List, find, and show Azure resources across subscriptions or resource groups. Handles prompts like "list the websites in my subscription", "list my web apps", "show my app services", "list virtual machines", "list my VMs", "show storage accounts", "find container apps", and "what resources do I have". USE FOR: list websites, list web apps, list app services, show websites in subscription, resource inventory, find resources by tag, tag analysis, orphaned resource discovery (not for cost analysis), unattached disks, count resources by type, cross-subscription lookup, and Azure Resource Graph queries. DO NOT USE FOR: deploying/changing resources (use azure-deploy), cost optimization (use azure-cost), or non-Azure clouds.
64
75%
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 ./plugin/skills/azure-resource-lookup/SKILL.mdQuality
Discovery
100%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 an excellent skill description that covers all key dimensions thoroughly. It provides rich natural trigger terms with many user-phrasing variations, clearly delineates its scope with both USE FOR and DO NOT USE FOR clauses, and names specific alternative skills to reduce conflict risk. The description is comprehensive without being padded with fluff.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: list, find, and show Azure resources, orphaned resource discovery, unattached disks, count resources by type, cross-subscription lookup, Azure Resource Graph queries, find resources by tag, and tag analysis. | 3 / 3 |
Completeness | Clearly answers both 'what' (list, find, show Azure resources across subscriptions/resource groups, tag analysis, orphaned resource discovery, etc.) and 'when' with explicit USE FOR and DO NOT USE FOR clauses that provide clear trigger guidance and boundary conditions. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user terms including common variations: 'list websites', 'list web apps', 'list app services', 'show my VMs', 'list virtual machines', 'show storage accounts', 'find container apps', 'what resources do I have'. These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via DO NOT USE FOR clauses that reference specific alternative skills (azure-deploy for deploying, azure-cost for cost optimization). The focus on listing/finding/showing resources is a clear niche distinct from deployment or cost analysis. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent skill with clear structure, useful routing tables, and a logical workflow, but it falls short on actionability by deferring concrete KQL examples to a non-existent reference file. The workflow lacks validation checkpoints, and the 'When to Use' section is verbose given that this information belongs in frontmatter. The skill would benefit from inline executable examples and a tighter feedback loop in the workflow.
Suggestions
Add 3-5 complete, executable ARG query examples inline (e.g., list all web apps, find unattached disks, tag audit) rather than deferring entirely to a missing reference file.
Integrate a validation/retry loop into the workflow: after Step 3, add explicit guidance like 'If results are empty, verify type spelling with `resources | distinct type | where type contains "web"`' then retry.
Remove or significantly condense the 'When to Use This Skill' section — this duplicates the skill description and wastes tokens on information Claude can infer from context.
Either provide the referenced `references/azure-resource-graph.md` bundle file or inline the most critical query patterns to ensure the skill is self-contained.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary content like the 'When to Use This Skill' section which largely restates the description/frontmatter, and the routing table is quite extensive. The tip/warning callouts add some value but the overall document could be tightened by ~30%. | 2 / 3 |
Actionability | Provides concrete CLI commands and MCP tool invocations, but the core workflow relies on `extension_cli_generate` to produce the actual query rather than giving executable ARG query examples directly. The YAML block for MCP invocation is helpful but the skill lacks complete copy-paste-ready KQL examples for common scenarios (those are deferred to a reference file that doesn't exist in the bundle). | 2 / 3 |
Workflow Clarity | The 3-step workflow is clearly sequenced (check dedicated tool → generate ARG query → execute and format), but there are no validation checkpoints or feedback loops. If a query returns empty results or errors, the error handling table lists fixes but there's no explicit 'verify → fix → retry' loop integrated into the workflow steps. | 2 / 3 |
Progressive Disclosure | References `references/azure-resource-graph.md` for query patterns which is good progressive disclosure design, but no bundle files are provided, meaning the reference doesn't actually exist. The main file also includes substantial inline content (routing table, error table) that could potentially be split out, though for a skill of this size it's borderline acceptable. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
915f809
Table of Contents
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.