Name: machine-learning-ops-ml-pipeline
Rating: 47.2 (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

50%

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-claude/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

50%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 lays out a coherent four-phase multi-agent MLOps orchestration with explicit handoffs and specific tooling, but it is verbose, contains no executable code, omits validation checkpoints for risky batch/deploy operations, and references a non-existent playbook file. It is functional guidance but sits at the midpoint on every dimension.

Suggestions

Add explicit validation checkpoints and feedback loops after each phase (e.g., verify data-quality gates pass before training, validate model metrics before promotion, smoke-test serving before canary rollout).

Provide at least minimal executable examples or concrete commands for the highest-value steps (e.g., a sample MLflow/Optuna training snippet, a KServe manifest, a validate-then-deploy CI gate) instead of prose-only deliverable lists.

Trim the 'Thinking', 'Success Criteria', and 'Final Deliverables' sections to essentials, and either create the referenced 'resources/implementation-playbook.md' or remove the dangling reference so progressive disclosure resolves to real files.

Dimension	Reasoning	Score
Conciseness	The body is mostly structured and actionable, but the 'Thinking' rationale, 'Success Criteria', and 'Final Deliverables' sections restate information and pad length beyond what Claude needs, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the lean 4-5 anchors.	3 / 5
Actionability	Each phase gives detailed deliverable lists and names specific tools (MLflow, Feast, KServe, Terraform), which is concrete guidance, but there is no executable code or commands anywhere — only prose specifications for delegated subagents, matching 'some concrete guidance but incomplete; missing key details'.	3 / 5
Workflow Clarity	Four phases are clearly sequenced with explicit inter-agent handoffs via {phaseX.agent.output}, but there are no validation checkpoints or feedback loops, and the destructive/batch operations (training, deployment) cap workflow_clarity at 3 per the judging guidelines.	3 / 5
Progressive Disclosure	The body has reasonable section/phase structure, but it is monolithic with all configuration, success criteria, and phase detail inlined, and its single external reference ('resources/implementation-playbook.md') points to a file that does not exist in the bundle, fitting 'some structure but could be better organized; references present but not clearly signaled'.	3 / 5
	Total	12 / 20 Passed

Description

50%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.

The description is a templated, third-person statement that conveys a clear 'what' but lacks any explicit 'when to use' trigger guidance and uses only generic action verbs. It is adequate but generic, with limited trigger-term coverage and moderate overlap risk against related ML/MLOps skills.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when the user needs to build or productionize an ML pipeline, set up MLOps, or orchestrate model training and serving').

Expand trigger terms to include natural synonyms users actually say: 'machine learning pipeline', 'MLOps', 'model training/serving pipeline', and specific tooling names where relevant.

Replace the generic 'Design and implement' verbs with more specific concrete actions (e.g., 'orchestrates multi-agent phases for data ingestion, feature engineering, training, deployment, and monitoring').

Dimension	Reasoning	Score
Specificity	The description names the domain ('complete ML pipeline') and two actions ('Design and implement'), but the verbs are generic and the $ARGUMENTS placeholder leaves the actual subject unspecified, matching the 'names domain and 1-2 concrete actions' anchor rather than the comprehensive 4-5 anchors.	3 / 5
Completeness	It clearly states what the skill does ('Design and implement a complete ML pipeline') but provides no 'Use when...' clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 3 with the 'when' only weakly implied.	3 / 5
Trigger Term Quality	'ML pipeline' is a natural term users would say, but the description omits common synonyms and variations a user might actually utter ('machine learning pipeline', 'MLOps', 'model training pipeline'), fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'ML pipeline' is a recognizable niche, but the breadth of 'complete ML pipeline' (data, training, serving, monitoring) creates real overlap risk with separate data-engineering, model-serving, or MLOps skills, fitting 'somewhat specific but could still overlap'.	3 / 5
	Total	12 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/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.