Name: genpage
Rating: 66.4 (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

81%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

62%

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

This skill excels at actionability and workflow clarity — every phase has concrete commands, exact flag names, validation checkpoints, and error recovery paths. However, it is significantly over-long and verbose, embedding detailed prompt templates, JSON schemas, and lengthy rationale blocks inline that could be extracted to reference files. The progressive disclosure is partially effective (good external references for edit flow and verification) but the main file itself carries too much detail for an orchestration overview.

Suggestions

Extract the subagent prompt templates (Phase 1 invocation prompt, Phase 5c prompts) into a separate `prompt-templates.md` reference file and link to it, reducing the main file by ~80 lines.

Move the check-auth.js JSON response schema and blocker-handling table to the troubleshooting.md reference rather than inlining the full JSON shape and all blocker values.

Condense the Phase 1 critical warning block — the 15-line explanation of why not to ask 'new or edit?' yourself can be reduced to 2-3 lines stating the rule and consequence, since Claude doesn't need the detailed rationale repeated.

Move the `workflow-log.md` formatting requirements and eval-harness grep token list to a separate `logging-requirements.md` reference file.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~400+ lines. It over-explains orchestration details, repeats prompt templates verbatim, includes lengthy inline warnings (e.g., the Phase 1 critical block explaining why not to ask 'new or edit?' yourself), and documents internal implementation contracts (like the JSON shape of check-auth.js output) that could live in referenced files. Many sections explain things Claude can infer from context.	1 / 3
Actionability	The skill provides fully executable commands (pac model genpage upload with exact flags), concrete script invocations with paths, specific JSON output schemas, exact prompt templates for subagent invocation, and copy-paste ready PowerShell/bash commands. Every phase has concrete, specific instructions.	3 / 3
Workflow Clarity	The multi-phase workflow is clearly sequenced (Phase 0 through Phase 8) with explicit validation checkpoints: pre-flight auth checks with specific blocker handling, plan validation before dispatch (5a), PAGEREF placeholder verification (Phase 6.5 step 4), and browser verification. Error recovery paths are specified (identity mismatch warnings, fix-and-redeploy loops).	3 / 3
Progressive Disclosure	The skill references external files appropriately (rules.md, troubleshooting.md, edit-flow.md, verify-flow.md, data-caching.md, localization.md) and explicitly defers loading some until needed (verify-flow.md loaded on demand). However, the main SKILL.md itself is monolithic — the detailed prompt templates, the full check-auth.js JSON schema, the verbose Phase 1 warning block, and the deployment command logging format could all be extracted to reference files to keep the overview leaner.	2 / 3
	Total	9 / 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.

This is a strong skill description that clearly defines its scope, lists concrete actions, provides explicit trigger guidance with natural keywords, and occupies a distinct niche. The tech stack specifics (React v17, TypeScript, Fluent UI V9) and domain-specific terms ('genux', 'generative page') make it both informative and highly distinguishable from other skills.

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), and mentions orchestrating specialist agents for planning, entity creation, and code generation.	3 / 3
Completeness	Clearly answers both 'what' (creates, updates, deploys generative pages using specific technologies, orchestrates specialist agents) and 'when' (explicit 'Use it when...' clauses with specific trigger phrases like 'generative page', 'genux', etc.).	3 / 3
Trigger Term Quality	Includes strong natural trigger terms users would 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 niche targeting Power Apps model-driven generative pages specifically, with unique trigger terms like 'genux' and 'generative page' that are unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 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

Repository: microsoft/power-platform-skills
Commit: 180ed78

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.