CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ux-review

Reviews the question-to-answer flow, source-review friction, evidence navigation, mobile/desktop usability, and global search composer behaviors. Use during UX/UI refactoring.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/ux-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 content is an appropriately brief, well-structured checklist for a read-only review skill with some genuinely concrete anchors (file names, routing patterns). Its weaknesses are subjective, unmeasurable checklist criteria and the absence of validation checkpoints or explicit step ordering before posting a review record.

Suggestions

Replace subjective criteria with measurable checks, e.g., 'touch targets >= 44px', 'drawer opens in <= 1 interaction', or specific viewport widths to test.

Add explicit sequencing and a validation step, e.g., '1. Read protocol docs 2. Run each checklist section in order 3. Verify each finding against the code before including it 4. Post the Review record comment'.

Clarify or inline the pull-request-workflow reference so the link path resolves within the skill's own bundle rather than a fragile ../../../ relative path.

DimensionReasoningScore

Conciseness

The body is lean and imperative with no padding and no explanation of concepts Claude already knows; every line (placement rules, routing paths, drawer behavior checks) earns its place.

5 / 5

Actionability

Some items are concrete ("master-search-header.tsx", "?q=...&run=1", placement rules), but several checklist criteria are subjective and lack executable specifics or acceptance thresholds ("load with minimal user interaction", "verify touch boundaries", "layout density").

3 / 5

Workflow Clarity

A rough sequence exists (consult AGENTS.md and the review protocol before starting, run the checklist, post one Review record comment after), but checklist items have no explicit ordering and no validation checkpoints to confirm findings before posting.

3 / 5

Progressive Disclosure

The skill is under 50 lines with well-organized sections and no bundle files needed, which would merit a 5, but the relative link "../../../docs/agents/pull-request-workflow.md" is an awkward, non-local navigation path, a minor organization gap.

4 / 5

Total

15

/

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 is concise, third-person, and covers both what the skill does and when to use it, with a distinctive project-specific scope. Its main weaknesses are a single generic action verb and a narrow trigger clause that misses common natural phrasings users would say.

Suggestions

Vary the action verbs to name distinct concrete actions (e.g., 'Audits search composer placement, traces question-to-answer flows, checks mobile touch targets') instead of one blanket 'Reviews'.

Broaden the 'Use when' clause with concrete trigger phrases users would naturally say, e.g., 'Use when the user mentions UX/UI review, usability, responsiveness, or search behavior issues'.

DimensionReasoningScore

Specificity

The description names several concrete review targets ("question-to-answer flow, source-review friction, evidence navigation, mobile/desktop usability, and global search composer behaviors") but relies on a single generic action verb ("Reviews"), matching the anchor for naming a domain with concrete targets but not comprehensive distinct actions.

3 / 5

Completeness

Both what ("Reviews the question-to-answer flow...") and when ("Use during UX/UI refactoring") are explicitly stated, but the 'when' clause is a single narrow trigger without concrete user-mention phrases, so it does not reach the fully explicit level.

4 / 5

Trigger Term Quality

"Use during UX/UI refactoring" plus terms like "mobile/desktop usability" provide some relevant keywords, but common natural variations users would say (e.g., "usability review", "responsive design", "design review") are missing.

3 / 5

Distinctiveness Conflict Risk

Project-specific phrases like "source-review friction" and "global search composer behaviors" establish a clear niche with distinct triggers, with only minor overlap risk against a generic UI-review skill.

4 / 5

Total

14

/

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

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

BigSimmo/PsychSift

Path

.cursor/skills/ux-review/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.