canvas-app

Creates or edits a Power Apps Canvas App through the Canvas Authoring MCP coauthoring session. Handles new app generation, direct targeted edits, complex multi-screen changes, responsive layout, per-screen self-QA, and compile-error convergence. Trigger on requests to create, build, generate, modify, update, change, fix, or edit a Canvas App or .pa.yaml files.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%Weight 40%Scale 1-5

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

The content is a well-structured, highly actionable orchestration workflow with strong validation and feedback loops; its main weakness is verbosity, with a long, repetitive post-build checklist that could be trimmed or externalized.

Suggestions

Consolidate the repeated 'send the owning screen back for self-QA / in-place repair' guidance into one stated rule instead of restating it across many post-build bullets.

Move the lengthy per-check QA rationale into QAChecks.md (or a dedicated reference) and keep only the decision rule inline to reduce body length.

Tighten verbose phrasing like 'This costs one cheap turn. The defects these checks catch ...' to a single clause; the operational rule already earns its place.

Dimension	Reasoning	Score
Conciseness	The body is densely operational and largely free of generic concepts Claude already knows, but it is long and repetitive — the post-build QA/checklist block reiterates 'send the screen back' guidance many times and could be tightened without losing clarity.	3 / 5
Actionability	Highly actionable throughout: exact tool calls (sync_canvas, compile_canvas, describe_control), absolute file paths, a copy-paste builder invocation template, and one-for-one verification steps that cover the common cases.	5 / 5
Workflow Clarity	A clearly sequenced multi-step process (workspace → route → planned handoff → shared invariants) with explicit validation checkpoints (compile after each wave), feedback loops (re-invoke planner, in-place repair), and detailed checklists; validation is abundant so no destructive/batch cap applies.	5 / 5
Progressive Disclosure	Branch detail is delegated to clearly signaled one-level-deep references (CreateWorkflow.md, EditWorkflow.md, QAChecks.md, ValidationWorkflow.md), but no local bundle files exist and the main body remains very long, so some inline detail (e.g. the QA checklist) could arguably live in a reference.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

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 specific, trigger-rich, and clearly distinguishes the skill's niche; it answers both what it does and when to use it in concise third-person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'new app generation, direct targeted edits, complex multi-screen changes, responsive layout, per-screen self-QA, and compile-error convergence' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (creates/edits a Canvas App, handles the listed capabilities) and 'when' ('Trigger on requests to create, build, generate...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage with synonyms ('create, build, generate, modify, update, change, fix, or edit') plus the concrete file extension '.pa.yaml', matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	A clear niche (Power Apps Canvas App via the Canvas Authoring MCP, .pa.yaml files) with distinct triggers and minimal overlap risk with unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: microsoft/power-platform-skills
Path: plugins/canvas-apps/skills/canvas-app/SKILL.md
Commit: 4c284ab

Reviewed: 2 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.