Book summarizer

Use this skill when the user wants a long-form book summarized in the user's preferred language at an explicitly verified 20 percent compression ratio, with...

Security Scan

The skill appears to do what it claims: local helper scripts plus instructions for producing and validating 20% summaries; nothing in the bundle attempts unexpected network access or credential collection.

Purpose & Capability

Name/description match the included scripts and instructions. The three Python helper scripts implement counting, splitting, aggregating, and ratio verification which are appropriate for a summarizer. Minor mismatch: the skill declares no required binaries but the SKILL.md and scripts assume a Python runtime (commands like `python scripts/...`).

Instruction Scope

SKILL.md confines activity to local files and the provided scripts (count, split, aggregate, verify). It also instructs the agent to draft summary batches 'in chat' — which implies sending book text to the LLM provider during summarization. The skill itself does not add remote endpoints, but using it will typically transmit source text to whatever model/service the agent invokes.

Install Mechanism

No install spec (instruction-only). Scripts are bundled and rely only on the Python standard library; nothing is downloaded or executed from external URLs.

Credentials

No environment variables, credentials, or config paths are requested. The skill does not require unrelated secrets or system credentials.

Persistence & Privilege

always is false and the skill does not request elevated or persistent system presence. It does not modify other skills or system-wide settings.

Assessment

This package is internally consistent and only operates on local text files via bundled Python scripts. Before installing: (1) ensure you have a Python runtime available (the skill's metadata omits this dependency), (2) be aware that summarization normally involves sending book text to the model/provider — do not use it for sensitive/private documents unless you trust your model endpoint, and (3) respect copyright for non-public works. The code is small and uses only the standard library; review it yourself if you want to confirm behavior locally.

Use this skill for requests like:

• "Summarize this book at a 20% compression ratio"
• "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

1. Start from a local plain-text book file or a downloaded Project Gutenberg text.
2. Count the source words with python scripts/book_tools.py count <original_file>.
3. Compute the target summary length with python scripts/book_tools.py target <original_file> --ratio 0.20.
4. If the source is too large for one reply, split it with python scripts/split_book.py <original_file> 3000.
5. Draft summary batches in order, preserving chronology and section fidelity.
6. Merge the batches with python scripts/book_tools.py aggregate <summary_file> <batch_files...>.
7. 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.