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 pcfgit 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/pcf)<a href="https://agentmods.dev/skills/microsoft/power-platform-skills/pcf"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/pcf/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/pcf"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/pcf.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00171 | $0.03403 |
| Opus 5.5 | $0.00068 | $0.01361 |
| Sonnet 5.5 | $0.00034 | $0.00681 |
| Haiku 4.5 | $0.00017 | $0.00340 |
Grade A, and why
pcf scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin check: Run
node "${PLUGIN_ROOT}/scripts/check-version.js"— if it outputs a message, show it to the user before proceeding.
PCF skill
Build, repair, upgrade, deploy, bind, verify and inventory Power Apps component framework controls. Run the work in the main conversation loop. Do not dispatch interactive authoring, approval, deploy consent, binding choices or browser-verification choices to a subagent.
Critical startup
- Set
PLUGIN_ROOTto the installedplugins/pcfdirectory. - Resolve interaction once:
node "${PLUGIN_ROOT}/scripts/resolve-interaction-mode.js" # Optional for automation: --non-interactive - In unattended mode, do not call
AskUserQuestion,EnterPlanModeorExitPlanMode. Use explicit request details and documented non-destructive defaults only; writeUnattended default: <question> → <answer> (<reason>)toworkflow-log.mdin the session working directory; halt on ambiguous environment, app/form/control identity or destructive choices.pcf-intent.json,pcf-plan.mdandworkflow-log.mdlive in that working directory.hooks/validate-write-safety.jsdetects a pcf session only frompcf-intent.jsonorpcf-plan.mdat or one level under the cwd;workflow-log.mdis not a session marker.--outmust be a new, empty subdirectory. Never write those session files into--outbefore scaffold runs — a non-empty directory is refused. - Suppressing a prompt never authorizes an environment write.
pcf-push.jsstill requires an explicit--envand prior consent recorded by the user or automation.
Routing
| User intent | Route |
|---|---|
| Build, fix, upgrade, deploy, bind, verify, inventory a PCF code component | Stay in /pcf:pcf. |
| Why a PCF control will not build, import, update or render | Stay in /pcf:pcf; start with ../../references/pcf-troubleshooting.md and the doctor output. |
| Whole custom page / generative page | Use /model-apps:genpage. |
| Whole model-driven app with tables/forms/views/pages | Use /model-apps:app-builder. |
| Use an existing control without code changes | Guide Maker binding and verification; do not scaffold. |
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.
- 4d ago First seen · 187 lines · 171 tokens per session scan A 0fac09240f80
pcf is a skill published in the GitHub repository microsoft/power-platform-skills (1,016 stars, last pushed today), licensed MIT. It adds 171 tokens to every session and 3,403 once invoked, about $0.0007 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 2026-10-14.
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.
benchmark
Local-only regression / benchmark skill for ui-clone-skills maintainers. Drives the standard ui-reverse-engineering pipeline against the canonical reference site (https://realfood.gov) and records AE/SSIM, iteration count, gate fail counts, and outcome to benchmark/history.csv so prompt / sub-doc / model-version drift…
ui-reverse-engineering
Clone or recreate a live website URL, page, or section as React + Tailwind with extracted DOM, CSS, assets, responsive layout, motion, and interactions. Use for live-URL implementation or fidelity repair; not capture-only or diff-only requests.
motherduck-create-dive
Create, edit, publish, share, or embed MotherDuck Dives using their React and SQL runtime.
ux-heuristics
Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "users are confused", "form usability", "navigation problems", "Nielsen heuristics", "cognitive walkthrough", or "is this easy to use". Also trigger when reviewing a design for usability issues, improving…
blue-ocean-strategy
Create uncontested market space using value innovation instead of competing head-to-head. Use when the user mentions "blue ocean", "red ocean", "strategy canvas", "ERRC framework", "value innovation", "non-customers", "buyer utility map", "the market is too crowded", "how do we stand out", or "escape the price war".…