- Home
- Skills
- Business & Operations
- Meeting Contradiction Detector
Meeting Contradiction Detector
Detect conflicts between meeting notes and chat logs to stop scope creep and "invisible" decision changes.
$9
Works with the AI Agents you already use
Meeting Contradiction Detector
Example session with this skill installed
Compare these meeting notes: 'Agreed on PostgreSQL for the database, Sarah to lead' with this Slack log: 'Sarah: Actually let's use MongoDB, it's faster for this. Dave: Sounds good.'
- Read your context and instructions
- Compiled the meeting contradiction detector
Analyzed 1 meeting transcript and 1 chat log. Found 2 discrepancies regarding database architecture and formal decision-making.
[Contradiction Analysis Report]
✅ Aligned Items:
- Sarah remains the lead for the database implementation.
⚠️ Contradictions & Drift Detected:
1.
Direct Contradiction: The team switched from a relational to a non-relational database without updating formal project documentation.
- Receipts: Source A ("Agreed on PostgreSQL for the database") vs. Source B ("Sarah: Actually let's use MongoDB... Dave: Sounds good.")
- Suggested Resolution: Ask the team: "Are we officially pivoting to MongoDB as suggested in Slack, or should we stick to the PostgreSQL decision from the formal meeting?"
- Decision Authority Drift: A architectural change was made via a casual chat message rather than a formal review.
- Receipts: Source A ("Agreed on...") vs. Source B ("Sounds good.")
- Suggested Resolution: Ask Dave: "Does your 'sounds good' in Slack constitute a formal approval of the architecture change, or do we need a quick sync?"
📋 Final Action Item Summary:
- Sarah to confirm database selection (PostgreSQL vs MongoDB) by EOD.
- Update the system architecture diagram once the database type is finalized.
Next steps
- Post the suggested resolution questions in the project Slack channel.
- Update the
ARCHITECTURE.mdfile once the team confirms the choice. - Attach this report to the Jira ticket to document the pivot.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Teams suffer from verbal amnesia and "invisible" scope creep. Decisions made in meetings often drift in Slack threads or get silently reassigned, leading to wasted dev hours and finger-pointing during sprint reviews.
What it does
- Extracts core commitments, decisions, and action items from transcripts and chat logs.
- Cross-references multiple sources to flag direct contradictions in tech stack or architecture choices.
- Identifies silent owner changes where tasks migrate between team members without formal handoffs.
- Detects timeline drift and unauthorized scope additions by comparing current notes against project briefs.
- Generates "receipts" using direct quotes to provide undeniable evidence of discrepancies.
Why this beats prompting it yourself
General LLMs often try to "harmonize" conflicting information or pick one source as correct by default. This skill is hardcoded to be adversarial, specifically hunting for friction and providing the exact quotes needed to resolve the dispute without manual scrolling.
Use cases
- Reviewing Monday's meeting transcript against Wednesday's Slack "recap" to find drift.
- Auditing a project brief against the latest sprint planning notes for scope creep.
- Resolving "who said what" disputes by extracting timestamped evidence from multiple documents.
Requires text-based inputs like transcripts, chat exports, or markdown notes. Cannot join live calls or access private Slack channels directly without the user pasting the content.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
Permissions
No special permissions declared or detected