muapi-color-analysis-board

Turn a portrait photo into a high-end editorial "Color Analysis Board" in a luxury fashion-magazine style (Dior / Ralph Lauren aesthetic) — best colors, undertone, makeup guide, capsule wardrobe, hair & jewelry recommendations, all laid out on a clean beige/ivory grid.

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 ./library/visual/color-analysis-board/SKILL.md

Quality

Content

75%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 tight, executable single-purpose recipe with a clear prompt block and sensible input-handling guidance. Its weaknesses are minor: the exact muapi command line is implied rather than given verbatim, and there is no explicit output-validation/retry checkpoint.

Suggestions

Include the literal `muapi image edit` command line with the parameters filled in (or a minimal curl example) so the generation step is copy-paste ready.

Add an explicit checkpoint after generation: verify the board rendered all panels and retry with adjusted prompt parameters if moderation flagged content or a panel is missing.

Trim the curl fallback boilerplate in the Notes to the essential 'use the raw endpoint + muapi predict wait <request_id>' line, since the full curl template adds tokens without new information.

Dimension	Reasoning	Score
Conciseness	The body is efficient and largely assumes Claude's competence, with the prompt block doing the work; minor padding exists in the 'Notes for the Executing Agent' (e.g. the curl fallback boilerplate) that could be trimmed but is genuinely useful guidance rather than concept explanation.	4 / 5
Actionability	Provides a concrete executable recipe (model id, image size, format, quality, moderation, full prompt block) and an explicit CLI command shape, with only minor gaps such as the literal `muapi image edit` invocation syntax not being fully spelled out as a copy-paste command.	4 / 5
Workflow Clarity	The single-step generation workflow is clearly sequenced with an input-gathering pre-check and a post-generation suggestion step; no destructive/batch operation is involved so the validation cap does not apply, though there is no explicit 'verify the output / retry on moderation failure' checkpoint.	4 / 5
Progressive Disclosure	Content is well-organized into Inputs, Steps, Trigger Keywords, and Notes sections with no nested references and no bundle files to navigate; it is a self-contained single-file skill that is appropriately structured, stopping just short of the cleanest possible overview-with-references pattern.	4 / 5
	Total	16 / 20 Passed

Description

66%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 vividly communicates what the skill produces and its aesthetic, with good coverage of concrete deliverables. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which limits the completeness dimension.

Suggestions

Append an explicit 'Use when...' clause naming the trigger phrases (e.g. 'Use when the user asks for a color analysis, personal color palette, seasonal color analysis, or capsule wardrobe board from a portrait photo.')

Lead with active third-person verbs (e.g. 'Generates a Color Analysis Board...') instead of opening with the noun phrase 'Turn a portrait photo into...'.

Fold one or two high-signal trigger synonyms directly into the description rather than relying solely on the body's Trigger Keywords list.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete deliverables ('best colors, undertone, makeup guide, capsule wardrobe, hair & jewelry recommendations') and an explicit output format ('clean beige/ivory grid'), but the actions are framed as outputs rather than verbs and coverage of the single generation action is slightly thin.	4 / 5
Completeness	The 'what' is clearly and richly stated, but there is no explicit 'Use when...' / 'when Claude should use it' clause in the description; per the guideline, a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural phrases a user might say ('color analysis', 'personal color palette', 'capsule wardrobe') but relies on the body's Trigger Keywords section rather than embedding file-extension-style synonyms or the most common phrasings directly in the description.	4 / 5
Distinctiveness Conflict Risk	The niche ('editorial Color Analysis Board from a portrait photo') is fairly distinct and unlikely to collide with unrelated skills, though it could overlap with broader styling/wardrobe or image-generation skills.	4 / 5
	Total	15 / 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: SamurAIGPT/Generative-Media-Skills
Path: library/visual/color-analysis-board/SKILL.md
Commit: 3b62f78

Reviewed: 6 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.