"Generate a substantial summary and verify the ratio"
"Produce the summary in batches and validate the final total"
Rules
Default target ratio: 0.20
Default tolerance: 0.02
Accept only summaries between 18% and 22% of the original word count
Output must be in user's language of choice (e.g., pt-BR)
If the ratio is outside the allowed range, do not import the summary
In chat-only mode, if the source is very large, generate the summary in multiple batches and merge them before validation
All packaged helper scripts live in scripts/ inside this skill folder
Workflow
Start from a local plain-text book file or a downloaded Project Gutenberg text.
Count the source words with python scripts/book_tools.py count <original_file>.
Compute the target summary length with python scripts/book_tools.py target <original_file> --ratio 0.20.
If the source is too large for one reply, split it with python scripts/split_book.py <original_file> 3000.
Draft summary batches in order, preserving chronology and section fidelity.
Merge the batches with python scripts/book_tools.py aggregate <summary_file> <batch_files...>.
Validate the final ratio with python scripts/verify_summary_ratio.py <original_file> <summary_file>.
Key Files
scripts/book_tools.py
scripts/split_book.py
scripts/verify_summary_ratio.py
SKILL.md
Notes
The packaged scripts use only the Python standard library.
Run the commands from the skill folder, or use explicit paths if you call them from elsewhere.
For very large books, prefer the automated pipeline over single-turn chat drafting.
In chat-only mode, books above roughly 80k words should be summarized over multiple turns; do not pretend a single short draft satisfies the 20% rule.
1---2name: case-053213description: Book Summarizer4---56# Book Summarizer78Use this skill for requests like:910- "Summarize this book at a 20% compression ratio"11- "Generate a substantial summary and verify the ratio"12- "Produce the summary in batches and validate the final total"1314## Rules1516- Default target ratio: `0.20`17- Default tolerance: `0.02`18- Accept only summaries between `18%` and `22%` of the original word count19- Output must be in user's language of choice (e.g., pt-BR)20- If the ratio is outside the allowed range, do not import the summary21- In chat-only mode, if the source is very large, generate the summary in multiple batches and merge them before validation22- All packaged helper scripts live in `scripts/` inside this skill folder2324## Workflow25261. Start from a local plain-text book file or a downloaded Project Gutenberg text.272. Count the source words with `python scripts/book_tools.py count <original_file>`.283. Compute the target summary length with `python scripts/book_tools.py target <original_file> --ratio 0.20`.294. If the source is too large for one reply, split it with `python scripts/split_book.py <original_file> 3000`.305. Draft summary batches in order, preserving chronology and section fidelity.316. Merge the batches with `python scripts/book_tools.py aggregate <summary_file> <batch_files...>`.327. Validate the final ratio with `python scripts/verify_summary_ratio.py <original_file> <summary_file>`.3334## Key Files3536- `scripts/book_tools.py`37- `scripts/split_book.py`38- `scripts/verify_summary_ratio.py`39- `SKILL.md`4041## Notes4243- The packaged scripts use only the Python standard library.44- Run the commands from the skill folder, or use explicit paths if you call them from elsewhere.45- For very large books, prefer the automated pipeline over single-turn chat drafting.46- In chat-only mode, books above roughly 80k words should be summarized over multiple turns; do not pretend a single short draft satisfies the 20% rule.4748
Run npx skillmds@latest add knownasnaffy/case-05321 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Book Summarizer It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: CAUTION, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
knownasnaffy (@knownasnaffy) published this skill. Their other Agent Skills are listed on their SkillMD profile.
knownasnaffy