Name: machine-learning-ops-ml-pipeline
Rating: 28.000000000000004 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

machine-learning-ops-ml-pipeline

Design and implement a complete ML pipeline for: $ARGUMENTS

Quality

20%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/machine-learning-ops-ml-pipeline/SKILL.md

The canonical home for this skill is machine-learning-ops-ml-pipeline in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

16%Scale 1-5

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

This skill is an aspirational architecture document rather than an actionable skill. It extensively describes what an ideal MLOps pipeline should look like but provides no executable code, no concrete commands, and no specific implementation guidance. The pseudo-agent orchestration format (subagent_type, prompt templates) doesn't correspond to any real system Claude can execute, making the entire skill essentially a wishlist of deliverables rather than instructions Claude can follow.

Suggestions

Replace the abstract '<Task>' blocks with concrete, executable code examples for at least the critical components (e.g., actual MLflow tracking setup code, a real Feast feature definition, a working Dockerfile).

Remove the 'Thinking' section and trim explanatory bullet points that describe well-known ML concepts—focus only on project-specific decisions and non-obvious patterns.

Add explicit validation checkpoints with concrete commands (e.g., 'Run `great_expectations checkpoint run` and verify all suites pass before proceeding to Phase 2').

Create the referenced 'resources/implementation-playbook.md' and move detailed phase specifications there, keeping SKILL.md as a concise overview with clear navigation links.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive explanations of concepts Claude already knows (what MLOps is, what feature stores do, what Kubernetes is). The skill is over 250 lines of mostly high-level descriptions and bullet-point lists that explain standard ML engineering concepts rather than providing novel, actionable instructions. The 'Thinking' section alone is unnecessary padding.	1 / 5
Actionability	Despite its length, the skill contains zero executable code, no concrete commands, and no specific implementation examples. It consists entirely of abstract descriptions and deliverable lists. The '<Task>' blocks are pseudo-orchestration templates with placeholder references like '{phase1.data-engineer.output}' that aren't tied to any real system or executable framework.	1 / 5
Workflow Clarity	The phased structure (Phase 1-4) provides a clear sequence with logical dependencies between phases. However, there are no validation checkpoints, no feedback loops for error recovery, and no concrete verification steps. The 'Success Criteria' section lists metrics but doesn't explain how to verify them during the workflow.	3 / 5
Progressive Disclosure	The skill references 'resources/implementation-playbook.md' but no bundle files exist to support it. The massive amount of content is inlined in a single monolithic file with no actual separation of concerns. Configuration options, success criteria, and detailed phase specifications should be in separate referenced files.	2 / 5
	Total	7 / 20 Passed

Description

25%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.

This description is too vague and template-like to serve as an effective skill selector. It lacks concrete actions, natural trigger terms, and any 'when to use' guidance. The placeholder '$ARGUMENTS' suggests this is an unfinished template rather than a polished skill description.

Suggestions

Add a 'Use when...' clause with specific trigger phrases like 'when the user asks to build a machine learning model, train a classifier, create a prediction pipeline, or set up ML workflows'.

Replace the generic 'design and implement' with concrete actions such as 'preprocesses data, engineers features, trains models, evaluates performance, and generates predictions'.

Include natural synonyms and related terms users would say, such as 'machine learning', 'model training', 'data science', 'sklearn', 'deep learning', 'classification', 'regression'.

Dimension	Reasoning	Score
Specificity	Names the domain ('ML pipeline') but the actions are minimal and generic. 'Design and implement' are broad verbs, and '$ARGUMENTS' is a placeholder that provides no concrete actions or capabilities.	2 / 5
Completeness	There is a vague 'what' (design and implement an ML pipeline) but no 'when' clause at all. There is no guidance on when Claude should select this skill, which per the rubric caps completeness at 3, and the weak 'what' brings it to 2.	2 / 5
Trigger Term Quality	'ML pipeline' is a relevant keyword, but it misses many natural terms users would say such as 'machine learning', 'model training', 'data preprocessing', 'feature engineering', 'model evaluation', etc. The placeholder '$ARGUMENTS' contributes no trigger terms.	2 / 5
Distinctiveness Conflict Risk	Very broad — 'ML pipeline' could overlap with data science skills, model training skills, data preprocessing skills, or any machine learning-related skill. The description lacks specificity to carve out a clear niche.	2 / 5
	Total	8 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/machine-learning-ops-ml-pipeline/SKILL.md
Commit: 57c135b

Reviewed: 4 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.