mcpbeat Sign in

Infopath To Canvas Agent Skill

Migrate a Microsoft InfoPath form (.xsn) to a Power Apps Canvas app. USE WHEN the user wants to convert, port, or migrate an InfoPath form/template to Canvas Apps, or asks for help moving off of InfoPath.

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
30
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/microsoft/power-cat-skills --skill infopath-to-canvas

What it tells the agent to use

found in the instruction text
Glob reads your files

The instruction itself

4 sections, as written by the author

Migrate an InfoPath Form to a Canvas App

Migrate the InfoPath form described below:

$ARGUMENTS

A .xsn is a CAB archive containing manifest.xsf (rules, views, data connections),

schema*.xsd (data schema), template.xml (defaults), and XSL views. This skill runs three

phases: extract → inventory → hand off to generate-canvas-app. Pause for user approval

after the inventory.


Phase 0 — Extract

From $ARGUMENTS, resolve a .xsn path. If the user gave a folder, Glob for *.xsn

inside; ask if there are multiple or none.

If a sibling xsn_extracted/ already contains manifest.xsf, reuse it. Otherwise extract to

<source_dir>/xsn_extracted/:

  • Windows: & "$env:SystemRoot\System32\expand.exe" "<form>.xsn" -F:* "<xsn_extracted>" via PowerShell
  • macOS / Linux: cabextract -d <xsn_extracted> <form>.xsn

Verify manifest.xsf and schema1.xsd exist; abort if not.


Phase 1 — Inventory

Spawn a general-purpose Agent to write infopath-inventory.md covering:

  • Fields — from schema1.xsd + template.xml dfs:dataFields: decoded name, type

(Text, Date, Number, Choice, multi-Choice, Person, NoteEnhanced/rich-text, Lookup, …),

constraints (maxLength, pattern, enumeration, minOccurs/nillable), default.

Decode URL-encoded names: _x0020_=space, _x0028_=(, _x0029_=), _x002d_=-,

_x0023_=#, _x0026_=&.

  • Rules — from manifest.xsf: schema-required fields, xsf:errorCondition (field +

XPath translated to plain English + message), xsf:ruleSet/xsf:domEventHandler (trigger,

condition, action), xsf:submit destination.

  • Lookup connections — every non-schema*.xsd schema: source name + columns used.
  • Views — section headings and field ordering from the XSL views; note multiple views.
  • Section recommendation — propose logical sections of 10–30 fields each for Canvas.

After the agent returns, surface counts (fields / rules / connections / sections) and ask:

  • Mock with collections in App.OnStart (default), or wire to real SharePoint?
  • Keep all sections, or drop any?
  • Aesthetic preferences? (default: clean professional)

Wait for answers.

If the user wants to wire to real SharePoint, strongly suggest they add the SharePoint

list(s) as a data source in the app *before* generation — Canvas can't bind to a connection

that doesn't exist in the app. Tell them the steps (Power Apps Studio → Data → Add data →

SharePoint → pick site/list) and that this skill can verify the schema once it's done.

When they confirm, call mcp__canvas-authoring__list_data_sources to see what's connected,

then mcp__canvas-authoring__get_data_source_schema for each list. Diff against the

inventory: every InfoPath field should map to a SharePoint column of compatible type. Report

any missing columns, type mismatches (e.g. InfoPath Date vs. SP Text), or

extra-required columns the form doesn't populate. Pause and let the user reconcile

(rename columns, add missing ones, or trim the inventory) before Phase 2.


Phase 2 — Hand off to generate-canvas-app

Write canvas-app-prompt.md containing:

  • The kept sections + field lists with type hints (call out dates, multi-choice, rich text).
  • Each InfoPath rule restated as the desired Canvas behavior in plain English (the inner

skill maps to Power Fx).

  • Mock-data plan if mocking: 3–5 sample records per section, plus choice-list collections

seeded from enumerations / lookup tables.

  • The user's aesthetic answer.
  • Validation should block submit (DisplayMode.Disabled on Save buttons) — an intentional

upgrade from InfoPath's flag-but-don't-block behavior; flag this as a deliberate change.

Then invoke generate-canvas-app via the Skill tool, passing the prompt as args. If

that skill isn't available, instruct the user to run /generate-canvas-app against

canvas-app-prompt.md.

Other skills for the same job

different authors, same section of the catalogue
Canvas Design
by anthropics
vendor ×13

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

1388k tokens
Algorithmic Art
by anthropics
vendor ×10

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

15k tokens scripts
Image Enhancer
by frostant
×6

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

635 tokens
Video Downloader
by CommandCodeAI
×4

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

671 tokens
Histolab
by christophacham
×3

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

18k tokens
Omero Integration
by christophacham
×3

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

32k tokens
Pydicom
by christophacham
×3

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

13k tokens scripts
Transformers
by christophacham
×3

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

13k tokens

How to use it

Copy the folder

Take microsoft/infopath-to-canvas from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.