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
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/microsoft/power-platform-skills/add-nativenpx skills add microsoft/power-platform-skills --skill add-nativegit clone --depth 1 https://github.com/microsoft/power-platform-skillsWrote 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/add-native)<a href="https://agentmods.dev/skills/microsoft/power-platform-skills/add-native"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/add-native.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00096 | $0.06670 |
| Opus 5 | $0.00048 | $0.03335 |
| Sonnet 5 | $0.00019 | $0.01334 |
| Haiku 4.5 | $0.00010 | $0.00667 |
Grade A, and why
add-native 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 yesterday.
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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📋 Shared instructions: shared-instructions.md — read first.
Add Native Capability
Generate a one-file typed wrapper under src/native/ for a native device capability that the upstream template already ships. Screens import the wrapper instead of touching Expo modules directly, so the discriminated-union result contract stays consistent across the app.
Hard rules — do NOT cross these lines
- Never run
npx expo install,npm install, oryarn addfor a native module. The set of native modules inpackage.jsonis fixed by the upstream template. Adding a new one breaks the rewrap pipeline (the customer's binary is built from a pre-built base, not from theirpackage.json). - Never edit
app.config.js— plugins,ios.infoPlist,android.permissions, or anything else. All native config the template ships is intentional and signed off; arbitrary additions cannot be honored at rewrap time. - Never edit
package.jsondependenciesfor native modules. Native means the package ships platform source/projects, a podspec, codegen, an Expo module/config plugin, orreact-native.config.js; a package-name prefix alone is not proof. Pure-JavaScript dependencies are out of scope for/add-nativeand are installed from an approvedJavaScript Dependenciesplan by/create-mobile-appor/edit-app. - If the requested module isn't actually present in
package.json— STOP. That means the upstream template hasn't shipped it yet; do not work around by installing it.
Routing — /add-native is the public entry point
Some capabilities have a dedicated implementation helper that does more than a plain wrapper (camera writes scanner/upload helpers; PDF report/viewer helpers enforce local-vs-HTTPS boundaries; pen has native-control-specific validation). Users should still call /add-native <capability> for native controls. When a dedicated implementation exists, run it internally and do not ask the user to run that helper directly.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +1 lines e93780c00d73
- 5d ago First seen · 325 lines · 96 tokens per session scan A 6ffa48da52c6
add-native is a skill published in the GitHub repository microsoft/power-platform-skills (814 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 6,670 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
canvas-apps-ui-gen
Generates paste-ready Power Apps Canvas App YAML. Invoke when the user wants to replicate a UI mockup, improve an existing Canvas app screen, or build a new screen from a text description. Also invoke when the user asks to "improve", "redesign", or "generate YAML" for a Canvas app screen.
vertical-fintech-mobile
Domain-knowledge pack for money on a phone — wallets, payments, custody and signing, transaction lifecycle, KYC/AML gates, and offline reconciliation. The rules that separate a payments app from a CRUD app with a currency symbol: a balance is a claim about a server, an idempotency key must outlive the process that…
validate-mobile
Run a Maestro flow on an explicitly selected iOS or Android device and report behavioral evidence.
fec-pwa-implementation
用于添加或审查 Progressive Web App 能力，如可安装性、manifest 元数据、Service Worker 注册、Workbox 缓存、离线兜底、应用更新提示、maskable icons 或 iOS PWA 兼容性。不要用于普通 API 缓存或不可安装的性能调优；中文触发词包括 PWA、离线、Service Worker。.
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…
eng-unity-mobile-optimization
Mobile-specific Unity optimization patterns for memory, battery, thermal, and performance.