CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

baoyu-article-illustrator

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style × Palette three-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary instruction-style skill body: highly actionable with exact paths, flags, and option tables; a gated six-step workflow with explicit batch validation and retry loops; and clean progressive disclosure where every reference resolves to a real, well-organized bundle file. The only weakness is minor — a couple of duplicated runtime-substitution caveats that could be consolidated.

DimensionReasoningScore

Conciseness

Dense, table-driven content with no explanations of concepts Claude already knows, but a few trimmable redundancies: the runtime-substitution caveat is stated twice ("Concrete AskUserQuestion references below are examples — substitute the local equivalent" and "Tool names above are examples; use the local equivalent in other runtimes") and backend selection is restated in Step 5.2. Fits anchor 4 (efficient, minor instances that could be trimmed); not 5 because not every token earns its place.

4 / 5

Actionability

Provides exact, executable guidance throughout: file patterns ("prompts/NN-{type}-[slug].md"), concrete flag syntax ("--type infographic --style vector-illustration --palette macaron", "--preset edu-visual", "--ref <files...>"), resolved EXTEND.md paths with fallback order, a specific AskUserQuestion option table, and an output-path table. As an instruction-only skill, the guidance is copy-paste-ready and covers the common cases, matching anchor 5.

5 / 5

Workflow Clarity

Six clearly sequenced steps with a checklist, explicit hard gates ("⛔ BLOCKING", "Do not start Step 4 or later until the user completes Step 3"), batch validation ("Never start a batch until all its prompt files exist on disk"), and an error-recovery feedback loop ("Retry failed items once without regenerating successful ones"). The batch-operation validation requirement is satisfied, matching anchor 5.

5 / 5

Progressive Disclosure

The body is a genuine overview with well-signaled, one-level-deep references — all 8 referenced files exist in the bundle — and even includes conditional-loading guidance ("Load references/codex-imagegen.md only for this branch"). The styles.md → styles/*.md second level is an organized gallery fan-out rather than a buried chain, matching anchor 5 (clear overview, easy navigation).

5 / 5

Total

19

/

20

Passed

Description

83%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 with concrete third-person actions and an explicit bilingual 'Use when' trigger clause. The main gaps are minor: a few missing natural trigger synonyms and one loosely scoped trigger ("add images"), plus unmentioned capabilities like inserting images into the article.

Suggestions

Add missing natural trigger synonyms such as "add illustrations", "插图", and standalone "配图" to the 'Use when' clause to broaden keyword coverage.

Mention the article-insertion output (e.g., "inserts generated illustrations into the article at the identified positions") so the 'what' covers the full capability set.

Scope the generic "add images" trigger to the article context (e.g., "add images to an article") to reduce overlap with general image-generation skills.

DimensionReasoningScore

Specificity

Lists three concrete actions covering the full pipeline ("Analyzes article structure", "identifies positions requiring visual aids", "generates illustrations") but omits other real capabilities such as inserting images into the article and output directory management, and "Type × Style × Palette three-dimension approach" is awkwardly phrased. This matches anchor 4 (several specific actions, minor gaps) rather than 5 (comprehensive coverage), and exceeds anchor 3's 1-2 actions.

4 / 5

Completeness

Clearly answers both "what" (three concrete actions) and "when" with explicit quoted trigger phrases ("Use when user asks to..."). Matches anchor 5 exactly; not 4 because the when-clause is already fully explicit with concrete triggers, not merely present. Third-person voice throughout, so no voice penalty applies.

5 / 5

Trigger Term Quality

Includes natural phrases users would say — "illustrate article", "add images", "generate images for article", "为文章配图" — with bilingual coverage, but misses common variations like "add illustrations", "插图", or standalone "配图". Fits anchor 4 (good keyword coverage, a few natural terms missing); not 5 because synonym coverage is not comprehensive.

4 / 5

Distinctiveness Conflict Risk

The article-illustration niche with article-scoped triggers is mostly distinct, but the unqualified trigger "add images" could overlap with general image-generation or image-editing skills. Fits anchor 4 (mostly distinct, minor overlap risk with closely related skills); not 5 because one trigger is not narrowly scoped.

4 / 5

Total

17

/

20

Passed

Validation

68%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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, 2 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 1 missing, 3 deeper-than-1-level

Warning

Total

11

/

16

Passed

Repository

JimLiu/baoyu-skills

Path

skills/baoyu-article-illustrator/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.