CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

story-import

逆向导入已有小说。将已写好的小说(半成品或完本)反向解析为标准项目目录结构,兼容 story-long-write / story-short-write 后续写作流程;内部复用 story-long-analyze / story-short-analyze 的拆解管道,按篇幅自动分流。触发方式:/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」。

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

The content is a strongly executable phase-based workflow with concrete templates, commands, author-confirmation checkpoints, and validation steps, supported by a clean overview-plus-references structure. Its only weaknesses are minor: some duplicated caveats could be tightened, and a few reference files sit two links deep instead of being directly surfaced from SKILL.md.

Suggestions

Deduplicate the Agent-compatibility and version-mismatch guidance: state the rules once in the top blockquote and have Step 4 reference it ('按顶部说明') instead of restating the details, trimming the conciseness gap.

Surface the second-hop reference files directly in SKILL.md (e.g. mention outline-reverse-rules.md and tracking-initialization.md / character-state-reverse.md in the 时刻表 or Phase descriptions) so every bundle file is one clearly-signaled link from the overview.

Consolidate the 对标 boundary rules stated in both 名词与目录边界 and Phase 1 Step 3 into a single location, with the other spot pointing back to it.

DimensionReasoningScore

Conciseness

The body is almost entirely project-specific operational rules with no padding about concepts Claude already knows, but contains minor over-explanation that could be trimmed: the Agent-compatibility/version blockquote details are restated in Step 4, and the 对标 boundary rules appear in both the 名词与目录边界 section and Step 3. This matches anchor 4 (efficient with minor trims) rather than anchor 3, since the redundancy is limited.

4 / 5

Actionability

Fully executable guidance: exact file paths ({书目录}/.story/work/导入记录.md), a copy-paste-ready 导入记录 template with progress checklist, exact commands (scripts/tracking_commit.py init / check), verbatim author-facing questions, and explicit decision branches covering the common cases (装环境 vs 直接导入, 接着残章写 vs 先补完再导入).

5 / 5

Workflow Clarity

The 时刻表 table sequences Phases 1–5 with explicit read/落盘 handoffs, and validation checkpoints appear throughout: `check` 通过后勾进度, 结构迁移验收, Phase 5 自检, 卷划分必须等作者确认, plus batch-recovery rules (续跑从第 B+1 章整批重做). The destructive/batch cap does not apply because validation is explicit, matching the anchor-5 pattern of clear sequence with feedback loops and checklists.

5 / 5

Progressive Disclosure

The body is a well-organized overview with one clearly signaled, real reference file per phase and a navigation table mapping each 时刻 to what to read. However, three reference files (outline-reverse-rules.md, tracking-initialization.md, character-state-reverse.md) are only reachable via a second hop from other references rather than directly from SKILL.md, a minor two-level nesting gap matching anchor 4 rather than the clean one-level structure of anchor 5.

4 / 5

Total

18

/

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.

The description clearly states what the skill does and gives explicit, natural trigger phrases including the command, giving strong completeness and trigger quality. It is held back slightly from top marks by unspecified concrete deliverables and minor overlap signaling with the sibling analyze skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — "反向解析为标准项目目录结构", "按篇幅自动分流", "复用 story-long-analyze / story-short-analyze 的拆解管道" — but coverage has gaps (no mention of the concrete outputs like 设定/大纲/正文/追踪), matching the 'several specific actions, minor gaps' anchor rather than the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both: what ("将已写好的小说(半成品或完本)反向解析为标准项目目录结构") and when ("触发方式:/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」") with concrete trigger phrases, matching anchor 5; the trigger-guidance cap does not apply because an explicit trigger clause is present.

5 / 5

Trigger Term Quality

Includes natural user phrases 「导入小说」「反向解析」「把我的书导进来」 plus the /story-import command, giving good keyword coverage; a few natural variations (e.g. 「导入我的小说」「把小说导进来」) are missing, so it falls just below the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (reverse-importing an existing finished or half-written novel into a writable project) with distinct triggers, but "内部复用 story-long-analyze / story-short-analyze 的拆解管道" creates minor overlap risk with those closely related skills, matching the 'mostly distinct' anchor rather than the minimal-conflict anchor 5.

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-import/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.