Explain

Inline self-comprehension adapter. Calls the distill engine to extract the essence of long text and renders it as inline markdown. audience=me is auto-fixed. Output only — no file generation. Triggers: "설명해", "이해하게", "explain", "정리해서 보여줘", "readme 읽고", "shrink", "줄여줘", "압축"From its SKILL.md

Install

npx -y skills add jazz1x/galmuri --skill explain

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 1 command, including `touch ".galmuri/tmp/.warned-shrink"`.

SKILL.md

2.7 KB, 427 tokens by cl100k_base, as published. Nobody here has run it

galmuri:explain — Inline reader-side summary

Prerequisites

scripts/preflight.sh passes (jq, bats, bash).
skills/distill/ engine is installed.

Step 1: Alias detection + Input Capture

When triggered via shrink / 줄여줘 / 압축:

if [ ! -f ".galmuri/tmp/.warned-shrink" ]; then
  echo "[deprecated] the 'shrink' trigger is routed to a context-based adapter. Scheduled for removal in a future release." >&2
  touch ".galmuri/tmp/.warned-shrink"
fi
# source_tokens < 80 → explain runs; otherwise → delegate to another adapter

Pipe user input (a file path or stdin) into .galmuri/tmp/source-{slug}.txt. If no path is provided: "Tell me a file path or some text to explain. e.g. README.md — what should I explain?"
audience is locked to me automatically (no separate prompt).

Step 2: Engine Invoke

Call the galmuri:distill skill via the Skill tool with these arguments:

--mode reduce --ratio 0.2 --audience me --input {tmp file path from Step 1}

The engine returns an EngineOutput JSON. Pass it directly to Step 3.

Do not attempt to inline the distill logic here — always delegate to the skill.

Step 3: Render

EngineOutput.units → inline markdown:
- First unit's claim becomes the top-line summary.
- Each unit's essence is listed as a bullet.

Step 4: Output

Emit markdown to stdout. No file-generation step (by design).
On session end, .galmuri/tmp/source-{slug}.txt is cleaned up automatically (hook).

Output Schema

Markdown body only. No JSON output.

What ships with it: 2 files

5.5 KB alongside SKILL.md

SKILL.jp.md2.9 KB
SKILL.ko.md2.6 KB