critique

Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, and overall design quality with actionable feedback.

2.32x

Quality

68%

Does it follow best practices?

Impact

100%

2.32x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./archived/legacy-companion/.agents/skills/critique/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

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 strong, actionable instruction-only skill with a clear evaluation framework and report structure. Its main weaknesses are modest verbosity from motivational coaching and the lack of progressive disclosure for a body that is long enough to warrant split-out reference material.

Suggestions

Trim the rhetorical coaching in the closing 'Remember' block and dimension intros; keep the concrete diagnostic questions, which already imply the desired directness.

Consider moving the detailed per-dimension checklists or the report template into a reference file (e.g. references/dimensions.md) referenced one level deep from SKILL.md, leaving a concise overview.

Optionally add a short validation checkpoint for the critique (e.g. 'Re-read the Anti-Patterns Verdict before finalizing to ensure each tell is specific and evidenced').

Dimension	Reasoning	Score
Conciseness	Well-organized and assumes Claude's design competence without explaining basic concepts, but the repeated imperative coaching ('Be brutally honest', 'Be direct—vague feedback wastes everyone's time', 'Prioritize ruthlessly') and the 10 fully-expanded dimension checklists add tokens that could be tightened.	2 / 3
Actionability	Gives a concrete evaluation framework — 10 dimensions each broken into specific diagnostic questions — plus a structured report template with a What/Why/Fix/Command format per issue and a concrete list of skill commands to recommend.	3 / 3
Workflow Clarity	Provides an explicit sequence: 'First' use the frontend-design skill, then evaluate the 10 dimensions with #1 flagged 'CRITICAL', then generate the critique report — with 'Start here' markers giving clear ordering for a read-only analysis task.	3 / 3
Progressive Disclosure	Sections are clearly organized, but at ~107 lines all content lives inline in SKILL.md with no split-out reference files; the only cross-reference is the pointer to the frontend-design skill, and the body exceeds the 50-line simple-skill threshold that would allow a lenient score of 3.	2 / 3
	Total	10 / 12 Passed

Description

60%Weight 40%Scale 1-3

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 about capabilities and domain but is missing an explicit 'when to use' trigger and natural user phrasing. Adding a 'Use when...' clause with conversational trigger terms would materially improve it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a design critique, UI/UX review, or feedback on an interface's visual and experiential quality.'

Include natural trigger terms users would actually say ('critique', 'review the design', 'is this design any good', 'UX feedback') rather than only design-director phrasing.

Tighten 'overall design quality' toward a more distinct niche to reduce overlap with general design or frontend-design skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete assessment areas — 'visual hierarchy, information architecture, emotional resonance, and overall design quality' plus 'actionable feedback' — naming the domain and several specific capabilities rather than vague language.	3 / 3
Completeness	Clearly states what the skill does (assesses the listed dimensions with actionable feedback) but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant terms like 'design', 'UX', and 'feedback' but lacks natural user phrasing such as 'critique my design' or 'review the UI', and offers no explicit trigger keywords or common variations.	2 / 3
Distinctiveness Conflict Risk	The UX-critique framing is reasonably distinct, but 'overall design quality' is broad and could overlap with general design or frontend-design skills; no clearly walled-off niche with distinct triggers.	2 / 3
	Total	9 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: The-Vibe-Company/companion
Path: archived/legacy-companion/.agents/skills/critique/SKILL.md
Commit: 90804d3

Reviewed: 18 days ago

Table of Contents

Discovery Implementation Validation

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.