baoyu-comic

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, validated multi-step workflow and excellent progressive disclosure backed by a real, well-organized bundle. Its main weakness is length and redundancy between the backend-selection and image-generation sections.

Suggestions

Consolidate the overlapping backend-resolution rules in "Image Generation Tools" and "Step 7: Image Generation" into a single authoritative section referenced once, to reduce redundancy and tighten token use.

Tighten the two ⛔ prohibition rules (no SVG/code rendering, no text repair overlays) to concise one-line constraints with a brief rationale, moving extended justification to a reference file if needed.

Move the detailed EXTEND.md preference-edit examples and one-line backend-pin recipes (currently under "Changing Preferences") into references/config/preferences-schema.md, keeping only a pointer in the main body.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining concepts Claude already knows, but it is long (~340 lines) with notable redundancy — backend resolution rules are restated across "Image Generation Tools" and "Step 7: Image Generation", and the two ⛔ prohibition rules are elaborated at length, so it could be tightened.	2 / 3
Actionability	It provides concrete, copy-paste-ready guidance: specific commands (sips, pngquant, bun, npx), exact file naming and paths (prompts/NN-{cover\|page}-[slug].md, characters/characters.png), flag options, and frontmatter YAML examples.	3 / 3
Workflow Clarity	The 9-step process is clearly sequenced with a progress checklist, flow diagram, step summary table, and explicit validation/checkpoint gates (Step 1.1 BLOCKING, Step 2 REQUIRED, review gates at 4/6) plus feedback loops for batch/destructive operations (timestamped backup rule, retry-once policy, --ref failure recovery).	3 / 3
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references (art-styles/, tones/, presets/, layouts/, config/, workflow.md, partial-workflows.md, codex-imagegen.md), all verified to exist, with content appropriately split per style/tone/preset rather than inlined.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 specific, complete, and distinctive, using third person and providing explicit multilingual trigger terms. It is concise and avoids vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	"Creates original educational comics with detailed panel layouts and batch-capable image generation" lists multiple concrete actions (comic creation, panel layouts, batch image generation), matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	It clearly answers both what (knowledge comic creator with specific capabilities) and when (an explicit "Use when..." clause with concrete triggers), matching the anchor for answering both what AND when.	3 / 3
Trigger Term Quality	"Use when user asks to create '知识漫画', '教育漫画', 'biography comic', 'tutorial comic', or 'Logicomix-style comic'" gives good coverage of natural multilingual terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	"Knowledge comic creator" is a clear niche with distinctive multilingual comic triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

68%

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 — 11 / 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: 5 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 8 deeper-than-1-level	Warning

	Total	11 / 16 Passed

Repository: jimliu/baoyu-skills
Commit: c9a50cc

Reviewed: 3 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.