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 skills add microsoft/power-platform-skills --skill deploygit 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/deploy)<a href="https://agentmods.dev/skills/microsoft/power-platform-skills/deploy"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/deploy/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/deploy"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 6 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.
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 | $0.00032 | $0.00498 |
| Opus 5.5 | $0.00013 | $0.00199 |
| Sonnet 5.5 | $0.00006 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
deploy 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.
What it actually says
📋 Shared Instructions: shared-instructions.md - Cross-cutting concerns.
Deploy
Builds and deploys the app in the current directory to Power Platform.
Workflow
- Check Memory Bank → 2. Build → 3. Deploy → 4. Update Memory Bank
Step 1: Check Memory Bank
Check for memory-bank.md in the project root. If found, read it for the project name and environment. If not found, proceed — the project may have been created without the plugin.
Step 2: Build
npm run build
If the build fails:
- TS6133 (unused import): Remove the unused import and retry.
- Other TypeScript errors: Report the error with the file and line number and stop. Do not deploy a broken build.
Verify dist/ exists with index.html before continuing.
Step 3: Deploy
Ask the user: "Ready to deploy to [environment name]? This will update the live app." Wait for explicit confirmation before proceeding.
Resolve the CLI first (see cli-binary.md): run as
$PA app push(npx --no-install pa …), never a barepa. Onpower-apps-only projects, translate topower-apps push.
pa app push
Capture the app URL from the output if present.
If deploy fails, report the error and stop — do not retry silently. Common fixes:
- Auth error / token expired →
pa auth logout(orpower-apps logoutonpower-apps-only projects), then retry — the CLI will re-prompt browser login. - Environment mismatch → update
environmentIdinpower.config.jsonto the correct value and retry.
Step 4: Update Memory Bank
If memory-bank.md exists, update:
- Last deployed timestamp
- App URL (if captured)
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 · 61 lines · 32 tokens per session scan A eec293714b32
deploy is a skill published in the GitHub repository microsoft/power-platform-skills (1,016 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 498 once invoked, about $0.0001 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 2026-08-30.
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.
qector-services
QECTOR service surfaces: REST (FastAPI / Flask), gRPC, MCP stdio, Prometheus metrics exporter (manual 17.4). Covers the Provisional status, the production checklist (manual 24.1), the request-size cap, the bearer-token check, the per-client rate limit, the strict decoder-type enum, the deployment modes (manual 24…
ash-framework
Ash Framework — resources, actions, policies, aggregates, calculations, AshPhoenix.Form, LiveView, migrations. Use when generating resources via mix ash.codegen, editing changes, checks, types, validations, or domain code interfaces.
liveview-patterns
Build LiveView: async data (assignasync), PubSub (check connected?), phx-change events, form components/modals/uploads, streams for lists, livepatch. Use when handling interactions, debugging events, or tracking Presence.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
oban
Use when writing, scheduling, testing or debugging Oban jobs, even for a how-to question: workers, cron, retries, unique jobs, queues, Pro Workflow/Batch. Load it before touching job code; it holds the job rules.