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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

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.

A well-structured orchestration skill body: clear multi-step workflow with gates and validation, and excellent progressive disclosure via verified one-level references. Slight redundancy in the backend-selection rule and a light error-recovery loop are the main trim/upgrade opportunities.

Suggestions

De-duplicate the backend-resolution guidance: state the 'substitute the local equivalent' caveat once and have Step 4 reference the top-level rule instead of restating it.

Expand the Step 4 failure path beyond 'auto-retry once' into an explicit validate→fix→retry feedback loop so it earns the full workflow-clarity anchor.

Pull the most critical backend invocation snippet (e.g. the preferred `baoyu-image-gen --provider codex-cli` call) inline into Step 4 rather than only linking out, to close the actionability gap.

Dimension	Reasoning	Score
Conciseness	Mostly dense procedural guidance with no padding of concepts Claude already knows, but the backend-resolution rule and 'substitute the local equivalent' caveat are stated in two places and could be tightened.	4 / 5
Actionability	Concrete option tables, file paths, naming conventions, and validation commands ('test -f refs/...') give mostly executable guidance; the actual backend invocation contract is deferred to a reference file, leaving a minor gap.	4 / 5
Workflow Clarity	Steps 0–5 are clearly sequenced with a progress checklist, blocking (⛔) and confirmation (⚠️) gates, and an explicit validation step ('test -f'), though the error-recovery feedback loop is limited to 'auto-retry once'.	4 / 5
Progressive Disclosure	The body is a well-organized overview with one-level-deep references to a real, verified bundle (palettes/, renderings/, dimensions/, workflow/, config/) and a consolidated References section, making navigation easy.	5 / 5
	Total	17 / 20 Passed

Description

92%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, third-person description that states concrete capabilities and explicit trigger phrases, clearly answering both what and when. Only minor gap is a few missing natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ('Generates article cover images') plus concrete capability parameters: 5 dimensions, 11 color palettes, 7 rendering styles, and three named aspect ratios — comprehensive coverage of what it can do.	5 / 5
Completeness	Clearly answers both what (generates covers with 5 dimensions, palettes, renderings, aspect ratios) and when ('Use when user asks to ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides three natural user-facing phrases ('generate cover image', 'create article cover', 'make cover') with synonym coverage, but omits common variations like '封面图' or 'blog cover' that a user might also say.	4 / 5
Distinctiveness Conflict Risk	The 'article cover images' niche plus the specific dimension/aspect vocabulary and distinct trigger phrases make it unlikely to fire for an unrelated skill.	5 / 5
	Total	19 / 20 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
Path: skills/baoyu-cover-image/SKILL.md
Commit: 1567581

Reviewed: 13 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.