baoyu-article-illustrator

Article illustrations: type × style × palette consistency.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/creative/baoyu-article-illustrator/SKILL.md

Quality

Content

78%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 skill body is well-structured, actionable, and progressively disclosed with verified reference files. Its main weaknesses are minor redundancy between the Core Principles and Pitfalls sections and a missing download-verification checkpoint in the image-generation workflow.

Suggestions

Add a verification step in Step 6 to confirm the downloaded image is non-empty/valid before inserting it into the article, closing the batch-operation validation gap.

De-duplicate the 'Strip secrets' and image_generate-URL points between Core Principles and Pitfalls to recover token budget.

Inline a minimal prompt-template skeleton (the ZONES/LABELS/COLORS/STYLE/ASPECT structure) so the core flow is executable without opening references/prompt-construction.md.

Dimension	Reasoning	Score
Conciseness	The body is dense and information-rich with tables and specific tool calls, assuming Claude's competence; it is not a 5 because Core Principles and Pitfalls repeat several items (e.g., 'Strip secrets', the image_generate-returns-a-URL point).	4 / 5
Actionability	Guidance is mostly executable — named tool calls with parameters, exact aspect-ratio mappings, and a copy-paste `curl -sSL -o ...` command; the gap keeping it from 5 is that full prompt templates are externalized to references/prompt-construction.md rather than shown inline.	4 / 5
Workflow Clarity	A 7-step checklist plus a BLOCKING prompt-before-image gate and an auto-retry-once feedback loop give a clear sequence with most checkpoints present; it is not 5 because there is no verification that downloaded images are valid/non-empty before insertion.	4 / 5
Progressive Disclosure	The body is a clear overview with a bottom References table and inline links to one-level-deep files (workflow.md, usage.md, styles.md, style-presets.md, prompt-construction.md), all of which exist on disk; content is appropriately split and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

48%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 concise and identifies a distinct niche, but it is too terse: it lacks concrete action verbs, natural trigger phrases, and any 'Use when' guidance. Adding an explicit trigger clause and a couple of action verbs would lift specificity and completeness.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. 'Use when the user asks to illustrate an article, add images to content, or says 为文章配图.'

Include concrete action verbs such as 'analyzes articles, identifies illustration positions, generates images' so the description states what the skill does, not just its framing.

Add common synonyms/file-context terms users actually say ('illustrate', 'add images', 'article figures') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'Article illustrations: type × style × palette consistency' names the domain and a framing concept but states no concrete actions (e.g., analyze, generate, insert), matching the 'names the domain but actions are minimal' anchor rather than the 3-anchor which requires 1-2 concrete actions.	2 / 5
Completeness	It conveys a clear 'what' (article illustrations with type/style/palette consistency) but has no 'Use when...' clause or equivalent trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	'Article illustrations' is a genuinely natural phrase a user might say, but the description omits common verb-form variations and synonyms like 'illustrate an article', 'add images', or '为文章配图', fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Article illustration with a type×style×palette framework is a clear, narrow niche with low overlap risk; it stops short of 5 only because explicit distinct triggers are absent from the description itself.	4 / 5
	Total	12 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/creative/baoyu-article-illustrator/SKILL.md
Commit: 6680afb

Reviewed: about 3 hours 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.