design-critique

Get structured design feedback on usability, hierarchy, and consistency. Trigger with "review this design", "critique this mockup", "what do you think of this screen?", or when sharing a Figma link or screenshot for feedback at any stage from exploration to final polish.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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 well-organized, actionable critique framework with a strong output template and clear input handling. Its main weakness is mild verbosity from generic feedback-coaching and a redundant Tips section.

Suggestions

Trim the 'How to Give Feedback' section or fold its non-obvious points into the framework; remove generic advice Claude already applies.

Drop or merge the 'Tips' section, since its three items duplicate the 'What I Need From You' (context, stage, focus) guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with a well-structured framework and output template, but the 'How to Give Feedback' section coaches generic principles Claude already knows ('Be specific', 'Explain why') and the 'Tips' section restates the 'What I Need From You' content (context, stage, focus).	2 / 3
Actionability	For an instruction-only skill the guidance is concrete and actionable: per-dimension critique questions plus a copy-paste-ready output template with severity markers and tables.	3 / 3
Workflow Clarity	The single-task flow is unambiguous — input handling (Figma URL / file / ask user) is explicit, followed by the critique framework and a defined output structure; no destructive or batch operations require validation checkpoints.	3 / 3
Progressive Disclosure	No bundle files exist; the single SKILL.md is well-organized into clearly labeled sections (Usage, What I Need, Critique Framework, Output, Tips) with content appropriately kept inline rather than split, which suits this cohesive skill.	3 / 3
	Total	11 / 12 Passed

Description

80%

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 has strong triggers, completeness, and distinctiveness, but uses imperative/second-person voice ('Get structured design feedback') instead of the required third-person voice, which caps its specificity score per the rubric.

Suggestions

Rewrite in third person to match rubric examples, e.g. 'Provides structured design feedback on usability, hierarchy, and consistency.'

Replace the single vague action with several concrete ones (e.g. 'evaluates visual hierarchy, checks accessibility contrast, and flags consistency issues') to lift specificity to a 3.

Dimension	Reasoning	Score
Specificity	Base specificity is 2 — it names the domain ('structured design feedback on usability, hierarchy, and consistency') but offers a single action rather than multiple concrete ones — but the imperative 'Get structured design feedback' is second-person voice, so per the rubric guideline the specificity score is reduced by 1.	1 / 3
Completeness	It explicitly answers both what ('Get structured design feedback on usability, hierarchy, and consistency') and when ('Trigger with ... or when sharing a Figma link or screenshot for feedback at any stage from exploration to final polish').	3 / 3
Trigger Term Quality	Natural trigger phrases a user would actually say are well covered: 'review this design', 'critique this mockup', 'what do you think of this screen?', plus 'Figma link or screenshot' for feedback.	3 / 3
Distinctiveness Conflict Risk	Design critique with Figma/mockup-specific triggers is a clear niche unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: anthropics/knowledge-work-plugins
Commit: f96c57c

Reviewed: 2 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.