New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Vexa Meetings

by Vexa-ai in Vexa-ai/vexa

Sends a Vexa bot into a meeting, follows the live transcript and writes meeting notes with speakers, decisions and action items into Obsidian, Notion or Markdown.

Apache-2.0Auto-check passedProductivity & Automation

Install Vexa Meetings

skills CLI
$ npx skills add Vexa-ai/vexa --skill vexa-meetings -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Vexa-ai/vexa vexa-meetings --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Vexa-ai/vexa.git skills-src && mkdir -p .claude/skills && cp -r skills-src/clients/claude-plugin/skills/meetings .claude/skills/vexa-meetings && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vexa-meetings
GitHub stars
2.9k
Token cost
~631 tokens
SKILL.md length
318 words
Files
2
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

Sends a Vexa bot into a meeting, follows the live transcript and writes meeting notes with speakers, decisions and action items into Obsidian, Notion or Markdown.

  • Works in 4 steps: parse_meeting_link(meeting_url) →… → request_meeting_bot(meeting_url). A… → get_meeting_transcript(platform,… → …
  • Sending a bot to a video call and following its transcript
  • SKILL.md covers Send a bot to a call, Write a meeting into the…, Search across meetings and Make the data durable, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill drives the connected Vexa MCP server. It starts with whats_waiting, parses a meeting link into a platform and meeting id, requests a bot (a person in the call must admit it) and reads the transcript while the meeting runs, using since_index to fetch only new segments, then stops the bot when the call is over.

To file a meeting, it finds it with list_meetings, reads the transcript segments and writes one dated note per meeting in your existing format, with title, participants from the speaker labels, a short summary, decisions, action items with owners and the transcript or a link to it. Names are never guessed. search_transcripts returns ranked snippets for questions like what was decided, and annotate_meeting stores titles and metadata such as a CRM id for later filtering. speak_in_meeting is used only when you ask for exact words, since everyone hears it.

When your agent uses it

  • Sending a bot to a video call and following its transcript
  • Filing a meeting into Obsidian or Notion with action items
  • Searching past meetings for what was decided
  • Tagging meetings with a ticket or CRM id for later lookup

Example prompts

  • “Send a bot to my call at this Google Meet link and tell me when it is admitted.”
  • “Write yesterday's product sync into my Obsidian notes with decisions and action items.”
  • “Search my meetings for what we decided about the pricing change.”

Requirements

  • The Vexa MCP server connected to your agent

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. parse_meeting_link(meeting_url) → platform + native_meeting_id.
  2. request_meeting_bot(meeting_url). A human in the call must admit the bot; expect a delay between requested and active.
  3. get_meeting_transcript(platform, native_meeting_id) while the meeting runs. Pass since_index to read only what is new. A meeting that is…
  4. stop_bot(platform, native_meeting_id) when done.

What it can do on your machine

Read from SKILL.md and the folder at commit f1a62fb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vexa Meetings loads about 631 tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 318 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~631

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Vexa-ai/vexa at commit f1a62fb, republished under its Apache-2.0 licence (© Vexa-ai). 318 words, ~631 tokens.

Download SKILL.mdSave it as .claude/skills/vexa-meetings/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
vexa-meetings
description
Work with the user's meetings through the Vexa MCP tools — send a bot to a call, follow the transcript while it runs, and write meetings into their notes (Obsidian, Notion, plain markdown) with speakers and action items. Use whenever the user mentions a meeting, a call, a transcript, meeting notes, or asks what was said.

Vexa meetings

The vexa MCP server is connected. Start with whats_waiting — it says what the user's Vexa needs right now.

Send a bot to a call

  1. parse_meeting_link(meeting_url) → platform + native_meeting_id.
  2. request_meeting_bot(meeting_url). A human in the call must admit the bot; expect a delay between requested and active.
  3. get_meeting_transcript(platform, native_meeting_id) while the meeting runs. Pass since_index to read only what is new. A meeting that is active with zero segments usually means the bot is not admitted yet or nobody has spoken.
  4. stop_bot(platform, native_meeting_id) when done.

Every tool returns platform + native_meeting_id; feed one tool's output straight into the next.

Write a meeting into the user's notes

When asked to sync, log, or file a meeting:

  • list_meetings (filters: status, platform, metadata) to find it; get_meeting_transcript for the segments; get_meeting_participants is not a tool — participants come from the segments' speaker names.
  • Write one note per meeting, dated, in the user's existing format if there is one (look at a recent note first). Include: title, date, participants (from speaker labels), a short summary, decisions, action items with owners, and the transcript or a link to it. Keep speaker labels as they are — do not guess names the transcript does not carry.
  • Ask before writing outside the folder the user named.

Search across meetings

search_transcripts returns ranked snippets of what was said, not whole transcripts. Use it for "what did we decide about X", then open the meeting for context.

Make the data durable

annotate_meeting attaches a title and metadata (a CRM id, a ticket, tags). Anything you put there is findable later with list_meetings(metadata_filter=...). If you learn something durable about a meeting, write it back.

Do not

  • Do not call speak_in_meeting unless the user asked for that exact thing to be said. It is audible to everyone present and irreversible.
  • Do not read a meeting's meetings_failed-style counters as reliability; a meeting ends in many states that are not errors.

© Vexa-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in clients/claude-plugin/skills/meetings of Vexa-ai/vexa.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit f1a62fb

Compare with similar skills

Vexa Meetings next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vexa Meetings compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vexa Meetings this skillVexa-ai/vexa2.9k—~631Automated safety check: PassApache-2.0
ComposioComposioHQ/composio30k1 repos~1.7kAutomated safety check: PassMIT
Claap Weekly RecapOthmane-Khadri/YALC-the-GTM-operating-system318—~5.4kAutomated safety check: PassMIT
Pmcoreyhaines31/makerskills851—~2.2kAutomated safety check: PassMIT
Granolawin4r/MuseAI-Skills3431 repos~805Automated safety check: PassNone
Qmdbreferrari/obsidian-mind5k—~1.7kAutomated safety check: PassMIT

Similar skills

  • Composio

    ComposioHQ/composio

    Route and complete Composio work across Composio For You and Composio Platform.

    30k GitHub starsUsed in 1 repo~1.7k tokens
    Productivity & AutomationAuto-check passed

  • Claap Weekly Recap

    Othmane-Khadri/YALC-the-GTM-operating-system

    Turns a week of Claap-recorded sales calls into action items and focus blocks on a Notion Kanban, delivered with a Slack summary.

    318 GitHub stars~5.4k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed

  • Pm

    coreyhaines31/makerskills

    When you want to manage projects across your businesses using a kanban + Eisenhower methodology.

    851 GitHub stars~2.2k tokensUpdated 2 days ago
    Productivity & AutomationAuto-check passed

  • Granola

    win4r/MuseAI-Skills

    Search and read Granola meeting notes and transcripts through Granola's OAuth-backed MCP server.

    343 GitHub starsUsed in 1 repo~805 tokens
    Productivity & AutomationAuto-check passed

  • Qmd

    breferrari/obsidian-mind

    Search the vault using QMD semantic search. An agent skill from breferrari/obsidian-mind.

    5k GitHub stars~1.7k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed

  • Swarmvault

    swarmclawai/swarmvault

    Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval…

    710 GitHub stars~6.1k tokensUpdated 3 mo ago
    Knowledge ManagementAuto-check passed

More from Vexa-ai/vexa

  • Vexa Scheduler Routines

    Vexa-ai/vexa

    Writes durable recurring or future-dated jobs for a Vexa workspace as routine files, replacing OS cron, timers and session-only reminders.

    2.9k GitHub stars~901 tokensUpdated yesterday
    Auto-check passed

  • Vexa MCP Setup

    Vexa-ai/vexa

    Set up or fix the Vexa MCP connection for this plugin — where the API key comes from, hosted vs self-hosted URL, and how to check the connection. Use when the…

    2.9k GitHub stars~289 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Vexa Meetings

What does Vexa Meetings do?

Sends a Vexa bot into a meeting, follows the live transcript and writes meeting notes with speakers, decisions and action items into Obsidian, Notion or Markdown. This skill drives the connected Vexa MCP server. It starts with whats_waiting, parses a meeting link into a platform and meeting id, requests a bot (a person in the call must admit it) and reads the transcript while the meeting runs, using since_index to fetch only new segments, then stops the bot when the call is over.

When should I use Vexa Meetings?

Vexa Meetings fits situations like: sending a bot to a video call and following its transcript; filing a meeting into Obsidian or Notion with action items; searching past meetings for what was decided; tagging meetings with a ticket or CRM id for later lookup.

How do I install Vexa Meetings in Claude Code?

Run `npx skills add Vexa-ai/vexa --skill vexa-meetings -a claude-code`. Or copy the skill folder (clients/claude-plugin/skills/meetings in Vexa-ai/vexa) into .claude/skills/vexa-meetings in your project. Claude Code loads it when a task matches its description.

How do I install Vexa Meetings in Codex?

Run `npx skills add Vexa-ai/vexa --skill vexa-meetings -a codex`. Or copy the skill folder (clients/claude-plugin/skills/meetings in Vexa-ai/vexa) into .agents/skills/vexa-meetings in your project. Codex loads it when a task matches its description.

Can I use Vexa Meetings in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Vexa-ai/vexa --skill vexa-meetings -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vexa-meetings, .gemini/skills/vexa-meetings, .github/skills/vexa-meetings and .opencode/skills/vexa-meetings in your project.

What does Vexa Meetings need to run?

SKILL.md names no scripts, command-line tools or credentials: Vexa Meetings is instructions for the agent only. Our summary lists: The Vexa MCP server connected to your agent.

Does Vexa Meetings access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vexa Meetings safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vexa Meetings use?

Vexa Meetings is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vexa Meetings use?

About 631 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vexa Meetings?

Skills that share tags, products or a category with Vexa Meetings: Composio (ComposioHQ/composio, 30k stars), Claap Weekly Recap (Othmane-Khadri/YALC-the-GTM-operating-system, 318 stars), Pm (coreyhaines31/makerskills, 851 stars) and Granola (win4r/MuseAI-Skills, 343 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vexa Meetings?

Vexa-ai (a GitHub organization) maintains it in Vexa-ai/vexa, which has 2,867 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.

Source: Vexa-ai/vexa on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.