microsoft/power-platform-skills is a plugin marketplace containing reusable skills, agents, and commands for developing with Microsoft Power Platform. Developers use it to build and deploy Power Pages sites, model-driven Power Apps, and related solutions through Claude Code or GitHub Copilot. The catalogue entries are the marketplace's included skills, agents, plugins, and other agent components.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/microsoft/power-platform-skillsnpx agentmods add skills/microsoft/power-platform-skills/build-android-binaryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/power-platform-skills/build-android-binary)<a href="https://agentmods.dev/skills/microsoft/power-platform-skills/build-android-binary"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/build-android-binary/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/power-platform-skills/build-android-binary"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/build-android-binary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Excessive Agency · line 126 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00150 | $0.05437 |
| Opus 5.5 | $0.00060 | $0.02175 |
| Sonnet 5.5 | $0.00030 | $0.01087 |
| Haiku 4.5 | $0.00015 | $0.00544 |
Grade A, and why
build-android-binary scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build-android-binary
Turns the extension's Android source (android/.../<Pascal>Module.kt + <Pascal>Package.kt) into the DEX binary that the wrap runtime loads at runtime via DexClassLoader. This is the heavyweight, toolchain-dependent step of producing a .ppmplugin: source code in, a runnable <Pascal>Plugin.dex out.
Naming note: this skill runs Gradle's
assembleReleasetask internally. Don't confuse that with/assemble-ppmplugin, which zips the final bundle — different layers. This skill produces a binary; that one produces the bundle.
Cross-platform: runs on macOS, Linux, and Windows — the Android path has no Mac-only step (JDK 17, Gradle, and Android SDK
d8exist on all three). Every shell command below is given in both bash and PowerShell forms per shared-instructions §5.
Read shared/ppmplugin-format.md §5 — the Android binary requirements this skill enforces.
What this skill does NOT do
- Does not author
manifest.json(run/generate-ppmplugin-manifestfirst — this skill reads it for cross-checks). - Does not zip the
.ppmplugin— that's/assemble-ppmplugin. - Does not build iOS — that's
/build-ios-binary(Mac-only). - Does not modify the canonical
android/— all standalone adjustments are made to a throwaway copy underppmplugin/staging/android-build/(Step 2). The source the engineer maintains is never touched.
Step 1 — Read shared docs + prereq block
- Read
shared/shared-instructions.mdandshared/ppmplugin-format.md. - Read
ppmplugin/staging/manifest.json. If absent, STOP withNEEDS_CONTEXT: manifest.json missing — run /generate-ppmplugin-manifest first(the build cross-checks against it). 2b. Read the## ppmplugin (third-party controls)block in.extension-state.md. If a DEX already exists atppmplugin/staging/android/<dex>, do NOT silently overwrite it — surface it (with its build timestamp) and ask viaAskUserQuestionwhether to replace it:- Source +
manifest.jsonunchanged since the recordedAndroid DEX: builttimestamp → recommend Keep existing (reuse) [default]; also offer Replace (rebuild). - Source or manifest changed → recommend Replace (rebuild) [default]; also offer Keep existing (note: stale — won't match current source). On Keep, skip straight to Step 6 (report) using the existing DEX. On Replace, continue the rebuild. Building is always safe to repeat — this gate just respects an artifact you may have produced on purpose.
- Source +
- Run prereq checks and print the visible block (shared-instructions §9.2). Policy: resolve, don't punt. Each check first tries to satisfy itself — locate a tool by its standard install path (not just PATH), or offer to run a safe install and execute it on
yes(§1.5 auto-fix flow). A check only hard-BLOCKs when it needs something genuinely un-resolvable without a human (e.g. a role grant). "Found but not on PATH" is NOT a block — use the absolute path. Checks:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 212 lines · 150 tokens per session scan A 3a39920d9b3e
build-android-binary is a skill published in the GitHub repository microsoft/power-platform-skills (1,021 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 5,437 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
swiftui-expert
This skill should be used when the user is building, reviewing, or debugging SwiftUI views and apps. Detects iOS and Swift version from the project. Covers creating views, state management with @Observable, NavigationStack routing, animations, accessibility, performance optimization, Liquid Glass adoption, design…
swiftui-expert
This skill should be used when SwiftUI work requires judgment about Observation and state ownership, view identity or lifecycle, navigation, app-target concurrency, persistence, Apple-platform behavior, accessibility, performance, or architecture. Trigger on "review this SwiftUI screen", "why isn't this view…
jetpack-compose-expert
Use when working in a native Android Jetpack Compose project - build.gradle.kts with androidx.compose BOM or org.jetbrains.kotlin.plugin.compose, .kt files containing @Composable functions, MainActivity with setContent, or mentions of Compose, Material 3, recomposition, ViewModel, StateFlow, Hilt, Room, or Navigation…
swiftui-expert
Use when working in a native iOS/SwiftUI project - .swift files, an .xcodeproj or Package.swift, Xcode schemes, or mentions of SwiftUI, Swift 6, @Observable, SwiftData, NavigationStack, actors, or Swift Testing. Builds views and features, wires Observation-based state, fixes Swift 6 strict-concurrency errors, models…
bootstrap-xcode-workspace
Create, adopt, extend, and align one Swift product workspace with app, extension, package, and service components under one permanent Xcode entrypoint.
android-kotlin-compose
Android development with Kotlin and Jetpack Compose. Use when user mentions "Compose", "Jetpack Compose", "Material3", "Hilt", "Room", "ViewModel", or needs to build Android UI, implement MVVM architecture, manage Compose state, or integrate Jetpack libraries (Navigation, Room, Hilt, ViewModel). Triggers on…