mockup
Create HTML mockups when no design was supplied, with real research, then review them with a critical eye.
Skill by jshepelsky
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/jshepelsky-mockup
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, research
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/mockup
What's inside
- Skill name
mockup- Description
- Create HTML mockups when no design was supplied, with real research, then review them with a critical eye. Steps 3 and 4 of /ship.
- License
- MIT
- Instructions
- 27 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Mockup: $ARGUMENTS
`$ARGUMENTS` is `create` or `review`, optionally followed by the work-folder slug.
Never commit, branch, or push. Mockups live in `.claude/work/<slug>/mockups/` and nowhere else; they are not app code.
Read `brief.md` and `plan.md` first. **If `brief.md` says a design was supplied, skip this skill**: tick checkpoints 3 and 4 in `status.md` with "design supplied" and stop.
## `create`
1. **Inventory the screens.** From `plan.md`'s `Design` section, list every screen and every state (loading, empty, error, success, permission denied, mobile and desktop). Each gets a mockup.
2. **Research before drawing.** Look at how the product already looks: pull the real stylesheet, design tokens, component library, fonts, and spacing scale from the repo. Then do real web research on the pattern you're building (a settings page, a checkout, a data table, an onboarding flow): what the best current examples do, what accessibility guidance says, what to avoid. Note sources.
3. **Build the mockups** as self-contained HTML files, one per screen, using the project's real tokens, fonts, and component styles so they look like the product, not a template. If the `frontend-design` skill is available, read it first. Include the real copy from `plan.md`, not lorem ipsum. Make them responsive. Add a `README.md` in the folder listing each file, what it shows, and the research sources.
4. **Show them.** Tell the user the paths and how to open them. Ask for reactions with specific questions ("is the primary action in the right place?", "should empty state link to import?"), each with your recommendation.
## `review`
1. Spawn `essentials:mockup-reviewer` with the work-folder path. In the same message, spawn `essentials:ui-designer` on the mockup files (ask it to report, not edit) and `essentials:copy-reviewer` on the strings. Wait for all three.
2. Merge the findings. Apply every must-fix and should-fix you can resolve directly to the mockup files: missing states, token and component mismatches, contrast, focus, touch targets, copy. Keep the reviewer's research sources.
3. Write `mockups/mockup-review.md`: what changed, what's flagged for the user (each with a recommendation), sources, verdict.
4. Show the user the updated mockups and ask the remaining questions. Stop. When they approve, tick checkpoints 3 and 4 in `status.md` and record the approved mockup list in `plan.md`'s `Design` section.
If the verdict is "revise" after your fixes, re-run `essentials:mockup-reviewer` once. If it's still "revise", stop and talk it through rather than looping.
Next: `/test-plan`.From jshepelsky/claude-essential-plugin, MIT.
More from jshepelsky/claude-essential-plugin
- 0.565score
flaky-test-investigation
jshepelsky
Investigate a flaky or failing test using evidence before proposing a fix.
SkillAFreshness: AClaude Code +9 - 0.565score
humanize
jshepelsky
Rewrite text to remove signs of AI-generated writing — inflated significance, promotional language, em-dash overuse, rule of three, AI vocabulary, copula…
SkillAFreshness: AClaude Code +9 - 0.561score
env-test
jshepelsky
Run the feature's tests against a deployed environment - full suites on staging, read-only and data-safe checks on production.
SkillAFreshness: AClaude Code +9 - 0.561score
phase-plan
jshepelsky
Order the work into phases with dependencies and blockers so development runs in the most efficient sequence.
SkillAFreshness: AClaude Code +9 - 0.561score
dev-setup
jshepelsky
Create and refresh the files that help Claude develop this feature well - CLAUDE.md, the essentials profile, and per-area notes.
SkillAFreshness: AClaude Code +9 - 0.561score
develop
jshepelsky
Build one phase from the phase plan - code, planned tests, every test type, per-phase code review - then hand off with a branch name, commit message, and a…
SkillAFreshness: AClaude Code +9 - 0.561score
document
jshepelsky
Write and audit documentation after a feature ships - CLAUDE.md, process docs, and anything a future session or developer needs.
SkillAFreshness: AClaude Code +9 - 0.561score
deploy
jshepelsky
Get the feature deployed to staging (preferred) or production using the project's real mechanism, with preflight, confirmation, and verification.
SkillAFreshness: AClaude Code +9 - 0.558score
commit
jshepelsky
Stage logical change groups and write a clean commit message from the diff.
SkillAFreshness: AClaude Code +9 - 0.558score
changelog
jshepelsky
Generate release notes from git history since the last tag (or a given range).
SkillAFreshness: AClaude Code +9 - 0.558score
first-run
jshepelsky
One-time setup — detect this codebase and write a profile the essentials agents specialize to.
SkillAFreshness: AClaude Code +9 - 0.553score
dependency-audit
jshepelsky
Audit dependencies for known vulnerabilities, outdated versions, and unused packages.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (6 days ago)
- Last release
- Oct 22, 2026 (6 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jshepelsky
- 0.565score
flaky-test-investigation
jshepelsky
Investigate a flaky or failing test using evidence before proposing a fix.
SkillAFreshness: AClaude Code +9 - 0.565score
humanize
jshepelsky
Rewrite text to remove signs of AI-generated writing — inflated significance, promotional language, em-dash overuse, rule of three, AI vocabulary, copula…
SkillAFreshness: AClaude Code +9 - 0.561score
deploy
jshepelsky
Get the feature deployed to staging (preferred) or production using the project's real mechanism, with preflight, confirmation, and verification.
SkillAFreshness: AClaude Code +9 - 0.561score
env-test
jshepelsky
Run the feature's tests against a deployed environment - full suites on staging, read-only and data-safe checks on production.
SkillAFreshness: AClaude Code +9 - 0.561score
phase-plan
jshepelsky
Order the work into phases with dependencies and blockers so development runs in the most efficient sequence.
SkillAFreshness: AClaude Code +9 - 0.561score
dev-setup
jshepelsky
Create and refresh the files that help Claude develop this feature well - CLAUDE.md, the essentials profile, and per-area notes.
SkillAFreshness: AClaude Code +9
Cite this page
mockup skill. Agent Mart. https://agentmart.dev/skills/jshepelsky-mockup (last updated 2026-10-24)