ml-adoption-playbook

End-to-end methodology for AI agents and software engineers to add machine learning algorithms to existing non-ML codebases. Covers problem framing, data readiness, architectural decoupling, and baseline model integration. Use when adding a machine learning capability to a codebase that has none, from problem framing through a baseline model.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ml-adoption-playbook/SKILL.md

Quality

Content

48%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A clearly structured five-phase playbook with good conciseness, but it reads as an advisory framework rather than an executable skill: no code, commands, or templates, and validation steps are implied rather than explicit. Referenced companion skills are named but not bundled or clearly navigated.

Suggestions

Add concrete, copy-paste-ready artifacts: a baseline training script skeleton, a sample data-contract schema, and an API/service interface stub, so the guidance is executable rather than descriptive.

Insert explicit validation checkpoints and a feedback loop — e.g., after training, require an evaluation script that compares against the heuristic/baseline and only proceed if it clears the mistake budget.

Clarify the references to mle-workflow / fastapi-patterns / pytorch-patterns as one-level-deep pointers with paths or a short 'Where to go next' section, or bundle the relevant details locally so navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	Largely lean with short bullet points and no padding about what ML/libraries are, but a few orienting sentences ('ML is useless without clean, accessible data') slightly over-explain.	4 / 5
Actionability	Provides high-level direction and named tools/patterns (fastapi-patterns, scikit-learn Logistic Regression) but no executable code, commands, or concrete templates — it instructs more than it enables.	2 / 5
Workflow Clarity	Five phases plus an iterative agent workflow are clearly sequenced, but validation/feedback checkpoints are implicit rather than explicit and there is no validate-fix-retry loop for the model training/build steps.	3 / 5
Progressive Disclosure	Well-organized sections, but referenced skills (mle-workflow, fastapi-patterns, pytorch-patterns) are external names with no bundle files and no clearly-signaled one-level-deep navigation; everything is inlined in a single 57-line file.	3 / 5
	Total	12 / 20 Passed

Description

85%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description that clearly states both what the skill does and when to use it, with concrete capability areas and natural trigger phrases. Minor room to add more discrete action verbs and a couple of trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas ('problem framing, data readiness, architectural decoupling, and baseline model integration') rather than vague language, though they are domains/phases more than discrete actions.	4 / 5
Completeness	Explicitly answers what it does (end-to-end methodology adding ML algorithms to existing non-ML codebases) and when to use it ('Use when adding a machine learning capability to a codebase that has none, from problem framing through a baseline model').	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('add ML', 'adding a machine learning capability') plus model-type synonyms (recommendation, classification, forecasting), but lacks code/file-extension-style trigger variants.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (adding ML to existing non-ML codebases, baseline model) unlikely to trigger for unrelated skills; trigger is tightly scoped.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/ml-adoption-playbook/SKILL.md
Commit: 06c5e11

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.