luongnv89/asm · skills/skill-auto-improver/SKILL.md

skill-auto-improver skillA

skill-auto-improver is agent-read markdown (skill) from luongnv89/asm: Improve an external, legacy, or drifted SKILL.md to the skill-creator standard — hard validation gates plus an advisory predictability audit. Don't use for authoring from scratch (skill-creator output is already standard), bulk eval, or prose edits..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add luongnv89/asm/skill-auto-improver@v2.1.0
Exact content
mdr add luongnv89/asm/skill-auto-improver@sha256:49de3172c094cf6e

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_5qed77dkquvsw6zl.svg)](https://markdownregistry.com/a/art_5qed77dkquvsw6zl)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v2.1.0 latest2026-08-27 2202b2c 20,657 BA view · diff
v2.0.02026-08-26 3b296d5 27,791 BA view · diff
v1.4.02026-08-26 7fca6fe 26,210 BA view · diff
v1.3.02026-07-01 07f3e08 20,574 BA view · diff
v1.1.02026-06-30 4f19a69 20,574 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.

Source

GitHub

luongnv89/asm · 913 stars · license MIT · pushed 2026-09-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5qed77dkquvsw6zl
GET https://markdownregistry.com/api/v1/resolve?ref=luongnv89/asm/skill-auto-improver
GET https://markdownregistry.com/api/v1/blob/49de3172c094cf6ecb4abd8c709accdff77ed39f98f13ed7c3d9d796ef158b72