Name: genpage
Rating: 70.39999999999999 (1 reviews)
Author: microsoft

genpage

Creates, updates, and deploys Power Apps generative pages for model-driven apps using React v17, TypeScript, and Fluent UI V9. Orchestrates specialist agents for planning, entity creation, and code generation. 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".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with clear, well-validated phased workflows and exact commands. Its main weaknesses are conciseness (extended rationale that over-explains) and progressive disclosure (the inline workflow is large and the referenced bundle files are absent in this context).

Suggestions

Trim the multi-bullet rationale blocks (e.g., Phase 1 'Reasons to NEVER ask') to one line each — Claude can infer the why from the stated rule.

Move the detailed Phase 6 deploy flag tables and Phase 6.5 navigation fix-up into a reference file (e.g. deploy.md) and keep the main body to the phase summary plus a link, improving progressive disclosure.

Consolidate the duplicate mock/Dataverse page-builder prompt templates into one parameterized block rather than two near-identical listings.

Dimension	Reasoning	Score
Conciseness	The body is action-dense but ~490 lines with extended rationale blocks (e.g., the multi-bullet "Reasons to NEVER ask" explanation) that re-justify decisions Claude could largely infer, so it is mostly efficient but could be tightened.	2 / 3
Actionability	Provides copy-paste-ready, fully-specified commands with exact flags ("pac model genpage upload --app-id ... --code-file ... --prompt ...") and concrete file paths, matching the executable-and-complete anchor.	3 / 3
Workflow Clarity	Sequenced phases 0–8 with explicit validation checkpoints (check-auth.js ok:false stops the workflow, duplicate-filename rewrite before dispatch, "Only proceed when validation passes" style gating) and clear error-recovery guidance.	3 / 3
Progressive Disclosure	References are one-level-deep and well-signaled (rules.md, troubleshooting.md, verify-flow.md, edit-flow.md), but no bundle files exist in the review context to back them, and the main body is a monolithic inline workflow that could itself be split, so structure is present but not fully realized.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is strong across all four dimensions: it states concrete actions, gives explicit when-to-use triggers with natural terms, and is clearly niched to Power Apps generative pages. It avoids vague fluff and over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Creates, updates, and deploys" plus "Orchestrates specialist agents for planning, entity creation, and code generation" — matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers both what (creates/updates/deploys generative pages) and when ("Use it when user asks... / Use it when user mentions..."), with two explicit trigger clauses.	3 / 3
Trigger Term Quality	Cites natural user-facing terms ("generative page", "page in a model-driven", "genux") that a user would plausibly say, giving good coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to Power Apps model-driven generative pages with distinctive triggers, making activation for the wrong skill unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 16 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
relative_links	Relative link issues: 1 missing, 3 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 missing, 1 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: microsoft/power-platform-skills
Commit: 55fa377

Reviewed: 5 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.