sagemaker-endpoint-deployer
Sagemaker Endpoint Deployer - Auto-activating skill for ML Deployment. Triggers on: sagemaker endpoint deployer, sagemaker endpoint deployer Part of the ML Deployment skill category.
34
Quality
3%
Does it follow best practices?
Impact
87%
0.98xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/08-ml-deployment/sagemaker-endpoint-deployer/SKILL.mdQuality
Discovery
7%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 severely underdeveloped, essentially just restating the skill name without explaining capabilities or usage triggers. It lacks concrete actions, natural user keywords, and explicit guidance on when Claude should select this skill. The redundant trigger terms and missing 'Use when...' clause make it nearly unusable for skill selection.
Suggestions
Add specific actions the skill performs, e.g., 'Deploy ML models to SageMaker endpoints, configure instance types, manage endpoint scaling, and monitor deployment status.'
Include a 'Use when...' clause with natural trigger terms: 'Use when deploying models to AWS, creating inference endpoints, hosting ML models, or when user mentions SageMaker, model deployment, or real-time inference.'
Add common variations users might say: 'AWS ML hosting', 'model serving', 'inference API', 'deploy to production', '.tar.gz model artifacts'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the tool ('Sagemaker Endpoint Deployer') and category ('ML Deployment') without describing any concrete actions. No specific capabilities like 'deploy models', 'configure endpoints', or 'manage instances' are mentioned. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond the name, and provides no 'when to use' guidance. There is no 'Use when...' clause or equivalent explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | The trigger terms are redundant ('sagemaker endpoint deployer' repeated twice) and overly specific to the skill name itself. Missing natural user terms like 'deploy model', 'inference endpoint', 'hosting', 'AWS ML', or 'model serving'. | 1 / 3 |
Distinctiveness Conflict Risk | The SageMaker-specific naming provides some distinctiveness from generic ML skills, but the vague 'ML Deployment' category could overlap with other deployment tools (e.g., Kubernetes ML deployments, other cloud ML services). | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%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 empty template that provides zero actionable guidance for SageMaker endpoint deployment. It contains only generic placeholder text that describes capabilities without demonstrating any of them. The skill fails to teach Claude anything about the actual task of deploying ML models to SageMaker.
Suggestions
Add executable boto3 code examples showing how to create a SageMaker endpoint (create_model, create_endpoint_config, create_endpoint)
Define a clear workflow with validation steps: 1) Create model artifact, 2) Configure endpoint, 3) Deploy, 4) Validate endpoint is InService, 5) Test inference
Include specific configuration examples for common instance types, auto-scaling policies, and multi-model endpoints
Add error handling guidance for common deployment failures (IAM permissions, container issues, instance availability)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with generic boilerplate that explains nothing specific about SageMaker endpoint deployment. Phrases like 'provides automated assistance' and 'follows industry best practices' are filler that Claude doesn't need. | 1 / 3 |
Actionability | No concrete code, commands, or specific guidance is provided. The skill describes what it does in abstract terms but never shows how to actually deploy a SageMaker endpoint - no boto3 examples, no CLI commands, no configuration snippets. | 1 / 3 |
Workflow Clarity | No workflow is defined. Deploying a SageMaker endpoint involves multiple steps (model registration, endpoint configuration, deployment, validation) but none are mentioned or sequenced. No validation checkpoints for this potentially costly operation. | 1 / 3 |
Progressive Disclosure | The content is a flat, generic template with no meaningful structure. No references to detailed documentation, no separation of quick-start vs advanced topics, and no links to examples or API references. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
f17dd51
- Reviewed
Table of Contents
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.