deploy-aws-eks
Guide for deploying the Anyscale AWS EKS public example from examples/aws/eks-public/. Use when the user asks about deploying, setting up, or configuring EKS for Anyscale.
64
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/deploy-aws-eks/SKILL.mdQuality
Discovery
89%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 is a reasonably well-crafted description with a clear 'Use when' clause and good trigger terms that target a very specific deployment scenario. Its main weakness is the lack of specific concrete actions beyond the general verbs 'deploying, setting up, configuring' — listing specific steps like 'configure Terraform modules, set up networking, provision node groups' would strengthen it. The narrow domain focus makes it highly distinctive.
Suggestions
Add more specific concrete actions the skill covers, e.g., 'Configures Terraform modules, sets up VPC networking, provisions EKS node groups, and deploys Anyscale services' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (deploying Anyscale AWS EKS) and references a specific example path, but doesn't list concrete actions beyond 'deploying, setting up, or configuring'. Lacks detail on what specific steps or capabilities the skill covers. | 2 / 3 |
Completeness | Clearly answers both 'what' (guide for deploying the Anyscale AWS EKS public example from a specific path) and 'when' (explicit 'Use when' clause covering deploying, setting up, or configuring EKS for Anyscale). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'deploying', 'setting up', 'configuring', 'EKS', 'Anyscale', 'AWS'. These are terms users would naturally use when asking about this topic. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a very specific niche: Anyscale + AWS + EKS + the specific example path. Unlikely to conflict with other skills unless there are multiple Anyscale EKS deployment skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid deployment guide with excellent actionability — every step has concrete, versioned commands ready to execute. The main weaknesses are the lack of validation checkpoints between steps (critical for a multi-step infrastructure deployment where each step depends on the previous) and the monolithic structure that could benefit from splitting detailed helm commands into supporting files. The content is mostly concise but has room for tightening.
Suggestions
Add explicit validation checkpoints after critical steps, e.g., `kubectl get nodes` after Step 3, `kubectl get pods -n kube-system | grep cluster-autoscaler` after Step 4, to verify each component before proceeding.
Consider splitting the detailed helm install steps (Steps 4-9) into a separate reference file, keeping SKILL.md as a concise overview with links to the detailed steps.
Remove the prerequisites links to installation docs — Claude can find these if needed — and trim variable descriptions to just the variable names and defaults in a compact table format.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with concrete commands and minimal fluff, but includes some unnecessary context like linking to tool installation docs (Claude knows how to find these) and explaining what outputs contain. The prerequisites section and some variable descriptions could be tighter. | 2 / 3 |
Actionability | Every step has concrete, copy-paste-ready shell commands with specific helm chart versions, repo URLs, and flag names. Variable examples are in real HCL syntax. The commands are fully executable with clear placeholders for user-specific values. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced and numbered with logical ordering, and the skip-to-step feature is useful. However, there are no validation checkpoints between steps — no verification that terraform applied successfully, that kubeconfig works, that helm installs succeeded, or that pods are running before proceeding. Troubleshooting is only at the end rather than integrated as verification steps. | 2 / 3 |
Progressive Disclosure | References to external files like `variables.tf`, `gpu_instances.tfvars.example`, and sample values YAML files are present and helpful. However, the skill is quite long (~130 lines of substantive content) and could benefit from splitting detailed helm install steps into a separate reference file, keeping SKILL.md as a higher-level overview. No bundle files are provided to support the references. | 2 / 3 |
Total | 9 / 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
b3e1428
- 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.