Bytesagain Doc Summarizer

Summarize and analyze text documents without external APIs. Use when extracting key points from reports, ranking bullet points, identifying keywords, checkin...

Security Scan

The skill is internally consistent with its description (local, Python-based text summarization) and requests no credentials or installs, but the bundled shell script contains an implementation bug that will likely prevent it from working as intended unless fixed.

Purpose & Capability

Name/description promise local document summarization and analysis; the provided shell script and embedded Python implement summary, bullets, keywords, stats, outline, and compare using only local file reads and text processing. Required tools (bash, python3) match the stated purpose and no unrelated credentials or binaries are requested.

Instruction Scope

The SKILL.md usage and commands align with the script. However, the script uses single-quoted here-documents (<< 'PYEOF') but embeds "$file", "$f1", "$f2" etc. inside the Python code. Because the here-doc delimiter is single-quoted, shell variable expansion is suppressed and the Python code will attempt to open files literally named "$file" (not the intended path). This is a functional bug (not a secret-exfiltration or scope creep). The script otherwise only reads the files the user supplies and does not send data externally.

Install Mechanism

No install spec or external downloads are provided; this is instruction-only with a bundled script. No archives or remote installers are used, so there is minimal install risk.

Credentials

The skill requires no environment variables, credentials, or config paths. That is proportional to its stated functionality (local text processing).

Persistence & Privilege

The skill does not request permanent presence (always:false) nor modify system settings. It is user-invocable and can run autonomously per platform default, which is expected for skills; no elevated or persistent privileges are requested.

Assessment

This skill appears to do only local text processing and does not request credentials or make network calls — that matches its description. However, the bundled script has a bug: the embedded Python blocks use a single-quoted here-doc so shell variables like $file are not expanded, meaning the tool will likely fail to open the file you pass. Before installing or running: (1) inspect or run the script locally and fix the here-docs (remove the single quotes so variables expand, or pass filenames via command-line args into Python); (2) run it on non-sensitive sample files first to confirm behavior; and (3) because the script reads any file you point it at, avoid passing secrets or system configuration files to it. If you want a turnkey fix, ask the author to remove the single quotes on the here-doc delimiters (or otherwise inject the filename safely into the Python code).

Summarize, analyze, and extract insights from text documents. Supports extractive summarization, keyword extraction, readability stats, outline detection, and document comparison — all without external APIs.

Usage

bytesagain-doc-summarizer summary <file>
bytesagain-doc-summarizer bullets <file>
bytesagain-doc-summarizer keywords <file>
bytesagain-doc-summarizer stats <file>
bytesagain-doc-summarizer outline <file>
bytesagain-doc-summarizer compare <file1> <file2>

Commands

• summary — Extract 3-5 key sentences as an extractive summary
• bullets — Generate ranked bullet points from most important sentences
• keywords — Extract and rank top 20 keywords with frequency chart
• stats — Word count, sentence count, reading time, and text metrics
• outline — Detect document structure from Markdown headers or numbered sections
• compare — Compare vocabulary overlap and unique terms between two documents

Examples

bytesagain-doc-summarizer summary report.txt
bytesagain-doc-summarizer bullets meeting-notes.md
bytesagain-doc-summarizer keywords article.txt
bytesagain-doc-summarizer stats essay.md
bytesagain-doc-summarizer outline documentation.md
bytesagain-doc-summarizer compare v1.txt v2.txt

Requirements

• bash
• python3

When to Use

Use when you need to quickly digest long documents, extract key points from reports, analyze text metrics, or compare two document versions for content differences.