Creates, updates, and deploys Power Apps generative pages for model-driven apps using React v17, TypeScript, and Fluent UI V9. Completes workflow from requirements to deployment. Uses PAC CLI to deploy the page code. Use it when user asks to build, retrieve, or update a page in an existing Microsoft Power Apps model-driven app. Use it when user mentions "generative page", "page in a model-driven", or "genux".
92
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 clearly defines its scope, lists concrete actions and technologies, and provides explicit trigger guidance with natural user terms. It covers a well-defined niche (Power Apps generative pages) with minimal risk of conflicting with other skills. The description is concise yet comprehensive, following best practices for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creates, updates, deploys Power Apps generative pages, specifies the tech stack (React v17, TypeScript, Fluent UI V9), mentions PAC CLI for deployment, and describes the full workflow from requirements to deployment. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates, updates, deploys Power Apps generative pages using specific technologies) and 'when' (explicit 'Use it when...' clauses with specific trigger phrases like 'generative page', 'page in a model-driven', 'genux'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'generative page', 'page in a model-driven', 'genux', 'Power Apps', 'model-driven app', 'build', 'retrieve', 'update'. Good coverage of both formal and shorthand terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Power Apps model-driven generative pages with specific tech stack. The trigger terms 'genux', 'generative page', and 'model-driven app' are very specific and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, comprehensive skill that provides an excellent step-by-step workflow for building Power Apps generative pages. Its greatest strengths are actionability (concrete commands and code throughout) and workflow clarity (well-sequenced steps with validation checkpoints and feedback loops). The main weakness is moderate verbosity—some content is repeated between inline references and external files, and certain sections (like the example descriptions in Step 3) could be trimmed without losing clarity.
Suggestions
Reduce redundancy by removing the inline DataAPI Quick Reference section and relying solely on the reference to genpage-rules-reference.md, or vice versa—having both creates duplication.
Shorten the example page descriptions in Step 3 (Options 1 and 2) to 1-2 sentences each, since they serve as illustrative prompts rather than specifications.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~300+ lines) and includes some redundancy (e.g., DataAPI rules repeated in both inline quick reference and references to genpage-rules-reference.md, column name warnings stated multiple times). However, most content is domain-specific and not something Claude would inherently know (PAC CLI commands, genux-specific workflows, DataAPI patterns), so the verbosity is partially justified. Some tightening is possible—the example descriptions in Step 3 are very long and the DataAPI quick reference duplicates the external reference file. | 2 / 3 |
Actionability | Excellent actionability throughout. Every step includes exact PowerShell commands, complete TypeScript code templates, specific flag names, and concrete examples. The component template, DataAPI quick reference, deployment commands, and Playwright verification steps are all copy-paste ready with no pseudocode or vague instructions. | 3 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced with explicit validation checkpoints: prerequisite verification (Step 1), schema generation before code writing (Step 5 marked CRITICAL), plan confirmation before coding (Step 4), user confirmation before deployment (Step 8), browser verification with fix-and-redeploy loop (Step 9.5). Feedback loops are present for error recovery at multiple stages, and destructive operations (deployment) require explicit user consent. | 3 / 3 |
Progressive Disclosure | The skill has a clear overview structure with well-signaled one-level-deep references to genpage-rules-reference.md, troubleshooting.md, and a samples directory with a helpful table mapping sample files to use cases. The main SKILL.md contains the workflow and essential inline references while deferring comprehensive rules and troubleshooting to separate files. Navigation is straightforward. | 3 / 3 |
Total | 11 / 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 | |
48e49c4
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.