Agent skill · Audited from source

Diagnose Deployment

skill · microsoft/power-platform-skillsMIT licenceAudited 18 Oct 2026 · source 8075ef5705c5

★ 1,020pushed today
✓SAFEGrade B · 89/100 · 18 Oct 2026 · 8075ef5
1,020repo stars · whole microsoft/power-platform-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 8075ef5705c5 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Surfaces PAC CLI upload errors and Dataverse async operation errors, pattern-matches against a known failure catalog, and optionally auto-fixes identified issues. Use when asked to: "diagnose deployment", "debug…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Diagnose Deployment (microsoft/power-platform-skills)”. Retrieved 18 Oct 2026. https://modelsatlas.com/skills/microsoft/diagnose-deployment

Trust audit

Audit 0.4.1 · source read 18 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 8075ef5705c5 · 18 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishermicrosoft GitHub organizationOwner of the repository this skill is read from
  • Source foldermicrosoft/power-platform-skills/plugins/power-pages/skills/diagnose-deploymentThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict8075ef5705c5A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Surfaces PAC CLI upload errors and Dataverse async operation errors, pattern-matches against a known failure catalog, and optionally auto-fixes identified issues. Use when asked to: "diagnose deployment", "debug…

---
name: diagnose-deployment
description: >-
  Surfaces PAC CLI upload errors and Dataverse async operation errors, pattern-matches
  against a known failure catalog, and optionally auto-fixes identified issues. Use when
  asked to: "diagnose deployment", "debug deployment", "deployment failed", "show
  deployment errors", "fix deployment issues", "show upload logs", "why did my deploy fail",
  or "troubleshoot upload".
user-invocable: true
allowed-tools: Read, Write, Edit, Bash, Glob, Grep, TaskCreate, TaskUpdate, TaskList, AskUserQuestion, mcp__plugin_power-pages_microsoft-learn__microsoft_docs_search, mcp__plugin_power-pages_microsoft-learn__microsoft_docs_fetch
model: opus
---

> **Plugin check**: Run `node "${PLUGIN_ROOT}/scripts/check-version.js"` — if it outputs a message, show it to the user before proceeding.

# diagnose-deployment

Surfaces and pattern-matches deployment errors against a known failure catalog. For each identified error with an available auto-fix, asks explicit user permission before applying any changes. Never auto-applies fixes without confirmation.

## Prerequisites

- Project root with `powerpages.config.json`
- PAC CLI installed (will report if missing)

## Phases

### Phase 1 — Verify Prerequisites and Locate Project

**Create all tasks upfront at the start of this phase.**

Tasks to create:
1. "Verify prerequisites and locate project"
2. "Collect deployment artifacts"
3. "Surface upload errors"
4. "Query solution import status"
5. "Diagnose and categorize findings"
6. "Offer auto-fixes"
7. "Present findings summary"

Steps:
1. Locate project root: search for `powerpages.config.json` in cwd and parent directories
2. Check PAC CLI: `pac --version` (report version or "not installed")
3. Check PAC CLI auth: `pac env who` (report environment URL or "not authenticated")
4. Check Azure CLI: `az account show` (report subscription or "not logged in")

Auth failures are non-blocking — report them as findings, continue collecting other artifacts.

### Phase 1.5 — Ground in current ALM documentation

> Reference: `${PLUGIN_ROOT}/references/alm-docs-grounding.md`

Cap this step at ~30 seconds. If MCP search / fetch errors out, log a one-line note and continue — this skill must remain runnable offline.

1. Run `microsoft_docs_search` with the query: `Power Pages deployment errors solution import troubleshooting`.
2. Fetch `https://learn.microsoft.com/en-us/power-platform/alm/solution-concepts-alm` (and at most one sister page on troubleshooting or known import errors) in parallel via `microsoft_docs_fetch`.
3. Extract a one-paragraph summary of what Microsoft Learn currently says about common deployment failures and their resolution. Compare against `${PLUGIN_ROOT}/references/deployment-error-catalog.md` and flag any new error patterns not yet captured in the catalog.
4. Use the summary to inform pattern-matching in Phase 5. If a new pattern is documented on Learn that isn't in the catalog, surface it to the user as a candidate addition rather than silently extending the catalog.

### Phase 2 — Collect Deployment Artifacts

Gather all available context:

1. Read `powerpages.config.json` — extract `siteName`, `websiteRecordId`, `compiledPath`
2. Check `.powerpages-site/` folder exists
3. Glob for manifest files: `.powerpages-site/*-manifest.yml` — list all found, note their environment hostnames
4. Check if `.solution-manifest.json` exists (for solution-related diagnostics)
5. Check if `docs/alm/last-import.json` exists (for recent import failures)
6. Check build output: confirm `{compiledPath}/` exists and is non-empty

Report: "Found project: `{siteName}`. Artifacts collected."

### Phase 3 — Surface Upload Errors

Re-run `pac pages upload-code-site` in capture mode to get fresh error output:

```bash
pac pages upload-code-site --rootPath "." 2>&1
```

> **Note**: This intentionally triggers the upload to capture any errors. If the upload succeeds cleanly, that is also a valid diagnostic result ("no errors found").

Capture stdout+stderr as a single string. Pass to `scripts/parse-deployment-errors.js`:

```bash
echo "{escaped-output}" | node "${PLUGIN_ROOT}/scripts/parse-deployment-errors.js"
```

Parse the JSON findings array. If the upload succeeded with no errors, note this and skip to Phase 5 with an empty findings list.

### Phase 4 — Query Solution Import Status

Only run if `.solution-manifest.json` exists.

1. Acquire Azure CLI token for environment URL
2. Check recent async operations (last 24 hours):
   ```
   GET {envUrl}/api/data/v9.2/asyncoperations?$filter=statecode eq 3 and statuscode eq 31 and createdon gt {yesterday}&$select=asyncoperationid,name,message,friendlymessage,statuscode,completedon&$orderby=completedon desc&$top=5
   ```
3. Check recent import jobs:
   ```
   GET {envUrl}/api/data/v9.2/importjobs?$select=solutionname,completedon,progress&$orderby=completedon desc&$top=3
   ```
4. If failed operations found, pass each `message` field through `parse-deployment-errors.js`

Skip gracefully if auth is not available (auth failure in Phase 1).

### Phase 5 — Auto-Diagnose Known Issues

Consolidate all findings from Phases 3 and 4. For each finding, categorize:

- **Error**: Blocks deployment
- **Warning**: May cause issues
- **Info**: Informational

Also add findings for missing artifacts discovered in Phase 2:
- Missing `websiteRecordId` → Error (patternId: `missing-website-record-id`)
- Empty build output → Error (patternId: `empty-build`)
- Multiple environment manifests → Warning (may indicate environment confusion)

Present all findings in a table:

| # | Severity | Type | Issue | Auto-fix? |
|---|---|---|---|---|
| 1 | Error | upload | JavaScript uploads blocked | Yes |
| 2 | Warning | config | Multiple manifest files found | No |

### Phase 6 — Offer Auto-Fixes

For each Error finding with `autoFixAvailable: true`, in order:

<!-- gate: diagnose-deployment:6.auto-fix | category=consent | cancel-leaves=nothing -->
> 🚦 **Gate (consent · diag

Excerpt, first 6,001 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 8075ef5

Download folder ↗
git clone https://github.com/microsoft/power-platform-skills
git -C power-platform-skills checkout 8075ef5705c5

The author documents no install command, so this uses the repository directly. Our verdict covers commit 8075ef5705c5 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 8075ef5705c5

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/microsoft/diagnose-deployment/badge.svg)](https://modelsatlas.com/skills/microsoft/diagnose-deployment/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/microsoft/diagnose-deployment/badge.svg)](https://modelsatlas.com/skills/microsoft/diagnose-deployment/)

Questions about Diagnose Deployment

What does the Diagnose Deployment skill do?
A plugin marketplace for GitHub Copilot and other AI agents that provides Power Platform development plugins, including reusable skills, agents, and commands for building and deploying solutions.
Is Diagnose Deployment safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Diagnose Deployment access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (8075ef5705c5), read on 2026-10-18. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.