martinforreal/compress-text-skill (compress-text)

Reads text in any format and produces a leaner, better-structured version via MECE semantic grouping and the Pyramid Principle. Generates multiple candidate groupings, scores each on size reduction and meaning-fidelity, and selects the best while preserving the original meaning, instructions, key points, references, and examples. Cuts redundancy with semantic and statistical analysis, and strips self-corrections plus the passages they supersede when the author pivoted (transcripts, dictation, drafts, chat). Preserves template tags (Handlebars/Jinja/Mustache/shell/ERB and explicit keep/drop markers) verbatim and can emit the result into a user-supplied template with named slots. Offers a dense LLM-oriented mode and a readable human-oriented mode. Use it to shrink, compress, trim, deduplicate, restructure, optimize, or clean up any text or transcript, reduce its token/context footprint, compress a template while keeping its tags, merge related docs and dedupe across them, or measure compression effectiveness.

Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.

Source:

github.com/martinforreal/compress-text-skill

Provenance:

Found by crawling (provenance, not a security rating)

We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.

5 critical findings reported by cisco-skill-scanner. The composite score alone does not reflect this — read the per-scanner reports below.

This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.