impeccable-design-polish

Follow-up design polish skill inspired by Impeccable. Use after a web or HTML artifact exists to audit, critique, polish, animate, harden, and prepare the page for a live/share pass.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/impeccable-design-polish/SKILL.md

Quality

Content

61%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 well-structured and concise for an instruction-only skill, but it lacks an explicit sequenced workflow with validation checkpoints for its destructive editing operations, and its actionability stops short of executable specifics.

Suggestions

Add a numbered, sequenced workflow (e.g., inspect → audit → prioritize → edit → verify) with an explicit validation/checkpoint step after editing, since Polish/Harden directly mutate the artifact.

Make the AI-tells list more actionable by pairing each tell with a concrete detection cue or fix pattern (e.g., how to test contrast, what restrained motion values to use).

Tighten or remove the closing sentence of the intro ("closer to something a designer would ship") and similar filler to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with well-organized sections and minimal padding; a few sentences like "closer to something a designer would ship" are slightly trimmable, keeping it at 4 rather than 5.	4 / 5
Actionability	Provides concrete directives ("Inspect the current HTML/page before editing") and a specific AI-tells list, but guidance on how to detect and fix each issue is incomplete — "directly edit the artifact to improve the top issues" lacks executable specifics, matching the 3 anchor.	3 / 5
Workflow Clarity	Modes (Audit/Critique/Polish/Animate/Harden/Live) are alternatives rather than a sequenced workflow, and the destructive edit operation lacks explicit validation checkpoints; the weak "finish in a better runnable state" check does not raise it above the destructive-skill cap of 3.	3 / 5
Progressive Disclosure	Single well-organized file with clear section headers and no nested references; slightly over 50 lines and with no external references, so it sits at 4 rather than the 5 reserved for compact single-purpose skills.	4 / 5
	Total	14 / 20 Passed

Description

80%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, action-oriented, and clearly scopes a follow-up design-polish niche for web/HTML artifacts. It answers both what and when but the trigger phrasing could be more user-intent-aligned.

Dimension	Reasoning	Score
Specificity	Lists six concrete actions — "audit, critique, polish, animate, harden, and prepare the page for a live/share pass" — giving comprehensive coverage of capabilities, matching the 5 anchor.	5 / 5
Completeness	Explicitly states what ("audit, critique, polish, animate, harden, and prepare") and when ("Use after a web or HTML artifact exists"), but the when is a state condition rather than a concrete user-intent trigger phrase, keeping it below 5.	4 / 5
Trigger Term Quality	Includes natural terms like "web or HTML artifact", "design polish", and "live/share pass"; good coverage but missing common synonyms a user might say (e.g., "cleanup", "review UI"), so it sits at 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	Niche is clear — post-generation design polish for web/HTML artifacts — with mostly distinct triggers; minor overlap risk with general frontend/design skills prevents a 5.	4 / 5
	Total	17 / 20 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: nexu-io/open-design
Path: skills/impeccable-design-polish/SKILL.md
Commit: 81044a0

Reviewed: 3 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.