summarize-meetings SKILL.md skillA
summarize-meetings from 2389-research/summarize-meetings is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add 2389-research/summarize-meetings/summarize-meetings@git:20260706.7e33712Pins git:20260706.7e33712 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- 2389-research/summarize-meetings
- Path
skills/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260706.7e33712, committed Jul 6, 2026
- First version recorded
- Mar 9, 2026
- Size
- 10,197 bytes
- Repository stars
- 15
- License
- MIT
Batch-processes a backlog of Granola meeting transcripts into structured Obsidian notes — summaries, People stubs, Concept notes, and wiki-links. Use when you have a pile of Granola meeting transcripts to summarize, process, or turn into Obsidian knowledge graph entries; or when asked to "summarize meetings", "process meetings", "meeting notes cleanup", or "extract insights from meetings".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Summarize Meetings
Process meeting transcripts from `Meetings/transcripts/` — extract people, action items, project ideas, blog ideas, knowledge graph connections, concepts, and general ideas. Populate the vault knowledge graph and generate rich summary files.
## Setup
Before running this skill, determine the absolute path to the Obsidian vault. Check the project's `CLAUDE.md` or user configuration, or ask the user: "What is the absolute path to your Obsidian vault?" There is no silent default.
All agent prompts in this skill use `{{VAULT_PATH}}` as a placeholder. Replace it with the actual vault path before dispatching any agent.
## Campaign Workflow
Processing works in **monthly batches**, most-recent month first. Each month follows this cycle:
1. Scan month (ls -lS)
2. Triage: check small/suspicious files
3. Identify skips vs substantive
4. Dispatch wave of agents (10-15)
5. Wait for returns
6. Dispatch remaining agents
7. All agents returned
8. Compile monthly report table
9. Post social media update
10. Next month or stop
### Step 1: Scan the Month
```bash
ls -lS "Meetings/transcripts/" | grep "YYYY-MM"
```
…Read the whole file at its exact version.
How to install
mdr add 2389-research/summarize-meetings/summarize-meetings@sha256:395221da8e39ea1cThe line at the top of this page pins the label git:20260706.7e33712, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_5j5oucsdlpy73qcx)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Mar 9, 2026 and Jul 6, 2026, about one every 119 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260706.7e33712 latest | 2026-07-06 | 7e33712 | 10,197 B | A | view · diff |
| git:20260309.6e7beea | 2026-03-09 | 6e7beea | 13,225 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10197 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
2389-research/summarize-meetings · 15 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5j5oucsdlpy73qcx GET https://markdownregistry.com/api/v1/resolve?ref=2389-research/summarize-meetings/summarize-meetings GET https://markdownregistry.com/api/v1/blob/395221da8e39ea1ceeba5183c6650a690b4ca6c4a714161dc5bbbc935d187131
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.