m365-auditor
Design Microsoft 365 audit log query specifications and compliance reporting for FINRA, state insurance examiner, and internal audit requirements in financial services tenants.
What this skill does
# M365 Auditor
Produce a Microsoft 365 audit specification that covers audit log query design, report templates, alert rules, and retention configuration for financial services compliance requirements. The output must be ready for use by a Microsoft Purview administrator and IT security team.
## Audit Log Sources and Enablement
Verify and document audit enablement status for each workload:
| Workload | Audit Source | Enable Command |
|----------|-------------|----------------|
| Exchange Online | Microsoft Purview Audit | Enabled by default for E3/E5 |
| SharePoint Online | Microsoft Purview Audit | Enabled by default |
| Microsoft Teams | Microsoft Purview Audit | Enabled by default |
| Azure AD / Entra ID | Microsoft Purview Audit | Enabled by default |
| Power Platform | Microsoft Purview Audit | Must be enabled per environment |
| Microsoft Defender for O365 | Defender portal | Separate configuration |
**Audit log retention tier**:
| License | Retention Period | Coverage |
|---------|-----------------|----------|
| E3 or Business Premium | 90 days | Standard audit |
| E5 | 1 year | Standard + advanced audit |
| Microsoft Purview Audit (Premium) add-on | 1 year or 10 years | Advanced audit events |
For FINRA-regulated broker-dealers: 10-year retention add-on is required for broker communications (FINRA Rule 17a-4). For state-regulated insurance agencies: confirm state-specific retention requirements (typically 5-7 years). Document the license tier and resulting retention period for this client.
## Key Audit Event Categories
### User Authentication and Identity
Events to capture and review:
| Operation | Description | Risk Signal |
|-----------|-------------|-------------|
| UserLoggedIn | Successful sign-in | Baseline — look for anomalous locations |
| UserLoginFailed | Failed sign-in | >5 failures = potential brute force |
| MFADenied | MFA challenge denied | User denying legitimate login |
| UserPasswordChanged | Password change | Verify it was user-initiated |
| Set-MsolUserPassword | Admin password reset | Privilege action — must be logged |
| Add member to role | Role assignment | Any admin role grant requires review |
| Remove member from role | Role removal | Ensure it was authorized offboarding |
### Document Access and Sharing
| Operation | Description | Risk Signal |
|-----------|-------------|-------------|
| FileAccessed | File opened or downloaded | Baseline — look for bulk access |
| FileDownloaded | File downloaded to device | >50 files in 1 hour = alert |
| SharingInvitationCreated | External share initiated | Any sharing outside approved domains |
| AnonymousLinkCreated | Anyone link created | Should be blocked by policy — if seen, alert |
| FileDeleted | File deleted | Bulk deletion (>20 files) = alert |
| FileModified | File edited | Useful for content audit trails |
### Email Activity
| Operation | Description | Risk Signal |
|-----------|-------------|-------------|
| Send | Email sent | High volume from single user |
| SendAs | Email sent as another identity | Any occurrence warrants review |
| HardDelete | Email permanently deleted | During investigation period = alert |
| MessageForwardingRuleEnabled | Auto-forward rule created | External auto-forward = data exfiltration risk |
| New-InboxRule | New inbox rule | Check destination for external address |
### Teams Activity
| Operation | Description | Risk Signal |
|-----------|-------------|-------------|
| TeamCreated | New team created | Verify naming policy compliance |
| MemberAddedToTeam | Member added | External guest added = review |
| ChatMessageSent | Chat message | Keyword detection for compliance |
| FileUploadedToChannel | File uploaded | Large file uploads |
| MeetingRecordingCreated | Recording started | Verify recording policy compliance |
### Admin Configuration Changes
| Operation | Description | Risk Signal |
|-----------|-------------|-------------|
| Set-TransportRule | Mail flow rule changed | All changes require change ticket |
| Set-AdminAuditLogConfig | Audit config changed | Attempt to disable auditing = critical alert |
| New-RoleGroupMember | Admin role granted | Privileged access change |
| Set-RetentionCompliancePolicy | Retention policy changed | Compliance risk |
## Query Design Templates
Provide ready-to-use Search-UnifiedAuditLog PowerShell query templates.
**Weekly security summary query**:
```powershell
# Run every Monday for prior week
$StartDate = (Get-Date).AddDays(-7).ToString("MM/dd/yyyy")
$EndDate = (Get-Date).ToString("MM/dd/yyyy")
# Authentication failures
Search-UnifiedAuditLog -StartDate $StartDate -EndDate $EndDate `
-Operations "UserLoginFailed" `
-ResultSize 1000 |
Select-Object -ExpandProperty AuditData |
ConvertFrom-Json |
Select-Object CreationTime, UserId, Operation, ClientIPAddress, UserAgent |
Export-Csv ".\weekly-auth-failures.csv" -NoTypeInformation
# External sharing events
Search-UnifiedAuditLog -StartDate $StartDate -EndDate $EndDate `
-Operations "SharingInvitationCreated","AnonymousLinkCreated" `
-ResultSize 1000 |
Select-Object -ExpandProperty AuditData |
ConvertFrom-Json |
Select-Object CreationTime, UserId, Operation, ObjectId, TargetUserOrGroupName |
Export-Csv ".\weekly-external-sharing.csv" -NoTypeInformation
# Admin role changes
Search-UnifiedAuditLog -StartDate $StartDate -EndDate $EndDate `
-Operations "Add member to role.","Remove member from role." `
-ResultSize 500 |
Select-Object -ExpandProperty AuditData |
ConvertFrom-Json |
Select-Object CreationTime, UserId, Operation, ModifiedProperties |
Export-Csv ".\weekly-role-changes.csv" -NoTypeInformation
```
**On-demand examination evidence query** (for regulatory examiner requests):
```powershell
# Query specific user activity for examination period
param(
[string]$UserEmail,
[string]$StartDate, # MM/dd/yyyy
[string]$EndDate # MM/dd/yyyy
)
$Operations = @(
"Send","FileAccessed","FileDownloaded","FileDeleted",
"UserLoggedIn","UserLoginFailed","SharingInvitationCreated"
)
Search-UnifiedAuditLog -StartDate $StartDate -EndDate $EndDate `
-UserIds $UserEmail `
-Operations $Operations `
-ResultSize 5000 |
Select-Object -ExpandProperty AuditData |
ConvertFrom-Json |
Select-Object CreationTime, UserId, Operation, ObjectId, ClientIPAddress, UserAgent |
Sort-Object CreationTime |
Export-Csv ".\examination-evidence-$UserEmail.csv" -NoTypeInformation
```
## Report Templates
### Weekly Security Summary
Delivered every Monday. Sections:
1. Authentication overview: Total sign-ins, failed sign-ins by user, MFA events, new IP addresses
2. Sharing activity: External shares initiated, anonymous links (should be zero), external guests added to Teams
3. Privilege changes: Admin role grants and removals, policy changes
4. Anomaly highlights: Any event exceeding alert thresholds from the prior week
5. Open items: Alerts from prior week requiring follow-up
### Monthly Compliance Report
Delivered first business day of each month. Sections:
1. User activity summary: Active users, inactive users (>30 days no sign-in)
2. Data loss prevention: DLP policy match counts by policy, false positive rate
3. External collaboration: External users with active access, external shares, guest users added/removed
4. Retention compliance: Items subject to retention policies, holds applied
5. Admin activity log: All admin actions during the month
6. Incidents: Any security incidents, escalations, or exceptions granted
### Examination Evidence Package
On-demand, per examiner request. Contents:
1. Cover memo: Scope of request, date range, custodians included
2. Email activity export: All sent/received emails for specified users and period (Exchange audit log)
3. Document access log: All file access and sharing events for specified users
4. Communication archive: Teams chat export (requires Microsoft Purview eDiscovery)
5. Chain of custody statement: How data was extracted, who extracted it, what Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.