semantic-compress
100 / 100 · Low risk
Fine to try.
Make an LLM-directed document smaller while preserving what it does. Two modes: a local span-level core->pointer pass, and an A/B-validated distill loop that produces the smallest document that behaves the same as the original. Point at core knowledge the model already holds (a concept name activates it); keep project-specific detail explicit and verbatim. TRIGGER when asked to compress, tighten, shorten, or strip a prompt / instruction / system message meant for an LLM; to distill a skill; to …
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'semantic-compress' ] || [ -L ~/.agents/skills/'semantic-compress' ]; then echo 'A skill folder named semantic-compress already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/bjcoombs/ai-native-toolkit' "$d" && git -C "$d" checkout --quiet 'f31582e1c9fe75950a9e522649565b93e3072fe0' -- 'skills/semantic-compress' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/semantic-compress' ~/.agents/skills/'semantic-compress' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'semantic-compress' ~/.claude/skills/'semantic-compress' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/bjcoombs/ai-native-toolkit/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | f31582e | 100 |
| 2026-11-07 | 82a6017 | 100 |