Meeting To Action

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha a79d9cd3663a · 15 Oct 2026Report an issue or request a re-scan

• PublisherInternLM GitHub organizationOwner of the repository this skill is read from
• Source folderInternLM/WildClawBench/skills/3/meeting-to-actionThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdicta79d9cd3663aA new audit runs when the source changes
• Repository statusNot archivedLast push 27 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Convert meeting notes or transcripts into clear summaries, decisions, and action items with owners and due dates. Use when a user asks to turn a meeting recording, transcript, or notes into a follow-up plan.

---
name: meeting-to-action
description: Convert meeting notes or transcripts into clear summaries, decisions, and action items with owners and due dates. Use when a user asks to turn a meeting recording, transcript, or notes into a follow-up plan.
---

# Meeting to Action

## Goal
Transform meeting content into an actionable follow-up package with clear ownership and deadlines.

## Best fit
- Use when the user provides a transcript or detailed notes.
- Use when the user needs action items, decisions, and next steps.
- Use when a concise recap email or message is required.

## Not fit
- Avoid when the user wants tasks or calendar invites created automatically.
- Avoid when the transcript is missing and cannot be summarized reliably.
- Avoid when sensitive content should not be shared.

## Quick orientation
- `references/overview.md` for workflow and quality bar.
- `references/auth.md` for access and token handling.
- `references/endpoints.md` for optional integrations and templates.
- `references/webhooks.md` for async event handling.
- `references/ux.md` for intake questions and output formats.
- `references/troubleshooting.md` for common issues.
- `references/safety.md` for safety and privacy guardrails.

## Required inputs
- Transcript or notes.
- Participant list and roles (if available).
- Preferred due date format and timezone.
- Audience for the recap (internal or external).

## Expected output
- Short summary and key decisions.
- Action items with owners, due dates, and status.
- Open questions or risks.
- Draft follow-up message or email.

## Operational notes
- Mark any inferred owners or due dates as tentative.
- Use clear, consistent action verbs.
- Deliver drafts only; do not send or update systems.

## Security notes
- Treat meeting content as confidential.
- Avoid sharing outputs outside the user context.

## Safe mode
- Summarize and draft action items only.
- Do not create tasks, invites, or messages automatically.

## Sensitive ops
- Creating tasks, calendar events, or sending messages is out of scope.

Excerpt, first 2,055 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/InternLM/WildClawBench
git -C WildClawBench checkout a79d9cd3663a

Works in

1. 2026-10-15
   ✓SAFE B 89 / 100

   first audit · source a79d9cd3663a

Questions about Meeting To Action

• github.com/InternLM/WildClawBench/tree/main/skills/3/meeting-to- — the audited source at commit a79d9cd3663a and every finding aboveObserved · 15 Oct 2026

Spotted something wrong? Report a correction · Methodology