Report Issue logo

Report Issue

Organization
microsoft
report-issue

Use when the user wants to report a bug, file an issue, submit a bug report, or report any problem with the mobile-app plugin.

Overview

Publishermicrosoft
Repositorypower-platform-skills
Skill namereport-issue
Stars
895
Forks
182
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by microsoft on GitHub. Read the source before you install it.

Installation

Install the Report Issue AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/microsoft/power-platform-skills.git /tmp/power-platform-skills
mkdir -p .claude/skills
cp -r /tmp/power-platform-skills/plugins/mobile-apps/skills/report-issue .claude/skills/report-issue
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Report Issue in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Report Issue on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Report Issue is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

📋 Shared instructions: shared-instructions.md — read this first.

Report Issue — mobile-app

Generates a fully-populated GitHub issue body for the microsoft/power-platform-skills repo, scoped to the mobile-app plugin. Read-only — no project modifications.

Workflow

  1. Capture user description → 2. Detect project context → 3. Collect diagnostics → 4. Render issue body → 5. Print URL

Step 1 — Capture user description

Telemetry checkpoint: capture_issue_description

If $ARGUMENTS contains a description, use it. Otherwise prompt:

"What's the issue? Briefly describe what you expected vs. what happened. (You can paste error output if helpful.)"

Then ask via AskUserQuestion:

"Issue category? (a) Bug — something broke (b) Unexpected behavior — wrong output but no error (c) Documentation — docs are wrong / missing (d) Feature request (e) Question / discussion"

"How blocking is this? (a) Blocking — can't proceed at all (b) Workaround exists — but painful (c) Annoying — non-critical (d) Polish — nice-to-have"

Step 2 — Detect project context

Read-only checks:

bash
test -f power.config.json && echo "in_project=true" || echo "in_project=false"
pwd
node --version
npm --version
node scripts/resolve-environment.js "$(node -e \"console.log(require('./power.config.json').environmentId)\")" 2>/dev/null || true
az --version 2>/dev/null | head -1
npx expo --version 2>/dev/null
uname -srm

If in a project:

bash
node -e "console.log(require('./package.json').name, require('./package.json').version)" 2>/dev/null
node -e "console.log(JSON.stringify({env: require('./power.config.json').environmentId, name: require('./power.config.json').displayName}))"
test -f memory-bank.md && echo "memory_bank=present"
test -f native-app-plan.md && echo "plan=present"
ls src/generated/services/ 2>/dev/null | head -10

If the description names a package matching @microsoft/power-apps-native-*, collect its declared and lockfile-resolved versions from package.json and package-lock.json. Do not read package source or metadata from node_modules/.

bash
node - <<'NODE'
const fs = require('node:fs');
const manifest = JSON.parse(fs.readFileSync('package.json', 'utf8'));
const lockfile = fs.existsSync('package-lock.json')
  ? JSON.parse(fs.readFileSync('package-lock.json', 'utf8'))
  : null;
const dependencies = { ...manifest.dependencies, ...manifest.devDependencies };
for (const [name, declared] of Object.entries(dependencies)) {
  if (!name.startsWith('@microsoft/power-apps-native-')) continue;
  const resolved = lockfile?.packages?.[`node_modules/${name}`]?.version ?? 'unknown';
  console.log(`${name}\tdeclared=${declared}\tresolved=${resolved}`);
}
NODE

For native-build issues also capture:

bash
[ "$(uname)" = "Darwin" ] && xcode-select -p
[ "$(uname)" = "Darwin" ] && pod --version 2>/dev/null
java -version 2>&1 | head -1
echo "ANDROID_HOME=$ANDROID_HOME"

Step 3 — Collect diagnostics

Telemetry checkpoint: collect_issue_diagnostics

Run npx expo doctor and capture the text output verbatim.

If the user pasted an error, capture verbatim. Otherwise look for recent failure signals:

  • Last 50 lines of any Metro / Gradle / Xcode log if user mentions a build failure
  • git status --short if in a git repo (to show modified files — sanitize for secrets first)
  • Output of npx tsc --noEmit if relevant

Do NOT capture:

  • Contents of src/playerConfig.ts (contains tenantId / clientId — sensitive)
  • Contents of .env or any file matching .env*
  • Connection IDs unless the user explicitly opted in (PII / can map to tenant)
  • Anything under node_modules/
  • Package source excerpts, patched package contents, or proposed fork code

Step 4 — Render issue body

Telemetry checkpoint: render_issue_report

Print this block — user copies into a new issue:

markdown
### Description

<user's description>

### Category

<Bug / Unexpected behavior / Docs / Feature / Question>

### Severity

<Blocking / Workaround / Annoying / Polish>

### Environment

| | |
|---|---|
| Plugin | mobile-app |
| Plugin version | <from .plugin/plugin.json, or legacy .claude-plugin/plugin.json fallback, or "unknown"> |
| OS | <uname output> |
| Node | <version> |
| npm | <version> |
| Power Apps CLI | <version> |
| Expo CLI | <version> |
| Xcode | <if macOS> |
| JDK | <if android> |
| ANDROID_HOME set | <yes/no> |

### Project context

<if in project>
- Project: `<name>` v`<version>`
- Power Platform env: `<env-id>`
- Memory bank present: <yes/no>
- Plan present: <yes/no>
- Connectors registered: <list from src/generated/services>
</if>

<if not in project>
Not run inside a mobile-app project.
</if>

### Affected native package

<include only when the issue concerns @microsoft/power-apps-native-*>
- Package: `<package name>`
- Declared version: `<package.json range>`
- Resolved version: `<package-lock.json version or unknown>`
- Platform: `<iOS / Android>`
- Ownership evidence: <why the documented caller contract is satisfied and the failure is package-internal>

### Reproduction steps

1.
2.
3.

### Expected

<what should have happened>

### Actual

<what happened>

### Logs / errors

<paste verbatim — sensitive values redacted>


### Notes

<anything else>

Step 5 — Print URL

Telemetry checkpoint: generate_issue_submission_url

Tell the user:

Open this URL to file the issue:

https://github.com/microsoft/power-platform-skills/issues/new?labels=plugin%3Amobile-app

Paste the block above into the body. Review for any sensitive values before submitting.

If the user wants to open it, suggest open <url> (macOS) / xdg-open <url> (Linux) / start <url> (Windows). Do not auto-open without confirmation.

Notes

  • This skill never modifies any file or invokes mutating commands. Pure diagnostic.
  • For diagnosing connection-specific failures, suggest the user run /list-connections first and paste that output into the issue.
  • For diagnosing build failures, suggest they include the full Metro/Gradle/Xcode log (not truncated).

Frequently asked questions

What does the Report Issue AI skill do?

Use when the user wants to report a bug, file an issue, submit a bug report, or report any problem with the mobile-app plugin.

Why use Report Issue on TypingMind?

Because you install it once and use it with any model. Report Issue is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Report Issue in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/microsoft/power-platform-skills/tree/main/plugins/mobile-apps/skills/report-issue. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Report Issue?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Report Issue?

As many as you like. As long as a model supports skills, you can use Report Issue with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Report Issue AI skill free?

Yes. It is published on GitHub by microsoft under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇