Install
$ agentstack add skill-jazz1x-galmuri-explain ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
galmuri:explain — Inline reader-side summary
Prerequisites
scripts/preflight.shpasses (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
meautomatically (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
claimbecomes the top-line summary. - Each unit's
essenceis listed as a bullet.
Step 4: Output
- Emit markdown to stdout. No file-generation step (by design).
- On session end,
.galmuri/tmp/source-{slug}.txtis cleaned up automatically (hook).
Output Schema
Markdown body only. No JSON output.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jazz1x
- Source: jazz1x/galmuri
- License: MIT
- Homepage: https://skills.sh/jazz1x/galmuri
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.