model-deployment

Deploy ML models with FastAPI, Docker, Kubernetes. Use for serving predictions, containerization, monitoring, drift detection, or encountering latency issues, health check failures, version conflicts.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%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 highly actionable, well-structured deployment skill with concrete code and clear reference navigation. The main weaknesses are duplicated code blocks across sections and a main workflow that could make its validation/rollback feedback loop more explicit.

Suggestions

De-duplicate the FastAPI server and Dockerfile: keep one canonical version and have the Quick Start reference it instead of re-pasting, to reclaim tokens.

Add an explicit validate-then-deploy feedback loop to the 6-step Quick Start (e.g., "if rollout status fails or health checks fail, run kubectl rollout undo and re-investigate") so the production workflow's checkpoints are unmistakable.

Consider moving the eight detailed Known Issues entries into a reference file, keeping only a short summary plus pointer in SKILL.md to tighten the overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete but repeats material: the FastAPI server and Dockerfile each appear twice (standalone sections and again in Quick Start) and the /health endpoint is re-shown in Known Issues, so noticeable tightening is possible without losing value.	3 / 5
Actionability	It provides copy-paste-ready FastAPI code, a Dockerfile, kubectl rollout commands, deployment.yaml probe/resource snippets, and Pydantic validation covering the common deployment cases.	5 / 5
Workflow Clarity	The "Deploy Model in 6 Steps" sequence is clear with checkpoints (build and test locally, kubectl rollout status) and a separate rollback procedure, but the main flow lacks an explicit validate->fix->retry loop for this production/destructive context, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Four reference files are clearly signaled one level deep in a dedicated "When to Load References" section with concise summaries, and the body is well sectioned; the inlined eight-item Known Issues block is fairly long and could be partly offloaded to a reference.	4 / 5
	Total	16 / 20 Passed

Description

87%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 clearly answers what the skill does and when to use it, with concrete tools and natural trigger phrases. Minor gains are possible from a broader set of distinct action verbs and a few more synonyms.

Dimension	Reasoning	Score
Specificity	"Deploy ML models with FastAPI, Docker, Kubernetes" names the domain plus several concrete capabilities (serving predictions, containerization, monitoring, drift detection), but the verb coverage is somewhat tool-list driven rather than a comprehensive set of distinct actions.	4 / 5
Completeness	It explicitly states both what ("Deploy ML models with FastAPI, Docker, Kubernetes") and when ("Use for serving predictions... or encountering latency issues, health check failures, version conflicts") with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Natural terms like "serving predictions", "containerization", "drift detection", "latency issues", "health check failures", and "version conflicts" are phrases users would actually say; a few common synonyms are absent but coverage is strong.	4 / 5
Distinctiveness Conflict Risk	"Deploy ML models with FastAPI, Docker, Kubernetes" carves a clear ML-serving niche with distinct triggers, and the use-for list is specific enough to minimize overlap with general web or DevOps skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: secondsky/claude-skills
Path: plugins/model-deployment/skills/model-deployment/SKILL.md
Commit: 84802a4

Reviewed: 3 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.