CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

57

Quality

72%

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

70%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 an exceptionally well-sequenced, highly actionable workflow with real validation gates and a genuine recovery path, and its per-mode reference routing is exemplary. Its weakness is bulk: four full placeholder skeletons and repeated justification blockquotes are inlined in SKILL.md instead of living in reference files, doubling its token footprint without adding decision-relevant guidance.

Suggestions

Move the four skeletons to a reference file (e.g. references/skeletons.md) or generate them from the existing templates, keeping only the section-heading lists inline in SKILL.md.

Trim the multi-line justificatory blockquotes (e.g. the accessibility-path warning and the circular-remediation note) to one line each — the rule survives without the rationale paragraphs.

Move the Phase 2 read-list details for stable, rarely-changing inputs (e.g. the project.yaml platform-block fallback rules) into a reference so the main body stays a decision-oriented overview.

DimensionReasoningScore

Conciseness

Roughly 340 of the ~815 body lines are four inlined skeletons made almost entirely of repeated "[To be designed]" placeholders, and several long blockquote justifications pad the flow. This is noticeably verbose with padded sections (anchor 2) rather than merely 'could be tightened' (anchor 3); the padding is structural, not incidental.

2 / 5

Actionability

Fully executable throughout: exact file paths, a copy-ready command (Grep pattern="^#+ .*UI Requirements" glob="design/gdd/*.md" output_mode="content" -A 20), scripted AskUserQuestion prompts with enumerated options, and concrete derivation rules for input methods. Specific examples cover the common cases; nothing is left as vague direction.

5 / 5

Workflow Clarity

Phases 1-8 are clearly sequenced with a per-section Context->Questions->Options->Decision->Draft->Approval->Write cycle, retrofit-mode detection before writing, a Phase 5 cross-reference checklist, and a Phase 7 recovery/resume procedure. Validation checkpoints are explicit at every write, matching the top anchor including error recovery.

5 / 5

Progressive Disclosure

The bundle references (references/sections-ux-spec.md, sections-hud.md, sections-patterns.md) exist, are one level deep, and are clearly signaled via a mode-routing table with 'read only the file matching the mode' — but ~42% of the body is inlined skeleton/template content that belongs in a separate reference file. Anchor 3 (content that should be separate is inline) fits better than 4 because the inlining is substantial, though the signaling itself is strong.

3 / 5

Total

15

/

20

Passed

Description

66%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 states concrete, domain-specific capabilities in third person and is appropriately concise, but it omits any 'use when' trigger guidance and misses one of the skill's four authoring modes (the interaction pattern library). It reads as a capability summary rather than a trigger-optimized description.

Suggestions

Add an explicit trigger clause, e.g. "Use when designing a game screen, flow, or HUD, or when the user mentions UX specs, wireframes, or accessibility requirements."

Mention the interaction pattern library mode (e.g. "also authors the interaction pattern library") so all four modes are represented.

Include natural trigger words users would say — "design", "wireframe", "usability" — alongside the existing "UX spec" and "HUD".

DimensionReasoningScore

Specificity

Lists several concrete actions — "Section-by-section UX spec authoring for a screen, flow or HUD", "Reads the player journey to provide context", "also project-wide accessibility" — but coverage has a gap: the interaction-pattern-library mode is never mentioned. Not 3 (more than 1-2 actions, each domain-specific); not 5 (a whole authoring mode is omitted).

4 / 5

Completeness

The 'what' is clear (author UX specs per screen/flow/HUD plus project-wide accessibility) but there is no 'Use when...' clause or equivalent explicit trigger guidance — the rubric caps completeness at 3 in that case. Not 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Natural keywords present ("UX spec", "screen", "flow", "HUD", "accessibility") that a user designing game UI would plausibly say. Missing common variations like "design", "wireframe", "usability", and "interaction patterns" — falls at anchor 4 (good coverage, a few natural terms missing), not 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (game UX specification, HUD, player journey) with distinct triggers unlikely to fire for unrelated skills; minor overlap risk with art-direction or a dedicated accessibility skill via the generic word "accessibility". Not 5 because "project-wide accessibility" could collide with a standalone accessibility skill.

4 / 5

Total

15

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (823 lines); consider splitting into references/ and linking

Warning

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

13

/

16

Passed

Repository
Donchitos/Claude-Code-Game-Studios
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.