ml-pipeline-workflow

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

0.98x

Quality

63%

Does it follow best practices?

Impact

73%

0.98x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/machine-learning-ops/skills/ml-pipeline-workflow/SKILL.md

The canonical home for this skill is ml-pipeline-workflow in wshobson/agents

Quality

Content

42%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.

The content is well-structured and covers the ML pipeline lifecycle conceptually, but it leans on generic best-practice prose and stub code rather than executable guidance, and its references point to bundle files that are not present.

Suggestions

Replace placeholder code blocks (`# See assets/...`) with minimal but complete executable snippets so Claude can act without chasing missing files.

Add explicit validation checkpoints between workflow phases (e.g., validate data quality before training, validate metrics before deployment) with a fix-and-retry loop for the destructive deployment step.

Either ship the referenced references/*.md and assets/* files or remove the broken cross-references so navigation is not dead-ended.

Dimension	Reasoning	Score
Conciseness	The body is mostly organized as lists, but large sections restate widely-known best-practice truisms ('Modularity: Each stage should be independently testable', tool name-drops) that Claude already knows and could be trimmed.	3 / 5
Actionability	Code blocks are largely stubs and pseudocode — `# See assets/pipeline-dag.yaml.template for full example` and a placeholder stages list — with high-level hints but missing the specific executable steps to actually build a pipeline.	2 / 5
Workflow Clarity	The Production Workflow lists sequenced phases (Data Prep → Training → Validation → Deployment) but has no explicit validation checkpoints or feedback loops; since deployment is a destructive/batch operation the cap-at-3 guidance applies.	3 / 5
Progressive Disclosure	The body is well-sectioned and points one level deep to references/ and assets/ files, but those directories do not actually exist in the bundle, so the clearly-signaled navigation leads to broken links.	3 / 5
	Total	11 / 20 Passed

Description

83%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 description with an explicit 'Use when' clause and concrete lifecycle actions. It clearly separates what the skill does from when to invoke it and occupies a distinct MLOps-pipeline niche.

Dimension	Reasoning	Score
Specificity	Lists several concrete lifecycle actions ('data preparation through model training, validation, and production deployment'), but the named stages are domain-level rather than the granular distinct actions seen in the 5-anchor PDF example.	4 / 5
Completeness	Explicitly answers both 'what' (build end-to-end MLOps pipelines from data preparation through deployment) and 'when' (Use when creating ML pipelines, implementing MLOps practices, or automating training/deployment) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases a user would say are present ('creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows'); good coverage with a few synonyms or alternate phrasings missing.	4 / 5
Distinctiveness Conflict Risk	Clear MLOps-pipeline niche with distinct triggers, though it could overlap with the related hyperparameter-tuning and model-deployment skills it itself references; mostly distinct with minor overlap risk.	4 / 5
	Total	17 / 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
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-wshobson/machine-learning-ops/skills/ml-pipeline-workflow/SKILL.md
Commit: 6453c0b

Reviewed: about 9 hours 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.