CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

quick-mockups

Create multiple UI design mockups in parallel. Use when asked to create mockups, wireframes, or design variations for a feature. Creates HTML files using Mantine v7 + Tailwind following Civitai's design system.

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, actionable runbook: an explicit directory convention, a fully worked example agent prompt, and a defined post-creation workflow. Its only weaknesses are a slightly overlong illustrative directory tree and the absence of an explicit recovery/verification loop if a parallel agent fails to produce its file.

Suggestions

Add a brief validation step after the agents run: check each expected file exists and re-launch or retry any missing variation before summarizing.

Trim the directory-structure example to one feature to cut illustrative padding.

DimensionReasoningScore

Conciseness

The body is lean — no concept explanations, just usage steps, a naming convention, a full example prompt, and short tips. It sits between anchors: efficient overall but the two-feature directory tree (crucible-discovery with 4 files plus crucible-rating with 3) is illustrative padding that could be trimmed to one example.

4 / 5

Actionability

Fully concrete and copy-paste ready: exact output path pattern 'docs/working/mockups/<feature-name>/', 'subagent_type: design-mockup', agent count, the four variation dimensions, and a complete example prompt with requirements and output path. Specific examples cover the common case; nothing is left as vague direction.

5 / 5

Workflow Clarity

Clear sequence: create directory → launch 3-5 parallel agents with structured prompts → list files → summarize each variation → ask user. The 'List all created mockup files' step acts as a post-batch checkpoint, but there is no explicit feedback loop (what to do if an agent fails or a file is missing), leaving a minor validation gap.

4 / 5

Progressive Disclosure

A single-purpose skill with no bundle files; nothing that belongs in a separate file is inlined. Sections are well-organized, the one external pointer ('.claude/agents/design-mockup.md') is clearly signaled, and navigation is trivial — matching the well-organized simple-skill case.

5 / 5

Total

18

/

20

Passed

Description

83%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.

A strong description that states concrete capabilities (parallel mockup creation, HTML output with a specific stack) and an explicit 'Use when' trigger clause with natural terms. Third-person voice is used correctly. The only gaps are a few missing synonyms (prototypes, UI designs) and unmentioned post-creation steps.

Suggestions

Add common synonyms like 'prototypes' or 'UI designs' to the trigger clause to widen natural-term coverage.

Mention the follow-up step (presenting variations and asking the user which direction to pursue) to round out the capability list.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Create multiple UI design mockups in parallel', 'Creates HTML files using Mantine v7 + Tailwind following Civitai's design system' — with a named tech stack. Not a 5 because it stops at creation; it doesn't mention summarizing variations or asking the user for direction, leaving a minor coverage gap.

4 / 5

Completeness

Explicitly answers both: what ('Create multiple UI design mockups in parallel... Creates HTML files using Mantine v7 + Tailwind') and when ('Use when asked to create mockups, wireframes, or design variations for a feature'). Both are concrete with explicit trigger phrases, matching the top anchor; not a lower score because the 'when' clause is explicit rather than implied.

5 / 5

Trigger Term Quality

'mockups, wireframes, or design variations for a feature' are natural phrases users would say. Good coverage but a few common synonyms are missing (e.g., 'UI designs', 'prototypes', 'comps'), so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

'mockups', 'wireframes', and 'design variations' carve a fairly distinct niche with the Civitai design-system framing. Minor overlap risk with general frontend/design-implementation skills, so it fits 'mostly distinct' rather than 'clear niche with minimal conflict risk'.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

civitai/civitai

Path

.claude/skills/quick-mockups/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.