by samuelfaj
Distill large CLI outputs into small answers for LLMs and save tokens!
# Add to your Claude Code skills
git clone https://github.com/samuelfaj/distillGuides for using cli tools skills like distill.
Last scanned: 5/14/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-14T06:46:56.203Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}distill is an open-source cli tools skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by samuelfaj. Distill large CLI outputs into small answers for LLMs and save tokens!. It has 653 GitHub stars.
Yes. distill passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/samuelfaj/distill" and add it to your Claude Code skills directory (see the Installation section above).
distill is primarily written in TypeScript. It is open-source under samuelfaj on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other CLI Tools skills you can browse and compare side by side. Open the CLI Tools category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh distill against similar tools.
No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
🔥🔥🔥 Save much more tokens with our client: https://remotecode.io/
Agent command outputs are one of the biggest sources of token waste.
Logs, test results, stack traces… thousands of tokens sent to an LLM just to answer a simple question.
🔥 distill compresses command outputs into only what the LLM actually needs.
Save up to 99% of tokens without losing the signal.
Install:
npm i -g @samuelfaj/distill
Run onboarding:
distill
And that's it!
Distill uses it's own Expert Language Model
https://huggingface.co/samuelfaj/distill-1.7B-MLX
Only: 1.7B - 4bit
Safe recommendation: machine should have 8 GB+ RAM; 16 GB+ is comfortable.
rg -n "terminal|PERMISSION|permission|Permissions|Plan|full access|default" desktop --glob '!**/node_modules/**' | distill "find where terminal and permission UI are implemented in chat screen"
We also teach your LLM to talk and think a more efficient way.
