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 edit-offline-profilegit 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/edit-offline-profile)<a href="https://agentmods.dev/skills/microsoft/power-platform-skills/edit-offline-profile"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/edit-offline-profile/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/edit-offline-profile"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/edit-offline-profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 Tool Misuse · line 165 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 7 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 MCP Rug Pull · line 46 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00035 | $0.03305 |
| Opus 5.5 | $0.00014 | $0.01322 |
| Sonnet 5.5 | $0.00007 | $0.00661 |
| Haiku 4.5 | $0.00003 | $0.00331 |
Grade A, and why
edit-offline-profile 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 18d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared instructions: shared-instructions.md — read first.
References:
- dataverse-offline-api.md §4 / §7 — POST item + PATCH selectedcolumns
- offline-profile-reconciliation.md — refreshing the
schemaColumnsbaseline after a column edit
Edit Offline Profile
Re-run a single piece of an existing profile — change one table's row scope, update the column list, adjust sync frequency, or rename the profile. Avoids the cognitive cost of walking the full /setup-offline-profile wizard for a one-line change.
Scope: existing profile (read from <working_dir>/offline-profile.json or
--profile-id); edits at the table-item granularity. To ADD a new table return to
the owner for /add-table-to-offline-profile; deleting an entire profile is
outside this helper's scope, not an automatic recovery.
Invocation context and root binding
This internal helper is always a child invocation. Before any project read or
command, execute app-working-directory.md.
Require the owner's absolute working_dir; --working-dir, when supplied, must
identify that same native-canonical root. Missing, relative, or conflicting root
context returns NEEDS_CONTEXT before project access; an inaccessible directory
is BLOCKED. Never use the launch cwd or introduce another root resolver.
Receive MOBILE_APP_ORCHESTRATING=1, orchestrator, working_dir, phase,
approved_scope, and supplied answers from the owner. Preserve the selected
environment ID/URL/tenant, profile ID, table allowlist, item IDs, and exact
scope/column/sync/name/description changes. Missing or conflicting scope returns
NEEDS_CONTEXT, not another environment/profile/table selection. The marker is
not approval: schema approval alone does not authorize profile edits, publication,
deletion, or membership edits. Retain Step 3's single confirm unless supplied
answers already approve that same current offline change.
For --plan-only or a planning-phase handoff, return the current/proposed diff
after read-only discovery and STOP before Apply, PATCH, publication, or artifact
writes. A gate response cannot lift proposal-only mode.
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.
- 18d ago Changed · +114 lines 63b7f786d6ac
- 19d ago Changed 3480bc881548
- 1mo ago Changed e5e4f8cc2c74
- 1mo ago First seen · 167 lines · 35 tokens per session scan A b45e6572140b
edit-offline-profile is a skill published in the GitHub repository microsoft/power-platform-skills (1,064 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 3,305 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.
ios-hig-design
Design native iOS interfaces following Apple Human Interface Guidelines. Use when the user mentions "iPhone app", "iPad layout", "SwiftUI", "UIKit", "Dynamic Island", "safe areas", "HIG compliance", "SF Symbols", "haptic feedback", "iOS accessibility", "make my app feel native", or "follow Apple design guidelines".…
fec-pwa-implementation
A guide for adding Progressive Web App features to a website. A Progressive Web App, or PWA, is a website that can be installed like an app and can offer limited offline use through a web app manifest and a service worker.
validate-mobile
Run a Maestro flow on an explicitly selected iOS or Android device and report behavioral evidence.
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…
eng-unity-mobile-optimization
Mobile-specific Unity optimization patterns for memory, battery, thermal, and performance.