lh-ml-modeling SKILL.md skillA
lh-ml-modeling from jrodrigopuca/local-agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jrodrigopuca/local-agents/lh-ml-modeling@v1.1Pins v1.1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jrodrigopuca/local-agents
- Path
data-ml/skills/lh-ml-modeling/SKILL.md- Versions recorded
- 1
- Latest version
- v1.1, committed Oct 14, 2026
- Size
- 4,637 bytes
- Repository stars
- 2
- License
- Apache-2.0
Framing and building ML solutions honestly: problem framing, baselines, evaluation, and deployment. Trigger: load when framing an ML problem, choosing/training a model, designing evaluation, or deploying a model to production.
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
## Critical Patterns ### 1. Frame the problem before touching a model Translate the business need into an ML problem precisely: what's predicted (the target), from what (features available AT PREDICTION TIME — not features that only exist after the fact, the classic leakage trap), what a right/wrong answer costs, and what "good enough to ship" means as a number — written down BEFORE training, because it is also the stop rule: past that number, another week of tuning is spend without a decision behind it. Labels are data too: who produced them, how often two labelers agree, and what a label costs decide the ceiling of everything trained on them. A fuzzy framing produces a model that scores well and helps nobody. Sometimes the honest output of framing is "this doesn't need ML" — a rule or a query wins; say so. ### 2. Baseline first — it's the yardstick, not the warm-up Judgment #3 as a step: most-frequent-class, a simple rule, a linear model, before anything else. It sets the bar every fancier model must beat to justify its cost, and it is frequently good enough to ship while the "real" model is still training. ### 3. Split honestly, or your metrics are fiction …
Read the whole file at its exact version.
How to install
mdr add jrodrigopuca/local-agents/lh-ml-modeling@sha256:9d881ceeceed6f60The line at the top of this page pins the label v1.1, 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.
[](https://markdownregistry.com/a/art_a2nwbiea4otndrwa)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 14, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4637 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
jrodrigopuca/local-agents · 2 stars · license Apache-2.0 · pushed 2026-10-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_a2nwbiea4otndrwa GET https://markdownregistry.com/api/v1/resolve?ref=jrodrigopuca/local-agents/lh-ml-modeling GET https://markdownregistry.com/api/v1/blob/9d881ceeceed6f60aec179665ea5fe3e05e23a3ba8204f1466a565483ba1ec8c
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.