story-cover

小说封面生成。根据书名、作者名自动分析题材风格，调用 GPT-Image-2 生成含标题和署名的专业级网文封面；Codex CLI 优先使用内置 ImageGen，无需单独 API Key。触发方式：/story-cover、/封面、「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」。

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

A highly actionable, well-structured skill body with executable scripts, concrete prompt templates, explicit validation checkpoints, and clean one-level-deep reference delegation. The only weak spot is mild repetition of the proxy-size caveat and platform-sizing rationale across sections.

Suggestions

Consolidate the '中转代理会忽略 size' caveat into a single place (e.g. the env-var table) and reference it from Step 1 / Step 5 instead of restating it each time.

Move the per-genre 书名/作者名 font-style tables into references/cover-styles.md alongside the visual-style library to shrink the SKILL.md body and keep all style data in one place.

Dimension	Reasoning	Score
Conciseness	Mostly lean, domain-specific reference (font-style tables, env-var table, executable scripts) that assumes Claude's competence and avoids explaining known concepts; minor redundancy in the '代理会忽略 size' caveat and platform-sizing logic recurring across the env table, Step 1, and Step 5 keeps it just below a 5.	4 / 5
Actionability	Fully executable, copy-paste-ready bash scripts for 文生图/图生图/导出尺寸 with `set -euo pipefail`, jq-built request bodies, and per-genre font keyword tables plus a complete prompt template, matching the 'fully executable covering common cases' anchor.	5 / 5
Workflow Clarity	Six clearly sequenced steps with explicit validation checkpoints (jq '.error' early-exit, `[ -s "$OUT" ]`, `[ -f "$SRC" ]`) and a Step 6 quality-check checklist with an iteration feedback loop, matching the 'clear sequence with explicit validation and feedback loops' anchor.	5 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to references/cover-styles.md (verified to exist), a 'when to load' table, and deliberate delegation of the visual-style library to avoid drift, matching the 'clear overview, one-level-deep references' anchor.	5 / 5
	Total	19 / 20 Passed

Description

95%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, specific description that clearly states what the skill does and when to invoke it, with comprehensive natural and slash-command triggers. Third-person voice is maintained throughout, with no first/second-person drift.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — '自动分析题材风格', '调用 GPT-Image-2 生成含标题和署名的专业级网文封面', '优先使用内置 ImageGen' — with only minor coverage gaps, matching the 'lists several specific actions' anchor rather than the narrower 1-2 actions of a 3.	4 / 5
Completeness	Explicitly answers both 'what' (封面生成 pipeline) and 'when' via the '触发方式：' clause with concrete trigger phrases, matching the anchor that requires both; the explicit trigger guidance avoids the missing-'Use when' cap at 3.	5 / 5
Trigger Term Quality	Comprehensive natural triggers including slash commands ('/story-cover', '/封面') and user phrases ('帮我做个封面', '生成封面图', '做个小说封面', '封面设计') with synonyms, matching the comprehensive-coverage anchor; not below since it covers natural synonyms users would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (网文封面生成) with distinct, cover-specific triggers and minimal overlap with other skills, matching the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 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

	Total	13 / 16 Passed

Repository: worldwonderer/oh-story-claudecode
Path: skills/story-cover/SKILL.md
Commit: 5de060f

Reviewed: 4 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.