CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

story-cover

小说封面生成与提示词设计。根据书名、作者名和题材构建封面提示词;用户只要提示词时不生图,要求封面图时调用 GPT-Image-2,Codex CLI 优先使用内置 ImageGen。触发方式:/story-cover、/封面、「帮我做个封面」「生成封面图」「封面提示词」「封面设计」。

Quality

88%

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

SKILL.md
Quality
Evals
Security

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 well-engineered workflow skill: complete executable template and export script, clearly sequenced steps with validation checkpoints and an iteration loop, and exemplary progressive disclosure that defers the style library and API details to on-demand reference files. The only room for improvement is minor tightening of small redundancies in the Step 5 script and surrounding notes.

DimensionReasoningScore

Conciseness

The body is dense and operational throughout — project-specific knowledge Claude could not infer (`.active-book` resolution heuristics, platform pixel specs, directory conventions) with no padding or explanation of concepts Claude already knows. Minor trimming opportunities exist (the duplicate `[ -f "$SRC" ]` check in the Step 5 script, the repeated safe-area note below it, long parenthetical exclusion lists), keeping it at anchor 4 rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Guidance is fully executable: a single complete prompt template with every slot defined, a copy-paste bash script for platform-size export with magick/convert/sips fallbacks and explicit error messages, concrete file-naming rules (`封面_vN.png`, `.prompt.txt`), and exact dimensions (600×800, 200×280). The built-in-tool path cannot be literal code, but its steps are precisely specified; this matches anchor 5.

5 / 5

Workflow Clarity

Six explicitly sequenced steps with validation checkpoints throughout: pre-flight file existence check with exit-on-failure, "确认可读后把原图绝对路径交给 Step 5", a Step 6 quality-check checklist table, and a feedback loop ("未达标或作者希望调整时,可更换构图、色调、字体或平台风格重出"), plus explicit no-silent-fallback error policy. This matches anchor 5; anchor 4 would lack one of the checklist or recovery loop.

5 / 5

Progressive Disclosure

The body keeps only the workflow overview while bulky material is split into two real, one-level-deep references, each clearly signaled and loaded on demand: [references/cover-styles.md] for the style library and [references/api-fallback.md] with the explicit instruction "走该通路再读". Both files exist and contain the sections (「风格库」「平台风格」「构图变体」「题材推断规则」) the body cites; navigation is easy, matching anchor 5.

5 / 5

Total

19

/

20

Passed

Description

83%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 description that states concrete capabilities with explicit mode-conditioned behavior (prompt-only vs. image generation, tool routing) and an explicit trigger list including both slash commands and natural phrases. The only weaknesses are a few missing natural trigger variants and slightly generic cover-design phrases that create minor overlap risk with general design skills.

DimensionReasoningScore

Specificity

The description names concrete, conditional actions — "根据书名、作者名和题材构建封面提示词", "用户只要提示词时不生图,要求封面图时调用 GPT-Image-2", "Codex CLI 优先使用内置 ImageGen" — which is several specific actions with clear mode routing. It stops short of anchor 5 because capabilities the skill actually covers (platform-specific sizing/export, quality checks) are absent, leaving minor gaps in coverage.

4 / 5

Completeness

It explicitly answers both questions: what it does ("小说封面生成与提示词设计。根据书名、作者名和题材构建封面提示词…调用 GPT-Image-2") and when to use it via an explicit "触发方式:" clause listing concrete trigger phrases. This matches anchor 5 exactly; anchor 4 would require the 'when' to be less explicit than the enumerated trigger list given.

5 / 5

Trigger Term Quality

Triggers include slash commands ("/story-cover", "/封面") plus four natural user phrases (「帮我做个封面」「生成封面图」「封面提示词」「封面设计」) covering the main intent space. A few natural variants are missing (e.g., 「做个封面图」「换个封面」), so it fits anchor 4 (good coverage, a few natural terms missing) rather than anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The niche (novel covers from 书名/作者名/题材 with GPT-Image-2) is clearly distinct from general image or design skills. However, triggers like 「封面设计」 and 「生成封面图」 are generic enough to also match non-novel cover requests, giving minor overlap risk with closely related design/image skills — anchor 4 rather than anchor 5's minimal conflict risk.

4 / 5

Total

17

/

20

Passed

Validation

81%

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

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

Total

13

/

16

Passed

Repository

zenstory-ai/oh-story-claudecode

Path

skills/story-cover/SKILL.md

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.