qwen38-skill-style is agent-read markdown (skill) from xenodeve/xeno-skills: How to write a skill that Qwen3.8-27B will actually follow. For the author, not the model. Nine rules with the run that produced each: enumerate the unnamed deliverables, a command and a pass condition per rule, a fixed done-report, scripts as files, no sentence that harms when followed literally, measured anchors, a stated boundary, one with/without pair before merge, and one shared report shape across the family..
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.
mdr add xenodeve/xeno-skills/qwen38-skill-style@git:20260906.eb6285emdr add xenodeve/xeno-skills/qwen38-skill-style@sha256:406b4c64de49eeb1Pin 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.
[](https://markdownregistry.com/a/art_22r5aij43h66zeba)
0 badge views in 30 days
xenodeve/xeno-skills · 2 stars · license MIT · pushed 2026-09-06 · branch main
GET https://markdownregistry.com/api/v1/artifacts/art_22r5aij43h66zeba GET https://markdownregistry.com/api/v1/resolve?ref=xenodeve/xeno-skills/qwen38-skill-style GET https://markdownregistry.com/api/v1/blob/406b4c64de49eeb187497fc6b7774db19bbe2b17d794e8143ac595f5c0347446