Book summarizer
PassAudited by ClawScan on May 1, 2026.
Overview
This skill appears to do what it says: it summarizes local book files with simple bundled Python scripts, while creating local intermediate/output files that users should manage.
This looks safe for its stated purpose. Before using it, be comfortable with an agent reading the selected book file and writing local batch or summary files. For sensitive material, work in a dedicated folder and remove intermediate batches afterward.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Using the skill may cause local Python scripts to read the selected book file and create local output files.
The skill instructs the agent to run local Python helper scripts. This is clearly disclosed and central to the summarization workflow, not hidden or unrelated behavior.
Count the source words with `python scripts/book_tools.py count <original_file>` ... split it with `python scripts/split_book.py <original_file> 3000` ... Validate the final ratio with `python scripts/verify_summary_ratio.py <original_file> <summary_file>`.
Use explicit input and output paths, run the commands from the skill folder as instructed, and avoid pointing the workflow at unrelated sensitive files.
Private or copyrighted book text may be copied into a local batches directory during processing.
The splitter stores chunks of the original source text as local batch files, which can persist copies of content the user provides.
batch_output_dir = Path(output_dir) if output_dir else input_path.parent / "batches" ... batch_path.write_text(batch, encoding="utf-8")
Use a controlled working directory and delete intermediate batch files if the source text is sensitive.