agentmods.dev

meeting-moments-library-builder-cowork

meeting-moments-library-builder-cowork is a skill for Claude Code, Codex from microsoft/cat-agent-skills. It costs 169 tokens per session (2,244 once invoked), scanned A, original, MIT.

A Microsoft 365 meeting-transcript tool that finds authorised meeting moments and builds a searchable library of verified items. It produces HTML, CSV, and JSON files for review or reuse.

In plain words
What is it for?
Use it to create libraries of how-tos, decisions, customer feedback, demo highlights, lessons learned, or onboarding moments from selected meetings.
Why use it?
It turns scattered transcript content into an organised record instead of leaving useful decisions, lessons, or customer comments buried in meetings. The review step helps check each captured moment.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

not rated 101repo +5 yesterday A scan 169 tokens original MIT

Good fit Use it to create libraries of how-tos, decisions, customer feedback, demo highlights, lessons learned, or onboarding moments from selected meetings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/microsoft/cat-agent-skills/meeting-moments-library-builder-cowork
View source ↗ microsoft/cat-agent-skills
About the project

microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.

microsoft/cat-agent-skills · 101 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add microsoft/cat-agent-skills --skill meeting-moments-library-builder-cowork
Clone the repo
git clone --depth 1 https://github.com/microsoft/cat-agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for meeting-moments-library-builder-cowork

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/meeting-moments-library-builder-cowork/github.svg)](https://agentmods.dev/skills/microsoft/cat-agent-skills/meeting-moments-library-builder-cowork)
Your own site
<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/meeting-moments-library-builder-cowork"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/meeting-moments-library-builder-cowork/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for meeting-moments-library-builder-cowork

Your own site · 80×15
<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/meeting-moments-library-builder-cowork"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/meeting-moments-library-builder-cowork.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 169 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,244 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00169 $0.02244
Opus 5.5 $0.00068 $0.00898
Sonnet 5.5 $0.00034 $0.00449
Haiku 4.5 $0.00017 $0.00224

Measured 10d ago against content hash be7c817055cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

meeting-moments-library-builder-cowork scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/build_library.py, scripts/parse_transcript.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

submissions/meeting-moments-library-builder-cowork/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meeting Moments Library Builder for Cowork

Find authorized Microsoft 365 meeting transcripts and turn them into a portable library of verified moments. The default workflow needs no Scout, MCP server, Dataverse table, tunnel, or deployed agent.

One durable outcome

Every completed run produces a reviewable library package:

  • meeting-moments-library.html — searchable, self-contained browser view;
  • meeting-moments-library.csv — easy import into Microsoft Lists or another system; and
  • meeting-moments-library.json — structured source of truth.

Do not finish with only a chat summary. Return the files unless the user cancels.

First turn

  1. Briefly explain that you will identify and verify moments, show a review table, and produce the three library files.
  2. Ask what the library should capture:
    • how-tos;
    • decisions;
    • customer voice;
    • demo highlights;
    • lessons learned;
    • onboarding moments; or
    • a custom type.
  3. If the user already specified the type, confirm it in one line instead of re-asking.
  4. Ask for the date range and meeting series, titles, organizers, or keywords to search. Offer transcript upload only as a fallback.

Read references/capture-types.md before applying a preset.

Runtime contract

Cowork default

  • Discover meetings first through the runtime's native Microsoft 365 meeting capabilities.
  • When available, use workiq_list_meetings for the chosen window, then workiq_list_meeting_transcripts and workiq_get_meeting_transcript for explicitly selected meetings.
  • Never scan an unbounded calendar. Use the user-approved date window and meeting filters.
  • Inputs may also arrive as chat attachments, pasted text, or Microsoft 365 work context.
  • Use attached .vtt, .srt, or .txt transcripts directly. If audio/video transcription is available in the runtime, it may be used; otherwise ask for captions or a transcript.
  • Write intermediate files to the runtime working area and return final files as downloadable attachments.
  • Upload to SharePoint or OneDrive only when the user explicitly requests a destination and confirms the exact files to upload.

Read the full file on GitHub · 268 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 268 lines · 169 tokens per session scan A be7c817055cc

Subscribe to this mod's changes

meeting-moments-library-builder-cowork is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 169 tokens to every session and 2,244 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-29.

DocumentsProductivity
Related

meeting-moments-library-builder-cowork compared with skills from other repositories

meeting-moments-library-builder-cowork next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
meeting-moments-library-builder-coworkmicrosoft/cat-agent-skillsSkill101yesterdayMITA169Claude Code, Codex
orbit-notionnexu-io/open-designSkill107ktodayApache-2.0A117Claude Code, Codex
gogopenclaw/openclawSkill394ktodayMITA20Claude Code, Codex
boxNousResearch/hermes-agentSkill262ktodayMITA14Claude Code, Codex
feishuHmbown/CodeWhaleSkill41ktodayMITA33Claude Code, Codex
material-organizerOrkas-AI/OrkasSkill9.1ktodayMITA3Claude Code, Codex
recipe-save-email-attachmentsgoogleworkspace/cliSkill32k5d agoApache-2.0A20Claude Code, Codex