CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

design-first-ui-prompting

Use when you need design-first, spec-driven, skimmable prompts for UI generation. Covers prompt structure, constraints, variations, typography/spacing rules, and iteration workflow for consistent UI outputs.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent-skills/ui/design-first-ui-prompting/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a dense, highly actionable prompting guide: a copy-paste spec skeleton, concrete rules (one-variable iteration, 2-pass typography fallback), and a filled-in constraints-card example. Its main weaknesses are minor redundancy between the rules and checklist sections and the absence of explicit output-validation checkpoints in the iteration workflow.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no padding explaining what UI design or prompting is, and every section delivers specific guidance ('Lock one system, then iterate with variants', 'change ONE variable at a time'). Not 5 because there is minor redundancy: the 'Fast iteration checklist' and 'Rules that improve consistency' partially overlap (both list accent/spacing/texture tweaks), and lines like 'It anchors the output like a mini style guide' could be trimmed.

4 / 5

Actionability

For an instruction-only skill the guidance is fully concrete: a copy/paste prompt skeleton with fill-in blanks and worked examples (e.g., 'Grid: Swiss 6-col', 'Weights: H1 700, body 400'), a filled-in constraints card ('FONT CANELA / STYLE MINIMAL / MODE DARK'), an explicit 2-pass workflow for fragile typography, and a checklist of exact things to tweak. This matches 'copy-paste ready ... specific examples cover the common cases'.

5 / 5

Workflow Clarity

The iteration workflow is clearly sequenced — 'First output: nail layout + hierarchy + copy', then variants changing 'ONE variable at a time', with a fallback 2-pass workflow when 'the model keeps misspelling' — which is a genuine feedback loop for a fragile operation. Not 5 because there are no explicit validation checkpoints for judging whether an output succeeded before iterating further (success criteria appear only as blanks in the skeleton).

4 / 5

Progressive Disclosure

This is a single-file skill (no references/, scripts/, or assets/ bundles exist) with well-organized sections, clear headers, and appropriately inline core material — the prompt skeleton belongs in the body. Not 5 because at ~105 lines it exceeds the under-50-line simple-skill case, and the 'Keep a local reference pack' section's `refs/...` folder is described only vaguely rather than being a concrete, well-signaled structure.

4 / 5

Total

17

/

20

Passed

Description

62%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description has an explicit 'Use when' trigger and a clear enumeration of what the skill covers, but it reads as a table of contents rather than a statement of actions, and it lacks the natural trigger vocabulary (mockup, wireframe, landing page) users would actually say. The second-person 'you need' phrasing and jargon-heavy framing ('spec-driven, skimmable') further weaken it.

Suggestions

Rewrite the 'what' clause as concrete actions in third person (e.g., 'Builds design-first prompts for UI generation: structures goals, layout, type systems, and constraints; iterates via one-variable variants'), rather than 'Covers ... rules'.

Replace the circular 'Use when you need design-first, spec-driven, skimmable prompts' with concrete user situations and natural synonyms, e.g., 'Use when generating UI mockups, landing pages, dashboards, or onboarding screens with image or UI generation models'.

Add natural trigger terms users would actually say — mockup, wireframe, hero section, UI design, prompt template — to reduce reliance on skill-internal jargon like 'spec-driven' and 'skimmable'.

DimensionReasoningScore

Specificity

The description names the domain ('design-first, spec-driven, skimmable prompts for UI generation') and lists several concrete coverage areas ('prompt structure, constraints, variations, typography/spacing rules, and iteration workflow'), which would anchor at 4 — but these are topics covered rather than actions performed, and the second-person phrasing 'Use when you need' triggers the rubric's third-person penalty, reducing it to 3. It is not a 2 because the domain and coverage list are specific rather than generic.

3 / 5

Completeness

Both 'what' ('Covers prompt structure, constraints, variations, typography/spacing rules, and iteration workflow for consistent UI outputs') and 'when' ('Use when you need design-first, spec-driven, skimmable prompts for UI generation') are explicitly present, so the score-3 cap for a missing 'when' clause does not apply. Not 5 because the 'what' describes contents ('Covers...') rather than concrete actions, and the 'when' clause is somewhat circular — it restates the skill's own framing ('design-first, spec-driven, skimmable') rather than naming concrete user situations.

4 / 5

Trigger Term Quality

Some relevant natural keywords are present ('UI', 'prompts', 'design', 'typography', 'spacing'), but common variations users would actually say are missing (e.g., 'mockup', 'landing page', 'wireframe', 'UI design', tool names like Figma or image generators). This matches the anchor 'Some relevant keywords but missing common variations or synonyms' — not 4, since the keyword set is thin and leans on skill-specific jargon ('spec-driven', 'skimmable') rather than user-natural phrasing.

3 / 5

Distinctiveness Conflict Risk

The 'design-first UI prompting' niche is fairly distinct with identifiable triggers (prompt structure, typography/spacing rules, iteration workflow for UI generation). Not 5 because it could minorly overlap with adjacent design/brand-styling and general prompting skills given how broadly 'UI generation' and 'prompts' read.

4 / 5

Total

14

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

MengTo/Skills

Path

agent-skills/ui/design-first-ui-prompting/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.