- Home
- Skills
- Agents & Orchestration
- Meeting Follow Through Kit
Meeting Follow Through Kit
Turn meeting transcripts into structured action registers, decision logs, and source-linked follow-up emails.
$5
Works with the AI Agents you already use
Meeting Follow Through Kit
Example session with this skill installed
Here is the transcript from the Q3 Planning sync. Reconcile this against the previous register. Previous: ID-101 (Mobile API, Sarah, June 30). Notes: Sarah finished the API. Dev decided to delay the UI.
- Read your context and instructions
- Compiled the meeting follow through
I have processed the Q3 Planning sync notes and reconciled them with your previous register. Sarah's API task is marked as completed, and the UI delay has been logged as a new decision with a status update.
Meeting Follow-through Output
Source Index
| ID | Item Type | Source Reference |
|---|---|---|
| ID-101 | Action | "Sarah finished the API" |
| ID-102 | Decision | "Dev decided to delay the UI" |
Action Register
| ID | Description | Owner | Deadline | Status |
|---|---|---|---|---|
| ID-101 | Mobile API Development | Sarah | June 30 | Completed |
| ID-103 | UI Development | Unknown | Unknown | Blocked/Delayed |
Decision Log
| ID | Decision Made | Rationale |
|---|---|---|
| D-001 | Delay UI development phase | Development team consensus during Q3 sync |
Open Questions
- Who is the new owner for the delayed UI phase?
- What is the revised deadline for the UI milestone?
Follow-up Email Draft
Subject: Recap: Q3 Planning Sync - Decisions and Actions
Hi Team,
Following our Q3 Planning session, here is the summary of outcomes:
Decisions:
- We have decided to delay the UI development phase.
Key Actions:
- Completed: Mobile API Development (Sarah).
- Pending: Re-assigning ownership and setting a new timeline for the UI phase.
Please confirm the revised UI dates by EOD Thursday.
Best regards,
[User]
Next steps
- Assign a new owner to ID-103 (UI Development).
- Clarify the specific "UI delay" duration to update the Decision Log.
- Send the drafted recap email to the project distribution list.
Connects securely to your tools. The creator never sees your data.
About this skill
Turn messy meeting transcripts and notes into structured execution data. This skill eliminates the manual labor of tracking who promised what, which decisions were finalized, and which tasks remain stagnant. It treats meeting records as raw data, extracting explicit commitments while filtering out conversational noise and untrusted transcript instructions.
What it does
- Source Indexing maps every extracted item back to the original notes for auditability.
- Decision Logging captures finalized agreements with stable IDs to prevent context loss.
- Action Registration tracks owners, deadlines, and dependencies with strict evidence-based assignment.
- State Reconciliation compares new notes against prior registers to flag progress, blockers, or items with no update.
- Conflict Flagging identifies ambiguous dates, unknown owners, and contradictory records for human resolution.
How it works
- Capture a new meeting by providing notes or a transcript to identify date, audience, and commitments.
- Reconcile against a previous action register to carry forward IDs and update statuses.
- Correct the record using authorized overrides for owners, dates, or decision values.
- Review the generated source index, decision log, action register, and draft follow-up email.
Frameworks & tools
This tool is platform-agnostic and works with Markdown, plain text transcripts, and CSV-based action logs.
Why this beats prompting it yourself
Generic prompts often hallucinate task owners or treat every mentioned name as an assignee. This skill uses strict evidence rules, preserves dependencies, and maintains stable IDs across recurring meetings to ensure your tracking doesn't break over time.
Use cases
- Recurring syncs to carry forward pending actions and log new decisions.
- Transcript cleanup to filter out "assistant-facing" transcript errors and casual banter.
- Change management to log authorized corrections to project deadlines and ownership.
- Stakeholder reporting via concise, neutral follow-up email drafts.
Known limitations
Does not perform external actions like sending emails or scheduling invites. Requires manual interpretation of relative dates if no anchor date is provided.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Cannot send emails or sync with calendars directly. Requires anchor dates to resolve relative deadlines. Does not infer task owners without explicit evidence.
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 buying a skill.
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 7 days ago