CtrlK
BlogDocsLog inGet started
Tessl Logo

baoyu-article-illustrator

Article illustrations: type × style × palette consistency.

52

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

85%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 an exemplary instruction-only skill: a clear 7-step workflow with a blocking validation gate, concrete tool calls and file-naming conventions, and a clean one-level-deep reference structure with working links. Its only real flaws are a Pitfalls section that largely duplicates earlier sections and a couple of minor template/edge-case inconsistencies.

Suggestions

Trim the Pitfalls section to only the 1-2 pitfalls not already stated in Core Principles and Step 6 (data integrity, metaphor literalization), cutting the five restated items to save tokens.

Fix the outline template so the yaml fence contains actual YAML (use '#' headings or 'Illustration 1:' keys instead of '## Illustration 1' markdown inside the block).

Specify the recovery path when the auto-retry in Step 6 also fails (e.g., skip and report, or ask the user) so batch runs don't stall.

DimensionReasoningScore

Conciseness

The body is dense and table-driven with no explanation of concepts Claude already knows, but the Pitfalls section restates ~5 earlier points nearly verbatim (strip secrets ↔ Pitfall 2, prompt-file mandate ↔ Pitfall 4, URL download ↔ Pitfall 6, aspect ratios ↔ Pitfall 5, backend note ↔ Pitfall 7). Mostly efficient with a trimmable duplicated section — anchor 4, not 5, since that section costs meaningful tokens for emphasis only.

4 / 5

Actionability

Guidance is highly concrete: exact output tree, `curl -sSL -o "{output-dir}/NN-{type}-{slug}.png" "{url}"`, explicit aspect-ratio enum mapping, slug/conflict rules, and per-step tool calls. Minor gaps keep it below fully copy-paste-ready: the outline template mixes markdown headers inside a yaml fence, and 'auto-retry once' gives no path for repeated failure — anchor 4.

4 / 5

Workflow Clarity

Seven explicitly sequenced steps with a checklist, an explicit validation checkpoint ('BLOCKING: Every illustration must have a saved prompt file before any image is generated'), a failure feedback loop ('On generation failure, auto-retry once'), and ordered clarify-question rules with skip conditions. This batch operation has its validation gate present — matches anchor 5.

5 / 5

Progressive Disclosure

SKILL.md is a lean overview; all detail lives in one-level-deep references (workflow.md, styles.md, style-presets.md, prompt-construction.md, usage.md — all verified to exist), each inline-linked with section anchors per step and summarized in a References table. Clear overview with well-signaled one-level references — anchor 5.

5 / 5

Total

18

/

20

Passed

Description

36%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 a terse noun phrase that identifies the domain but omits the skill's actions, any 'use when' trigger guidance, and the natural trigger phrases (including the Chinese ones the body documents). It would rarely be selected by a model matching user requests against descriptions, even though the body contains an excellent 'When to Use' section whose content should be lifted into the description.

Suggestions

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

State the concrete actions: 'Analyze articles, propose illustration positions, generate images with Type × Style × Palette consistency, and insert them into the article.'

Include the natural synonyms users would say (illustrate, add images, 配图, article illustration) so trigger matching works across phrasings.

DimensionReasoningScore

Specificity

"Article illustrations: type × style × palette consistency." names the domain and its three dimensions but contains no concrete actions — no mention of analyzing articles, generating images, or inserting them. This matches 'Names the domain but actions are minimal or generic' rather than anchor 3, which requires 1-2 concrete actions.

2 / 5

Completeness

The 'what' is only weakly stated (a noun phrase plus a consistency claim, not what the skill actually does) and there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description. Matches anchor 2 ('vague what and no when'); the missing trigger clause also caps completeness at 3 per guidelines.

2 / 5

Trigger Term Quality

"Article illustrations" is a relevant keyword a user might say, but the description omits common natural variations like "illustrate article", "add images to article", or the Chinese "为文章配图" that the body itself lists. Some relevant keywords present, missing common synonyms — anchor 3, not 4, since coverage is essentially one term.

3 / 5

Distinctiveness Conflict Risk

"Article illustrations" is a fairly niche domain, but with no trigger phrases or capability statement the description could still overlap with general image-generation or diagram skills. Somewhat specific but overlap risk remains — anchor 3, not 4, since nothing distinguishes it from closely related skills.

3 / 5

Total

10

/

20

Passed

Validation

75%

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

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

Warning

Total

12

/

16

Passed

Repository
NousResearch/hermes-agent
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.