CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

normalize

Audits and realigns UI to match design system standards, spacing, tokens, and patterns. Use when the user mentions consistency, design drift, mismatched styles, tokens, or wants to bring a feature back in line with the system.

Quality

77%

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 ./templates/skills/impeccable/normalize/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 a well-structured, actionable normalization workflow with a clear sequence and cleanup validation. Its weaknesses are motivational padding that wastes context and the absence of an explicit fix-and-revalidate loop around destructive cleanup steps.

Suggestions

Remove the closing persona paragraph ('Remember: You are a brilliant frontend designer...') and the redundant opening sentence — they add tokens without actionable guidance.

Add an explicit feedback loop after cleanup: if lint/type-check/tests fail, fix the regressions and re-run before finishing.

Replace abstract directives like 'Think through the best possible experience for your use case and personas' with concrete criteria or a short example of a normalization decision.

DimensionReasoningScore

Conciseness

The body is mostly directive checklists, but includes unnecessary padding: the closing persona pep-talk ('You are a brilliant frontend designer with impeccable taste... world class') and the redundant opening sentence restate the description. Fits anchor 3 — mostly efficient with some content that could be tightened — rather than 4, since the padding is motivational filler Claude does not need.

3 / 5

Actionability

As an instruction-only skill it gives concrete, executable guidance: specific search terms ('grep for "design system", "ui guide", "style guide"'), token-replacement directives per dimension, and a lint/type-check/test cleanup step. Not 5 because portions remain abstract ('apply judgment', 'Think through the best possible experience') without concrete criteria or examples.

4 / 5

Workflow Clarity

The Plan → Execute → Clean Up sequence is clear, with analysis checkpoints and a verification step ('Lint, type-check, and test... Ensure normalization didn't introduce regressions'). Not 5 because there is no explicit validate-fix-retry feedback loop, even though the workflow includes destructive steps like 'Delete unused implementations, styles, or files'.

4 / 5

Progressive Disclosure

No bundle files exist, and the body is well-sectioned with nothing that clearly belongs in a separate file. Not 5 because it is slightly over the ~50-line simple-skill range and points to external skills (/frontend-design, /teach-impeccable) as mandatory context rather than well-signaled one-level-deep bundle references.

4 / 5

Total

15

/

20

Passed

Description

78%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.

A strong description that explicitly covers what the skill does and when to use it with natural trigger phrasing. Its main gaps are limited action variety in the what-clause and a few missing common trigger synonyms.

DimensionReasoningScore

Specificity

The description names the domain and two concrete actions ('Audits and realigns UI') plus alignment targets ('standards, spacing, tokens, and patterns'), but stops short of the several distinct actions the anchor-4 example demonstrates. Not score 2 because the actions and scope are concrete, not generic.

3 / 5

Completeness

Both parts are explicit: 'Audits and realigns UI to match design system standards...' answers what, and 'Use when the user mentions consistency, design drift, mismatched styles, tokens...' answers when with concrete trigger phrases. Matches the anchor-5 example exactly in structure.

5 / 5

Trigger Term Quality

Trigger terms are natural user phrasing ('consistency, design drift, mismatched styles, tokens', 'bring a feature back in line'), giving good keyword coverage. Not 5 because common variations users would also say — 'design system', 'style guide', 'UI cleanup' — are absent from the when-clause.

4 / 5

Distinctiveness Conflict Risk

The design-system normalization niche with triggers like 'design drift' and 'mismatched styles' is mostly distinct from adjacent skills. Not 5 because generic terms like 'consistency' and 'tokens' carry minor overlap risk with general frontend-design or styling skills.

4 / 5

Total

16

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

fengshao1227/ccg-workflow

Path

templates/skills/impeccable/normalize/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.