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 add-cloud-flowgit 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-cloud-flow)<a href="https://agentmods.dev/skills/microsoft/power-platform-skills/add-cloud-flow"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/add-cloud-flow/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/add-cloud-flow"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/add-cloud-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
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 →
- high Prompt Injection · line 79 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 237 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Rogue Agent · line 355 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Prompt Injection · line 611 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 11 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 616 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.
- medium Excessive Agency · line 662 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 | $0.00091 | $0.08429 |
| Opus 5.5 | $0.00036 | $0.03372 |
| Sonnet 5.5 | $0.00018 | $0.01686 |
| Haiku 4.5 | $0.00009 | $0.00843 |
Grade A, and why
add-cloud-flow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 709 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin check: Run
node "${PLUGIN_ROOT}/scripts/check-version.js"— if it outputs a message, show it to the user before proceeding.
Add Cloud Flow
Connect one or more Power Automate cloud flows to a Power Pages code site, or wire already-registered flows into additional pages/components. For new flows this skill:
- Creates the
adx_cloudflowconsumermetadata YAML in.powerpages-site/cloud-flow-consumer/ - Assigns web roles based on the flow's scenario and target audience
- Generates client-side TypeScript/JavaScript service code to trigger the flow with CSRF authentication
For already-registered flows, the skill skips metadata and role creation and goes straight to client-side integration — wiring the existing flow into new UI locations.
Core Principles
- Multiple flows in one run: The user can add several flows at once. All flows are planned together and implemented together before asking for deployment.
- Ask before acting: Present a full HTML plan (all flows, roles, reasoning) before creating any files.
- Web roles drive access: Every flow must have at least one web role. Anonymous Users role is valid but must be confirmed.
- Scenario determines roles: Understand what each flow does and who triggers it before picking roles.
- Use TaskCreate/TaskUpdate: Track all phases upfront before starting any work.
- Preserve site integrity: Before wiring a flow into a page or component, read
${PLUGIN_ROOT}/references/site-modification-integrity.md; localize every new visible state when configured and keep the UI bidirectional and expansion-safe.
Prerequisites:
- An existing Power Pages code site with
.powerpages-sitedeployed- PAC CLI authenticated (
pac auth whomust succeed)- Azure CLI authenticated (
az login --allow-no-subscriptionsworks whether or not your account has an Azure subscription — Dataverse and Power Platform tokens are AAD-scoped)
Initial request: $ARGUMENTS
Workflow
- Verify Prerequisites — Locate the project, confirm
.powerpages-siteexists, inventory web roles and existing flows - List Available Flows — Fetch flows from the Power Automate Flow RP API
- Select Flows & Understand Scenarios — User picks one or more flows; determine scenario and audience for each
- Determine Web Roles — Propose minimum roles per flow with reasoning
- Review Plan — Render HTML plan for all flows; get user approval
- Create Metadata — Write
.cloudflowconsumer.ymlfor each flow; create missing web roles first - Client-Side Integration — Generate typed service code to call each flow from the frontend
- Verify & Summarize — Validate all YAMLs, record skill usage, offer deployment
What ships with it
4 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.
- 9d ago Changed · +13 lines 7766018f8ec8
- 1mo ago First seen · 696 lines · 91 tokens per session scan A 106103c2381c
add-cloud-flow is a skill published in the GitHub repository microsoft/power-platform-skills (1,021 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 8,429 once invoked, about $0.0004 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
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.
deploy
Elixir/Phoenix deployment patterns — Dockerfile, fly.toml, runtime.exs, mix release, rel/ overlays. Use when configuring Fly.io, Docker, CI/CD, health checks, or production migrations.
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.
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.
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.
perf
Use when anything in a Phoenix app is slow, times out, or uses too much memory, even if the cause looks obvious. Load it before analyzing or fixing: it runs measured Ecto, LiveView and OTP checks and ranks fixes.