patrickserrano/lacquer · core/skills/skill-tuning-loop/SKILL.md

skill-tuning-loop skillA

skill-tuning-loop is agent-read markdown (skill) from patrickserrano/lacquer: Empirically test whether a lacquer skill needs an edit by mining real session transcripts for friction, proposing a bounded fix, and validating it against held-out cases before it ships. Use when a skill in core/skills/ or profiles/*/skills/ keeps getting corrected in practice, when triaging a scheduled tuning-pass PR, or when skill-authoring-standard's manual rubric isn't enough to tell whether a proposed edit actually helps. Distinct from skill-authoring-standard (a static prose rubric checked.

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 patrickserrano/lacquer/skill-tuning-loop@git:20260725.3f0d943
Exact content
mdr add patrickserrano/lacquer/skill-tuning-loop@sha256:03a2b47e5369d745

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_akgat6tedg7cww72.svg)](https://markdownregistry.com/a/art_akgat6tedg7cww72)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260725.3f0d943 latest2026-07-25 3f0d943 5,263 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5263 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

patrickserrano/lacquer · 3 stars · license MIT · pushed 2026-09-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_akgat6tedg7cww72
GET https://markdownregistry.com/api/v1/resolve?ref=patrickserrano/lacquer/skill-tuning-loop
GET https://markdownregistry.com/api/v1/blob/03a2b47e5369d745d837c08fa0446bd8f53e0a26e888d9e84c858ef411d8cee6

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.