story-long-analyze
The story-long-analyze skill performs deep structural analysis of long-form web novels. It breaks down plot, character architecture, pacing, and emotional design through a multi-stage pipeline, outputting structured reports and analysis files into a local library.
Is story-long-analyze safe to install?
Review the source first: our audit of story-long-analyze's source files found 5 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill performs extensive file system operations, including reading source text files and writing numerous analysis files into a local directory structure. It also spawns sub-agents to process content.
How we audit skills: our security review methodology.
Who is this skill for?
Writers and editors who want to analyze successful long-form web novels to understand their structure, pacing, and reader engagement techniques.
What can you do with it?
- Analyzing the golden three chapters of a novel for hook and pacing.
- Generating chapter-by-chapter summaries and extracting key plot points.
- Mapping character relationships and development throughout a story.
- Identifying emotional beats, reader demand engines, and recurring tropes.
- Synthesizing writing style profiles including sentence length and dialogue patterns.
How good is this skill?
Quality score: 9/10. The skill provides a highly detailed and structured methodology for literary analysis. It includes robust error handling, quality checks, and clear documentation for its pipeline stages.
What does the skill file contain?
# story-long-analyze：长篇网文拆文
你是网络小说结构分析师。
**核心信念：看懂别人的爆款，才能写出自己的爆款。**
---
> Agent 兼容性：检查专业 agent 是否可用时，按 `.claude/agents/{agent}.md` → `.opencode/agents/{agent}.md` → `.codex/agents/{agent}.toml` 的顺序查找。Codex 原生子代理调用优先使用同名 `agent_type`；如果当前 Codex 运行时返回 `unknown agent_type` 或未暴露 custom-agent registry，必须降级为 solo/direct 执行并报告 fallback。Claude/OpenCode 兼容面保留 `subagent_type`。
## 拆解边界声明（主线程同样适用）
你亲手做的**黄金三章深度拆解（Stage 1）、Stage 2 串行降级逐章处理、以及 Stage 3-6 的聚合/设定/报告/文风合成**，与 chapter-extractor 子代理遵循同一逻辑：拆的是用户**合法持有、拥有使用权**的虚构作品（已出版/连载或自有），性质是**只读的转化性文学批评**（编辑/评论/写作教学视角，不复制、不传播、不指导现实行为）。通俗题材里的家暴、出轨、复仇、暴力、...Frequently asked questions
What is the output format of the analysis?
The skill generates a directory structure under '拆文库/{书名}/' containing markdown files for summaries, character profiles, plot analysis, pacing, emotional modules, and a final report.
Can I resume an analysis if it stops?
Yes. The skill maintains a '_progress.md' file that tracks the current stage and chapter, allowing it to resume from the last breakpoint.
Does the skill handle sensitive content?
The skill is designed to treat common fictional narrative elements like violence or dark ethics as structural data for analysis and will not refuse to process chapters based on these themes.
How does it handle very long novels?
It uses a multi-stage pipeline with parallel processing for chapter summaries and specific分块 (chunking) strategies for aggregation stages to manage context limits.
Related skills
obsidian-markdown
51.9KUsers working with Obsidian vault files who need to generate or modify notes using Obsidian-specific syntax
The obsidian-markdown skill provides instructions and syntax patterns for creating and editing Obsidian Flavored Markdown. It supports wikilinks, embeds, callouts, frontmatter properties, tags, comments, highlights, LaTeX math, Mermaid diagrams, and footnotes.
humanizer-zh
35.2KEditors, writers, and content reviewers who need to refine AI-generated drafts to improve readability and authenticity
Humanizer-zh is a text editing skill that identifies and removes common AI-generated writing patterns to make content sound more natural and human-like. It provides a structured process for rewriting text by eliminating filler phrases, formulaic structures, and vague attributions while injecting personality and specific detail.
tavily-research
13.5KUsers requiring comprehensive multi-source analysis, market reports, literature reviews, or detailed comparisons
The tavily-research skill provides AI-powered deep research capabilities using the Tavily CLI. It gathers web sources, synthesizes information, and generates cited reports in text or JSON formats.
firecrawl-market-research
12.8KUsers requiring automated market research, financial data aggregation, or industry analysis
The firecrawl-market-research skill extracts market, financial, and company data using the Firecrawl API. It generates structured research reports including industry trends, company profiles, and comparison tables.