ML adoption playbook: end-to-end methodology for adding ML to an existing codebase
Five-phase playbook (framing, data readiness, decoupling, baseline model, MLOps handoff) for adding ML capability to a non-ML codebase
- What
- Five-phase playbook (framing, data readiness, decoupling, baseline model, MLOps handoff) for adding ML capability to a non-ML codebase
- Cost
- Free
- Needs
- nothing to install — the skill is a methodology your agent follows when adding ML to a codebase; no accounts, keys, or runtime dependencies
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @affaan-m's end-to-end methodology for adding a machine-learning capability to a codebase that has none, written for AI agents and software engineers. Runs five phases: problem framing (with a heuristic-first check and a "mistake budget" before any model code), data readiness (source audit, data contracts, train/test leakage prevention), architectural decoupling (model behind an API boundary with feature-flag rollouts and hardcoded fallbacks), baseline-first implementation (reproducible training script, tests for data transforms, evaluation against the baseline), and the MLOps handoff (experiment tracking, model registry, CI-gated evals). Also gives agents a concrete iterative workflow: ask clarifying questions, draft the data contract, write the decoupling interface before the training loop. Honest caveats: it's a methodology, not code — no scripts ship with it; references companion ECC skills (fastapi-patterns, pytorch-patterns, mle-workflow) not included here. MIT-licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: nothing to install — the skill is a methodology your agent follows when adding ML to a codebase; no accounts, keys, or runtime dependencies Install "ML adoption playbook: end-to-end methodology for adding ML to an existing codebase" for me. It gives my agent @affaan-m's five-phase ML adoption methodology: problem framing (heuristic check, metric definition, mistake budget), data readiness (source audit, data contracts, leakage prevention), architectural decoupling (model behind an API boundary, feature flags, hardcoded fallbacks), baseline-first implementation (reproducible training script, tests, evaluation vs baseline), and the MLOps handoff (experiment tracking, registry, CI evals) — plus an iterative agent workflow for driving it. MIT-licensed. Repository: https://github.com/affaan-m/ecc/blob/main/skills/ml-adoption-playbook/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "ml-adoption-playbook". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. nothing — it is a methodology; invoke it when adding ML to an existing codebase). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.