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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/story-import/SKILL.md

Quality

Content

67%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 thorough, well-validated multi-phase workflow with concrete commands, templates, and a clear reference structure. Its main weaknesses are length/repetition and detail inlined in the body that could live in reference files.

Suggestions

Consolidate the repeated fallback warnings ("绝不把...询问甩给用户", ZCode/Codex/Antigravity compatibility notes) into a single shared section instead of restating them in both the long-form and short-form phases.

Move the full 细纲 multi-section template and the long/short directory-tree listings into a reference file, keeping only a compact schema pointer in SKILL.md.

Provide resolved example commands for at least one concrete path so the placeholders ({PYTHON}, {项目根}, {story-import skill 根}) have a copy-paste-ready reference instance.

Dimension	Reasoning	Score
Conciseness	Information-dense and domain-specific rather than padded with general knowledge, but at ~648 lines it repeats the same fallback warnings (e.g. "绝不把...询问甩给用户") across phases and includes dense compatibility caveats that could be tightened.	3 / 5
Actionability	Provides concrete commands (tracking_commit.py init/check, wordcount measure with explicit python3→python→py -3 probing) and detailed templates, but commands still carry unresolved placeholders like {PYTHON}, {项目根}, and {story-import skill 根} that the model must resolve.	4 / 5
Workflow Clarity	Phases 1-4 are clearly sequenced with explicit validation (tracking_commit.py check, 置信度>=0.85 quality gates, fail-fast) and completion checklists, but the many conditional fallback branches (ZCode/Codex/Antigravity/version mismatches) somewhat obscure the main path.	4 / 5
Progressive Disclosure	References seven real reference files (all verified to exist) via clearly signaled one-level-deep links, organized by a 参考资料索引 table; however detailed templates and directory structures are inlined in SKILL.md rather than fully delegated to references.	4 / 5
	Total	15 / 20 Passed

Description

91%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, domain-specific description that clearly states what the skill does and gives explicit, natural trigger phrases. It is held back only by slightly abstract action wording and inherent overlap with the analyze skills it reuses.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "反向解析为标准项目目录结构", "复用...拆解管道", "按篇幅自动分流" — naming the domain and multiple specific operations, though the actions stay domain-abstract rather than fully concrete.	4 / 5
Completeness	Explicitly answers both what (逆向导入已有小说，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.	5 / 5
Trigger Term Quality	Provides the command "/story-import" plus natural synonyms users would say — 「导入小说」「反向解析」「导入」「把我的书导进来」 — giving comprehensive coverage of natural phrasings.	5 / 5
Distinctiveness Conflict Risk	Clear niche (reverse-importing existing works for continued writing) with distinct triggers, but it explicitly reuses story-long-analyze/story-short-analyze pipelines, creating minor overlap risk with those closely related skills.	4 / 5
	Total	18 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (648 lines); consider splitting into references/ and linking	Warning
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	12 / 16 Passed

Repository: worldwonderer/oh-story-claudecode
Path: skills/story-import/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.