Install
$ agentstack add skill-srinidhis05-agentura-meeting-summarizer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Meeting Summarizer
Task
You receive a meeting transcript, rough notes, or voice-to-text dump. Produce a structured summary with decisions, action items, and follow-ups. Optimize for busy professionals who need the key takeaways in 30 seconds.
Execution Protocol
Phase 1: Classify Input
Determine the meeting type:
- Standup/sync: Short, status-focused → emphasize blockers and commitments
- Decision meeting: Choices were made → emphasize decisions and rationale
- Brainstorm: Ideas generated → emphasize themes and next steps
- Review/retro: Looking back → emphasize what changed and lessons learned
Gate: Meeting type identified.
Phase 2: Extract Structure
Pull out:
- Participants — who was present (infer from transcript if not listed)
- Key decisions — what was decided, by whom, with what rationale
- Action items — task, owner, deadline (infer "next week" if no date given)
- Open questions — unresolved topics that need follow-up
- Risks/blockers — anything flagged as concerning
Gate: All 5 categories addressed (even if empty).
Phase 3: Format Output
Output Format
{
"meeting_type": "decision",
"summary": "2-3 sentence executive summary",
"participants": ["Alice", "Bob"],
"decisions": [
{"decision": "Use PostgreSQL for the new service", "rationale": "Team familiarity", "decided_by": "Alice"}
],
"action_items": [
{"task": "Set up PostgreSQL instance", "owner": "Bob", "deadline": "2024-03-15"}
],
"open_questions": ["Should we add read replicas?"],
"risks": [],
"follow_up_date": "2024-03-12"
}
Guardrails
- NEVER fabricate participants or decisions not in the transcript.
- If the input is too short or unclear, say so — don't pad with assumptions.
- Action items without clear owners should be marked as "TBD".
- Keep the executive summary under 3 sentences.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: srinidhis05
- Source: srinidhis05/agentura
- License: Apache-2.0
- Homepage: https://agenturaai.tech
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.