Tessl • The package manager for agent skills

SkillPublic

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.

Quality

68%

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 ./bundled/skills/ml-pipeline-workflow/SKILL.md

Quality

Content

38%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 skill presents a broad, well-organized outline but is mostly conceptual taxonomy and placeholder code rather than executable guidance, and its referenced bundle files do not exist. It needs real code examples and the missing references/assets to become actionable.

Suggestions

Replace the comment-only code blocks with complete, copy-pasteable examples (e.g., a real Airflow/Dagster DAG or a working training-job snippet) so the guidance is executable rather than illustrative.

Create the referenced bundle files (references/*.md, assets/pipeline-dag.yaml.template, etc.) or remove the dangling references, so progressive-disclosure navigation resolves to real content.

Add explicit validation/verification checkpoints to the deployment workflow (e.g., validate model artifacts, run validation suite, only proceed on pass, with rollback on failure) to support the batch/destructive operations.

Dimension	Reasoning	Score
Conciseness	The body is largely descriptive taxonomy and best-practice lists Claude already knows (e.g., 'Use model registries (MLflow)', 'Implement gradual rollouts'), with stub code blocks that only contain comments; much of the prose restates the description rather than adding executable value.	2 / 5
Actionability	Most code blocks are placeholders ('# See assets/...', '# Stream processing for real-time features') with no executable code or concrete commands, and the 'Usage Patterns' examples define a list of stage-name strings rather than runnable pipeline code.	2 / 5
Workflow Clarity	The Production Workflow lists a clear four-phase sequence, but the batch/deployment operations lack validation checkpoints and rollback gates; because destructive/batch deployment operations have no verify-then-proceed feedback loop, it is capped at 3.	3 / 5
Progressive Disclosure	The body repeatedly signals references to references/, assets/ and specific files (e.g., 'data-preparation.md', 'pipeline-dag.yaml.template'), but those directories and files do not exist, so the navigation points to nothing and large generic lists remain inlined in SKILL.md.	2 / 5
	Total	9 / 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 strong, well-structured description that clearly states both what the skill does and when to use it, with concrete lifecycle actions and natural trigger terms. Minor room to sharpen verb specificity and add synonyms to reach full marks.

Dimension	Reasoning	Score
Specificity	Names the domain (MLOps pipelines) and multiple concrete actions across the lifecycle ('data preparation through model training, validation, and production deployment'), though the verbs are high-level rather than sharply specific like the 5-anchor examples.	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...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('creating ML pipelines', 'implementing MLOps practices', 'automating model training and deployment workflows'); missing some common synonyms and explicit extensions, keeping it just below a 5.	4 / 5
Distinctiveness Conflict Risk	The MLOps/pipeline niche is fairly distinct and specific trigger phrases reduce overlap, but it could still overlap with related ML skills (e.g., training or deployment skills) without sharper boundary.	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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/ml-pipeline-workflow/SKILL.md
Revision: 5ce2258

Reviewed: 27 days ago

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.

ml-pipeline-workflow

Table of Contents

Is this your skill?