colorize

Add strategic color to features that are too monochromatic or lack visual interest. Makes interfaces more engaging and expressive.

1.10x

Quality

56%

Does it follow best practices?

Impact

93%

1.10x

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/colorize/SKILL.md

Quality

Content

62%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 well-structured, actionable design workflow with strong sequencing and validation gating. Its main weaknesses are moderate verbosity/repetition and a monolithic single-file structure that could benefit from offloading detailed reference material.

Suggestions

De-duplicate the 'STOP and call AskUserQuestionTool' guidance into the preparation section and remove the 'STOP and STOP' typo and stray periods.

Cut explanations Claude already knows (e.g. the success=green / error=red semantic mapping) and keep only the non-obvious color guidance.

Consider moving the detailed per-category color application lists into a reference file linked from a concise overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is well-sectioned and mostly efficient, but it repeats the 'STOP and call AskUserQuestionTool' instruction across multiple sections (one with a typo 'STOP and STOP'), restates semantic-color conventions Claude already know (success=green, error=red), and could be tightened without losing meaning.	2 / 3
Actionability	It gives genuinely concrete anchors (OKLCH values like 'oklch(97% 0.01 60)', WCAG 4.5:1/3:1 ratios, the 60/30/10 distribution, '2-4 colors max'), but much of the guidance is categorical enumeration of where color could go rather than specific, copy-paste-ready instructions, leaving it short of fully actionable.	2 / 3
Workflow Clarity	It sequences distinct phases (Context Gathering, Assess, Plan, Introduce, Balance & Refinement, Verify) with explicit gating checkpoints ('Do NOT proceed until you have answers', 'Do NOT proceed until it has executed') and a final verification checklist, matching the clear-sequence-with-explicit-validation anchor.	3 / 3
Progressive Disclosure	It is a single well-organized file with clear section headers, but it is monolithic with no bundle references, and the detailed application-category lists could plausibly be split into a reference file, fitting the 'some structure, content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

50%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 clear and reasonably specific about its purpose but lacks an explicit 'Use when...' trigger clause and only partially covers natural trigger terms. Adding explicit trigger guidance and a fuller action list would lift all dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when an interface looks too gray, monochromatic, or lacks visual warmth and personality.'

List 2-3 concrete actions instead of one action plus an outcome (e.g. 'Introduce semantic, accent, and tinted-neutral colors to flat or monochromatic interfaces').

Include common user phrasings like 'too gray', 'make it more colorful', or 'add some color' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('features', 'interfaces') and one concrete action ('Add strategic color'), but the second sentence ('Makes interfaces more engaging and expressive') describes an outcome rather than additional concrete actions, so it is not a comprehensive action list as required for a 3.	2 / 3
Completeness	It answers 'what' (add strategic color to monochromatic features) but the 'when' is only implied through the condition 'features that are too monochromatic' with no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes some natural terms a user might say ('monochromatic', 'color', 'visual interest'), but misses common variations like 'too gray', 'make it more colorful', or 'add some color', so coverage is partial rather than complete.	2 / 3
Distinctiveness Conflict Risk	The 'monochromatic / lack visual interest' framing gives it a recognizable niche, but color/design guidance overlaps broadly with general frontend-design skills and could trigger for the wrong skill, so it is not yet a clear distinct niche.	2 / 3
	Total	8 / 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/colorize/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.