design
Design and refine context-fit user interfaces, then verify the rendered result.
Skill by luizomf
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/luizomf-design
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, productivity
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/design
What's inside
- Skill name
design- Description
- Design and refine context-fit user interfaces, then verify the rendered result.
- License
- MIT
- Instructions
- 28 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Design Create a visually coherent interface that fits its users, task, content, product, and existing system. Treat beauty as contextual fitness plus deliberate craft, not conformance to a fashionable style. ## Process 1. **Ground the direction.** Inspect the current interface, repository conventions, reusable components, supplied references, and real content. State one sentence covering the audience, primary task, and material constraints. Existing product decisions outrank novelty unless redesign is explicitly in scope. This step is complete when every visible design decision can be traced to the product, content, reference, or stated direction. 2. **Choose a visual thesis.** Define one sentence for the intended character and hierarchy. Select a coherent typography, color, spacing, shape, imagery, and motion treatment; introduce at most one signature move unless the reference requires more. Prefer purposeful composition over decorative filler, repeated card grids, or fashionable effects without a product role. This step is complete when the thesis distinguishes the interface without competing with its primary task. 3. **Design the whole requested surface.** Preserve accurate content and information hierarchy. Reuse the established design system before adding tokens or components. Cover the relevant initial, loading, empty, error, success, disabled, selected, and responsive states instead of polishing only the ideal screenshot. Use clearly labeled mock data when real data is unavailable; product claims and user data remain grounded in supplied material. This step is complete when every in-scope state and primary interaction has an intentional presentation. 4. **Clear the usability floor.** Use semantic controls, keyboard operation, visible focus, sufficient contrast, useful labels, reduced-motion behavior, and layouts that survive narrow widths, zoom, long content, and missing content. Consult the relevant authoritative source when a component contract or accessibility requirement is uncertain. This step is complete when no known floor failure blocks the primary task. 5. **Render and iterate.** Inspect the actual result rather than inferring it from source code. Exercise the primary interaction, check desktop and a narrow viewport, and compare against the visual thesis and any supplied reference. Make focused corrections to hierarchy, typography, spacing, color, states, overflow, and interaction feedback. Distinguish rendered observations from code-based inference and name anything that could not be verified. This step is complete when no material mismatch or usability-floor failure remains within scope. ## Response Report the visual thesis, the material choices or changes, the rendered checks performed, and any unverified limitation. Keep the explanation shorter than the design work. ## Example ```text /skill:design Refine the transaction dashboard. Keep the existing components, make failed payments easier to scan, and verify desktop and mobile states. ```
From luizomf/omskills, MIT.
More from luizomf/omskills
- 0.609score
diagnosing-bugs
luizomf
Reproduction-first diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
orchestrate
luizomf
Carry a bounded change through implementation, independent review, and verified delivery in the current conversation.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
codebase-design
luizomf
Design or improve deep modules.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
dispatch-tickets
luizomf
Coordinate a multi-issue Mission by tracking dependencies, responsible agents, blockers, and verified deliveries.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
setup-omskills
luizomf
Configure repository instructions, issue-tracker operations, triage-label mappings, and domain-doc locations.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
research
luizomf
Investigate a bounded question or produce a durable cited research artifact.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
code-review
luizomf
Review a committed range or complete work-in-progress candidate against repository standards and its governing contract.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
to-spec
luizomf
Synthesize the current conversation and repository context into a spec, then publish it to the configured issue tracker without a requirements interview.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
to-tickets
luizomf
Break a plan, spec, or conversation into tracer-bullet tickets with explicit blocking and conflict edges, then publish them to the configured tracker.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
triage
luizomf
Categorize and verify issues or external pull requests, then move them through configured triage states and record the applicable brief or notes.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
wayfinder
luizomf
Plan work that exceeds one agent session as a shared map of investigation tickets, then resolve one ticket per session until the route to the destination is…
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
grill-with-docs
luizomf
Stress-test a repository plan or design through bounded Question rounds while updating domain terms and durable architecture decisions.
SkillAFreshness: A★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 22, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/luizomf/omskills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from luizomf
- 0.609score
diagnosing-bugs
luizomf
Reproduction-first diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
orchestrate
luizomf
Carry a bounded change through implementation, independent review, and verified delivery in the current conversation.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
dispatch-tickets
luizomf
Coordinate a multi-issue Mission by tracking dependencies, responsible agents, blockers, and verified deliveries.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
codebase-design
luizomf
Design or improve deep modules.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
research
luizomf
Investigate a bounded question or produce a durable cited research artifact.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
setup-omskills
luizomf
Configure repository instructions, issue-tracker operations, triage-label mappings, and domain-doc locations.
SkillAFreshness: A★ 3Claude Code +9
Cite this page
design skill. Agent Mart. https://agentmart.dev/skills/luizomf-design (last updated 2026-10-24)