
Storybook engineering guidance for reusable web components, stories, interaction tests, docs, and a11y coverage.
SkillBFreshness: BClaude Code +9 - 0.519score
ui-interface-review
hersti
Independent read-only interface review for substantial frontend work.
SkillBFreshness: BClaude Code +9 - 0.516score
ui-recon
hersti
Read-only reconnaissance of an existing frontend repository and running UI before substantial redesign or design-system work.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 27, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/hersti/ui-engineering
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hersti
- 0.529score
ui-design-direction
hersti
Context-aware design-direction skill for substantial frontend/UI work across marketing sites, editorial surfaces, product apps, dashboards, admin tools…
SkillBFreshness: BClaude Code +9 - 0.529score
ui-setup
hersti
Prepare the current frontend repository for the UI Engineering workflow.
SkillBFreshness: BClaude Code +9 - 0.529score
ui-doctor
hersti
Diagnose whether the current repository is ready for the UI Engineering workflow without changing files.
SkillBFreshness: BClaude Code +9 - 0.529score
ui-engineering
hersti
Orchestrates substantial frontend and UI work with audit-first context, product-aware design direction, shadcn-aware component engineering, Storybook state…
SkillBFreshness: BClaude Code +9 - 0.524score
ui-motion
hersti
Motion-design and animation-engineering guidance for web UI.
SkillBFreshness: BClaude Code +9 - 0.524score
ui-shadcn
hersti
Project-aware shadcn/ui component engineering for React web projects.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get ui-verify running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
ui-verify skill. Agent Mart. https://agentmart.dev/skills/hersti-ui-verify (last updated 2026-10-24)