CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ux-design

Section-by-section UX spec authoring for a screen, flow or HUD. Reads the player journey to provide context; also project-wide accessibility.

Quality

76%

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 ./.claude/skills/ux-design/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.

A well-structured orchestration skill: the body is an overview that routes each phase to exactly one reference file and gates mode-specific guidance, with highly concrete prompts, paths, and decision tables throughout. The main flaws are a section-numbering gap (Phase 6 is missing between sections 5 and 7) and minor token-level repetition in the phase headers and collaborative protocol lists.

Suggestions

Fix the phase numbering: the body jumps from '## 5. Cross-Reference Check' straight to '## 7. Recovery & Resume', implying a deleted Phase 6 — renumber or restore the missing section.

State the compact/resume re-read instruction once (e.g., in a 'Reading reference files' preamble) instead of repeating it verbatim in all four phase headers.

Consider inlining or summarizing the per-topic routing targets for the interaction-pattern guide so the second hop ('routes to three topic files') doesn't require loading a guide just to discover which topic file to read.

DimensionReasoningScore

Conciseness

The body is mostly lean tables and pointers that assume Claude's competence, but the 'Read it again if the conversation was compacted or resumed' line repeats verbatim across four phase headers and the Collaborative Protocol list overlaps its own Never/Always bullets.

4 / 5

Actionability

Fully concrete instruction-only guidance: an argument→mode→output-file table, exact file paths per phase, exact AskUserQuestion prompts with option lists, a kebab-case normalization example, and concrete next-step commands like '/ux-review' and '/gate-check production'.

5 / 5

Workflow Clarity

The phase sequence is clear with explicit approval checkpoints before every write, a cross-reference check phase, and a recovery/resume procedure, but the section numbering jumps from '## 5. Cross-Reference Check' to '## 7. Recovery & Resume', leaving a missing Phase 6 gap.

4 / 5

Progressive Disclosure

Well-signaled one-level-deep structure — one reference file per phase, all seven referenced bundle files verified present, and 'read only the file matching the mode; never load the other two' gating. Docked one level because the interaction-pattern guide 'routes to three topic files' (a second hop) and several guidance paths point outside the bundle to unverifiable .claude/docs/ locations.

4 / 5

Total

17

/

20

Passed

Description

61%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 is specific and mostly distinct, naming concrete outputs (screen/flow UX specs, HUD, accessibility requirements) and the player-journey input, with natural trigger vocabulary like 'UX spec' and 'HUD'. Its weaknesses are the absence of any explicit 'when to use this' trigger clause and the omission of the interaction-pattern-library mode, both of which leave it just above the midpoint rather than strong.

Suggestions

Add an explicit trigger clause, e.g., 'Use when designing or speccing a game screen, flow, HUD, interaction pattern library, or project-wide accessibility requirements.'

Mention the interaction-pattern-library output so the description covers all four authoring modes the skill supports.

Include a couple of common user phrasings like 'UI design' or 'wireframe' to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain and a couple of concrete actions ('Section-by-section UX spec authoring', 'Reads the player journey', 'project-wide accessibility'), but omits the interaction-pattern-library mode, so action coverage is not comprehensive — matching anchor 3 rather than anchor 4's 'several specific actions; minor gaps'.

3 / 5

Completeness

The 'what' is clear (authoring UX specs, HUD designs, and project-wide accessibility requirements), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines; not 2 because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

Natural terms users would say are present: 'UX spec', 'screen', 'flow', 'HUD', 'accessibility', 'player journey'. A few common phrasings are missing ('UI', 'wireframe', 'interaction patterns'), matching anchor 4's 'good keyword coverage; a few natural terms missing' rather than anchor 5's synonym-level coverage.

4 / 5

Distinctiveness Conflict Risk

'Section-by-section UX spec authoring for a screen, flow or HUD' carves a distinct game-UX niche with specific artifacts, carrying only minor overlap risk with closely related design skills (e.g., a sibling /ux-review skill) — anchor 4 rather than 5 because the terms 'design' and 'accessibility' are not uniquely owned by this skill.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

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

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

Donchitos/Claude-Code-Game-Studios

Path

.claude/skills/ux-design/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.