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.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

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

Quality

Content

70%

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

The body is a well-sequenced, well-organized methodology with clear validation checkpoints and appropriate cross-skill references, scoring high on workflow clarity and progressive disclosure. It is held back by minor commentary fluff and directional rather than fully concrete actionable detail.

Suggestions

Remove explanatory filler lines (e.g., "ML is useless without clean, accessible data.") so every line earns its place.

Make the actionable items more concrete: provide a minimal data-contract schema skeleton and an evaluation-script template rather than just requiring them.

Tighten directional phrasing like "Guide the user toward..." into specific steps the agent should perform.

Dimension	Reasoning	Score
Conciseness	Mostly efficient bullet structure that assumes Claude knows the referenced libraries, but it includes unnecessary commentary lines ("ML is useless without clean, accessible data.", "Do not tightly couple model inference to core business logic.") that could be tightened.	2 / 3
Actionability	Gives concrete specific guidance with named examples (scikit-learn Logistic Regression, PyTorch linear layer, fastapi-patterns, chronological splitting), but it stays directional — "Guide the user toward...", "Suggest placing..." — and provides no executable template, data-contract format, or evaluation script, fitting the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	Five phases are clearly sequenced (Phase 1–5) with an explicit 'When to Activate' section, plus a numbered Iterative Agent Workflow and validation checkpoints (eval against baseline, tests for transforms, CI eval step), matching the clear-sequence-with-explicit-validation anchor.	3 / 3
Progressive Disclosure	A single well-organized file with clear sections and cross-skill pointers (fastapi-patterns, pytorch-patterns, mle-workflow) for deeper detail; no bundle files exist and none are needed at this scope, so well-organized sections score 3 per the guidelines.	3 / 3
	Total	10 / 12 Passed

Description

60%

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

The description is specific and third-person, listing four concrete coverage areas, but it omits an explicit "Use when..." trigger clause and natural trigger-term variations. This caps completeness and trigger_term_quality at 2.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should activate this skill (e.g., 'Use when a user asks to add ML, an algorithm, or a model to an existing non-ML codebase').

Include natural trigger-term variations users would actually say — 'add ML', 'add an algorithm', 'integrate a model' — alongside the current phrasing.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and lists multiple specific coverage areas: "problem framing, data readiness, architectural decoupling, and baseline model integration" — matching the multiple-concrete-actions anchor, not just a single domain mention.	3 / 3
Completeness	Clearly answers WHAT the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Includes a natural phrase ("add machine learning algorithms to existing non-ML codebases") but omits common variations users would say ("add ML", "integrate a model", "AI"); missing common variations per the anchor.	2 / 3
Distinctiveness Conflict Risk	The "non-ML codebases" framing is a distinct niche, but the description lacks explicit distinct triggers and could still overlap with general ML/MLOps skills, matching the "somewhat specific but could overlap" anchor rather than the clear-niche anchor.	2 / 3
	Total	9 / 12 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
Commit: 754b8dd

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.