method-ml-track SKILL.md skillA

method-ml-track from sajor2000/methodsmith is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add sajor2000/methodsmith/method-ml-track@git:20261018.ea7134c

Pins git:20261018.ea7134c in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
sajor2000/methodsmith
Path
plugins/methodsmith/skills/method-ml-track/SKILL.md
Versions recorded
3
Latest version
git:20261018.ea7134c, committed Oct 18, 2026
First version recorded
Oct 16, 2026
Size
9,769 bytes
Repository stars
3
License
MIT

Adds reproducible ML experiment tracking (data hashes, splits, metrics, SAP links) with MLflow, W&B, DVC, or an offline log. Use when building or reviewing ML experiments.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# ML Experiment Tracking Setup

## Skill Value

- **Problem it solves:** ML analyses lose reproducibility when splits, seeds, metrics, and artifacts are not tracked consistently.
- **Use when:** The user builds or reviews ML experiments, prediction models, validation runs, or tracking setup.
- **Output:** Experiment tracking plan or scaffold with run metadata, metrics, artifacts, and reproducibility checks.
- **Ask only if:** Only when tracking backend, task type, or required metrics cannot be inferred.
- **Do not do:** Do not make a tracking service mandatory when local artifacts are sufficient.
- **Interaction:** Check repo/config/chat evidence first. Ask one decision-changing question at a time; use the current harness's blocking question UI when available, otherwise present numbered choices and wait.

Most ML papers in biomedicine are unreproducible because runs are not tracked. By the time the analyst writes the manuscript, "the version that got 0.89 AUC" is on no disk, with no record of hyperparameters or training-data hash. This skill wires tracking from day 1.

## When this skill activates

- New ML project (immediately after `method-cohort` and before model training)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add sajor2000/methodsmith/method-ml-track@sha256:243c55fa7b0ad717

The line at the top of this page pins the label git:20261018.ea7134c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_zumjeg7nf3vdm6bx.svg)](https://markdownregistry.com/a/art_zumjeg7nf3vdm6bx)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Oct 16, 2026 and Oct 18, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20261018.ea7134c latest2026-10-18 ea7134c 9,769 BA view · diff
git:20261017.73cbef72026-10-17 73cbef7 10,147 BA view · diff
git:20261016.73e5a372026-10-16 73e5a37 6,793 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (9769 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

sajor2000/methodsmith · 3 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_zumjeg7nf3vdm6bx
GET https://markdownregistry.com/api/v1/resolve?ref=sajor2000/methodsmith/method-ml-track
GET https://markdownregistry.com/api/v1/blob/243c55fa7b0ad71793e3d05aee38aee9647f27e41d98eebb34d80ecc1756033f

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from sajor2000/methodsmith

AGENTS.md AGENTS.md file
sajor2000/methodsmith · AGENTS.md
git:20261016.114b5d8 · audit A · 3 stars
CLAUDE.md CLAUDE.md file
sajor2000/methodsmith · CLAUDE.md
git:20260318.f47f829 · audit B · 3 stars
coding-tutor SKILL.md skill
sajor2000/methodsmith · plugins/coding-tutor/skills/coding-tutor/SKILL.md · Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates…
git:20261010.185da1f · audit A · 3 stars
AGENTS.md@plugins/methodsmith AGENTS.md file
sajor2000/methodsmith · plugins/methodsmith/AGENTS.md
git:20261016.114b5d8 · audit A · 3 stars
method-adversarial-review SKILL.md skill
sajor2000/methodsmith · plugins/methodsmith/skills/method-adversarial-review/SKILL.md · Challenges a high-stakes analysis diff or plan with an adversarial pass and, when available, a cross-model…
git:20261016.73e5a37 · audit A · 3 stars
method-anti-slop SKILL.md skill
sajor2000/methodsmith · plugins/methodsmith/skills/method-anti-slop/SKILL.md · Detects and removes generic AI-writing tells from finished scientific prose, keeping passive Methods voice. Use when…
git:20261016.73e5a37 · audit A · 3 stars
method-brainstorm SKILL.md skill
sajor2000/methodsmith · plugins/methodsmith/skills/method-brainstorm/SKILL.md · Explores a research or analysis idea, compares study designs, and scopes requirements before planning. Use when the…
git:20261016.73e5a37 · audit A · 3 stars
method-checklist SKILL.md skill
sajor2000/methodsmith · plugins/methodsmith/skills/method-checklist/SKILL.md · Selects EQUATOR reporting guidelines (CONSORT, STROBE, RECORD, PRISMA, TRIPOD+AI, TARGET, STARD, CLAIM) for a study…
git:20261016.73e5a37 · audit A · 3 stars
method-citations SKILL.md skill
sajor2000/methodsmith · plugins/methodsmith/skills/method-citations/SKILL.md · Builds evidence-traceable citations from PubMed and Paperclip into a DOCX with editable Zotero fields. Use when adding…
git:20261016.114b5d8 · audit A · 3 stars
method-clean-branches SKILL.md skill
sajor2000/methodsmith · plugins/methodsmith/skills/method-clean-branches/SKILL.md · Deletes local git branches whose upstream is gone, and their worktrees, after confirmation. Use when the user asks to…
git:20261016.73e5a37 · audit A · 3 stars
method-clif-meta-analysis SKILL.md skill
sajor2000/methodsmith · plugins/methodsmith/skills/method-clif-meta-analysis/SKILL.md · Plans formal R/Python meta-analysis. Use when pooling CLIF site effects or conducting a literature systematic review.
git:20261017.9e40c82 · audit A · 3 stars
method-clif-template SKILL.md skill
sajor2000/methodsmith · plugins/methodsmith/skills/method-clif-template/SKILL.md · Initializes or audits a CLIF analysis repo against the official CLIF Project Template, with PHI and output safeguards…
git:20261016.73e5a37 · audit A · 3 stars

Every file in sajor2000/methodsmith

Browse by kind, by grade A, or by owner.