CtrlK
BlogDocsLog inGet started
Tessl Logo

story-long-analyze

长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。单一深度拆解管道:跑完黄金三章(Stage 1)后产出快速预览报告并询问是否继续全量拆解,确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告,全程产物落盘 拆文库/{书名}/。触发方式:/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」「深度拆解」「完整拆解」「系统拆解」或提供小说文本文件路径——全部进入同一管道。

69

Quality

86%

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

73%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-architected, highly actionable skill with excellent workflow sequencing and validation feedback loops, supported by a clean one-level-deep reference bundle. Its main weakness is conciseness: several rationale and compatibility passages are heavier than needed.

Suggestions

Move the Agent compatibility / version-notice blockquotes and the format-drift rationale into a reference file (e.g. pipeline-ops.md), keeping only the operational rule in SKILL.md to reduce token load.

Tighten the Stage 2 hard-check prose: the four grep checks are valuable but their justifications can be trimmed to one line each while preserving the exact regexes.

The description frontmatter is very long; consider shortening it and moving trigger-phrase enumeration into the body's 流程衔接 section to keep frontmatter lean.

DimensionReasoningScore

Conciseness

The body is dense and largely assumes Claude's competence, but several passages over-explain rationale (e.g., the multi-paragraph Agent compatibility, version-notice, and format-drift justifications) that could be tightened or moved to references.

3 / 5

Actionability

Provides concrete executable guidance — a copy-paste Agent spawn template, shell one-liners for 汇总 and grep-based hard checks with exact regexes — with only minor gaps (some Stage steps defer detail to references rather than inlining).

4 / 5

Workflow Clarity

A clearly sequenced Stage 0-6 pipeline with explicit validation checkpoints (章节边界校验, 计数验证, 无损检查, 质量阈值自检), feedback loops (haiku→sonnet retry, validate→fix→revalidate), and resume-from-checkpoint handling for batch/destructive operations.

5 / 5

Progressive Disclosure

SKILL.md is an overview pointing to one-level-deep, clearly signaled references (output-templates.md, material-decomposition.md, pipeline-ops.md, etc., all verified to exist), with a load-time table; structure is good but the body still inlines substantial detail that could live in references.

4 / 5

Total

16

/

20

Passed

Description

100%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 is specific, comprehensive, and explicitly covers both what the skill does and when to trigger it, with a strong set of natural-language and command triggers. It is notably verbose for a frontmatter description, but verbosity is not penalized under the completeness/specificity anchors.

DimensionReasoningScore

Specificity

Enumerates multiple concrete analysis actions — 黄金三章拆解, 人设架构, 爽点设计, 节奏控制 — plus a staged pipeline (逐章摘要、聚合分析、设定关系、汇总报告) with artifacts landing on disk, matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly states what the skill does (deep deconstruction pipeline through six stages with disk persistence under 拆文库/{书名}/) and when to trigger it (named commands plus file-path input), answering both what and when with concrete phrases.

5 / 5

Trigger Term Quality

Provides both slash-command triggers (/story-long-analyze、/长篇拆文) and natural-language phrases users would say (「帮我拆这本书」「拆这本书」「分析黄金三章」「深度拆解」「完整拆解」), giving comprehensive synonym coverage.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (long-form web-novel structural deconstruction) with distinctive Chinese-language trigger phrases unlikely to collide with other skills, giving minimal conflict risk.

5 / 5

Total

20

/

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.

Validation13 / 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
worldwonderer/oh-story-claudecode
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.