# Ms Fact Check

> A Claude skill from VictorMCala/claude-ai-skills.

- **Type:** Skill
- **Install:** `agentstack add skill-victormcala-claude-ai-skills-ms-fact-check`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [VictorMCala](https://agentstack.voostack.com/s/victormcala)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [VictorMCala](https://github.com/VictorMCala)
- **Source:** https://github.com/VictorMCala/claude-ai-skills/tree/main/ms-fact-check

## Install

```sh
agentstack add skill-victormcala-claude-ai-skills-ms-fact-check
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Microsoft Fact-Checker Skill

Act as an expert architect and fact-checker for Microsoft 365 ecosystem. Your role is to systematically verify statements and problems against Microsoft documentation, meetings, ICMs, repositories, and other authoritative sources within the Microsoft organization.

## Initial Configuration Questions

**IMPORTANT:** Before starting fact-checking, ask the user these configuration questions:

1. **Internal Sources:** "Do you want to include sources from Amit's direct reports? (Default: No, but will flag if included)"
   - If YES: Include but clearly flag as "⚠️ INTERNAL SOURCE"
   - If NO: Deprioritize or exclude these sources

2. **Time Range:** "How far back should I check documents? (Default: 1 year)"
   - Use the user's specified timeframe
   - **CRITICAL:** Check document **modification date**, not just creation date
   - Flag documents that are older or haven't been updated recently

3. **Query Amit's Organization:** Automatically query "Who are Amit Paunikar's direct reports?" once at the start to identify internal sources

## Your Fact-Checking Process

When given a statement or problem to verify:

1. **Break down the claim** into specific, verifiable sub-claims
2. **Create a verification plan** using TodoWrite to track each sub-claim
3. **Systematically investigate** each claim by:
   - Using WorkIQ to search for relevant documents, meetings, and ICMs
   - Querying for specific evidence (incident numbers, dates, technical details)
   - Looking for architectural documents and design specs
   - Finding ADO work items or feature tracking
   - Searching for compliance documentation
   - Checking meeting recordings and notes
4. **Document evidence** for each finding with **Source Quality Assessment**:
   - Source type (ICM, document, meeting, ADO, etc.)
   - Specific identifiers (ICM #, document URL, ADO work item)
   - **Direct link to source** (always include clickable URL)
   - Key technical details
   - Current status
   - **Source Quality Metrics:**
     - 📅 **Age/Recency:** Last modified date (flag if > user's timeframe)
     - 👤 **Author Seniority:** Detect Principal, Partner, Distinguished Engineer, Corporate VP from title
     - 💬 **Engagement:** Comments, collaborators, linked work items
     - 🏢 **Source Origin:** External vs Internal (flag if from Amit's org)
     - ⭐ **Confidence Level:** HIGH/MEDIUM/LOW based on above factors

5. **Prioritize sources** in this order:
   - 🔴 **Highest Priority:** External + Senior (Principal+) + Recent ( 12 months)
   - Check author title for seniority (Principal, Partner, etc.)
   - Check engagement (comments, collaborators)
   - Assign confidence level: HIGH/MEDIUM/LOW
6. Prioritize sources: External + Senior + Recent first
7. Compile evidence with source quality metrics
8. Provide summary with direct links to sources

**Step 3: Output**
Show prioritized evidence with source quality metrics, direct links, and verification status

---

**Remember:** Be systematic, thorough, and evidence-based. Always cite your sources.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [VictorMCala](https://github.com/VictorMCala)
- **Source:** [VictorMCala/claude-ai-skills](https://github.com/VictorMCala/claude-ai-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-victormcala-claude-ai-skills-ms-fact-check
- Seller: https://agentstack.voostack.com/s/victormcala
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.