Name: mle-workflow
Rating: 64 (1 reviews)
Author: affaan-m

mle-workflow

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

Quality

76%

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 ./.agents/skills/mle-workflow/SKILL.md

The canonical home for this skill is mle-workflow in affaan-m/ECC

Quality

Content

60%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 content-rich, well-structured MLE workflow with executable examples and strong validation/rollback emphasis, but it is long and monolithic with no progressive disclosure: large reference tables are inlined and nothing is split into bundle files.

Suggestions

Move the 'Reuse the SWE Surface' and 'Ten MLE Task Simulations' tables into reference files under references/ and link to them from a concise overview, reducing SKILL.md to an index.

Tighten prose sections like 'Metric and Mistake Economics' and 'Data and Feature Hypotheses' into terse bullets so every token earns its place.

Add an explicit validate->fix->retry loop to the Core Workflow steps (e.g., after building the pipeline and after packaging for serving) to convert the validation emphasis into concrete feedback-loop steps.

Dimension	Reasoning	Score
Conciseness	The body is mostly substantive MLE-specific guidance Claude does not trivially know, but the ~340-line length and two large inlined tables ('Reuse the SWE Surface', 'Ten MLE Task Simulations') include padding that could be tightened or split out.	3 / 5
Actionability	Provides two executable Python blocks (frozen TrainingConfig with artifact hashing, fail-closed promotion gates) plus concrete fill-in templates, but much of the guidance remains prose checklists rather than copy-paste commands.	4 / 5
Workflow Clarity	The six-step Core Workflow is well sequenced with explicit validation checkpoints (promotion gates that fail closed, rollback triggers, a review checklist), though some steps are prose lists rather than explicit validate->fix->retry loops.	4 / 5
Progressive Disclosure	The skill is a single monolithic SKILL.md with no references/, scripts/, or assets/ bundle and no external file links, and it inlines large reference tables (SWE surface map, ten-task simulations) that clearly belong in separate files.	2 / 5
	Total	13 / 20 Passed

Description

92%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 strong, third-person description that pairs a concrete action list with an explicit 'Use when...' trigger and a distinctive production-MLE framing. Minor gap is the absence of synonyms and file-extension trigger terms.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback') with comprehensive coverage of the MLE lifecycle, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what ('Production machine-learning engineering workflow for...') and when ('Use when building, reviewing, or hardening ML systems beyond one-off notebooks') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('building, reviewing, or hardening ML systems', 'one-off notebooks') but lacks synonyms and file/extension variants, sitting above the score-3 anchor but below comprehensive score-5 coverage.	4 / 5
Distinctiveness Conflict Risk	The 'beyond one-off notebooks' qualifier carves a clear production-MLE niche with distinct triggers and minimal overlap with general Python or SWE skills.	5 / 5
	Total	19 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: .agents/skills/mle-workflow/SKILL.md
Commit: d8409a4

Reviewed: 1 day 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.