baoyu-cover-image

Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 11 color palettes and 7 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".

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 skill body is an actionable, well-sequenced orchestration guide with strong workflow gates and excellent progressive disclosure into a real reference bundle. Its main weakness is length and some repetition in the backend-selection material, which keeps conciseness below the top anchor.

Suggestions

Consolidate the image-backend selection logic into one place and have Step 4 reference it once, rather than restating the rule in both '## Image Generation Tools' and Step 4.

Move the detailed Codex/Cursor runtime caveats (aspect-ratio and output-path workarounds) into references/codex-imagegen.md or a runtime-compat reference, keeping only the routing decision inline.

Trim the repeated ⛔ prohibition paragraphs ('Never substitute SVG...', 'Never repair rendered text...') to a single concise rule set, since the same constraints reappear under 'Image Modification'.

Dimension	Reasoning	Score
Conciseness	The body is thorough and mostly efficient, but at ~280 lines it could be tightened: the backend-resolution rule is stated in '## Image Generation Tools' and re-referenced in Step 4, and lengthy Codex/Cursor caveats sit inline where they might live in references. It does not waste tokens explaining concepts Claude already knows, so it clears score 2 but not the 'every token earns its place' bar.	2 / 3
Actionability	Guidance is highly concrete and executable for an instruction-only skill: exact option names (--type, --palette, etc.) with their value sets, file paths, naming conventions (NN-{type}-[slug].md), a verification command ('test -f refs/ref-NN-{slug}.{ext}'), and specific backend tool names. No pseudocode vagueness is present.	3 / 3
Workflow Clarity	A clear Steps 0–5 sequence is given with a progress checklist, a flow diagram, explicit blocking gates (Step 0 '⛔ BLOCKING', Step 2 hard gate), validation checkpoints ('Before writing → Verify: test -f ...'), backup-before-regenerate, and an 'On failure: auto-retry once' feedback loop—matching the score-3 anchor.	3 / 3
Progressive Disclosure	The body is an overview that links one-level-deep into a real, well-organized bundle (dimensions/, palettes/, renderings/, workflow/, config/), with all cited paths verified to exist and a consolidated '## References' section for navigation. Content is appropriately split across files 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 concrete, uses correct third-person voice, and supplies explicit 'Use when...' triggers with natural phrasings, cleanly answering both what the skill does and when to invoke it. It carves a distinct niche that is unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	The description lists concrete specifics—'Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 11 color palettes and 7 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects'—naming the domain plus enumerated concrete capabilities rather than vague language. It uses third person ('Generates', 'Supports') per the guidelines, so no voice penalty applies.	3 / 3
Completeness	It explicitly answers both 'what' ('Generates article cover images...') and 'when' with an explicit 'Use when user asks to...' trigger clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	It provides natural phrasings a user would actually say—'generate cover image', 'create article cover', 'make cover'—covering common variations rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	'article cover images' is a clear niche with distinct triggers ('generate cover image', 'create article cover', 'make cover'), 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: 18 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 26 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.