AgentStack
SKILL verified MIT Self-run

Brief Me

skill-tmusser-context-to-action-skills-brief-me · by tmusser

Catch the user up from messy workplace context and surface what needs attention.

No reviews yet
0 installs
1 views
0.0% view→install

Install

$ agentstack add skill-tmusser-context-to-action-skills-brief-me

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

Are you the author of Brief Me? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

brief-me

Purpose

Turn messy connected or pasted context into a short conversation-state brief the user can act on quickly.

Use For

  • "What did I miss?"
  • "Brief me before this meeting."
  • "What changed since Monday?"
  • "What needs my response?"

Inputs

  • Slack
  • Gmail
  • Calendar
  • Zoom transcript
  • Atlassian
  • Hex or other data output
  • Pasted notes
  • Any combination of the above
  • A reduce-to-facts ledger or conversation-state record

Guardrails

  • Read before write.
  • Do not send messages, create events, update tickets, or publish outputs unless explicitly asked.
  • Separate source-backed facts from assumptions and suggestions.
  • Prefer small source windows.
  • Surface source gaps.
  • Do not dump raw transcript content by default.
  • Keep the output workplace-user friendly.

Portable Output Contract

  • Use only the useful subset of source-backed facts, assumptions, source gaps,

stakeholder sensitivities, potential misreads, and the suggested next action.

  • Use the smallest useful output.
  • Label assumptions and preserve source gaps, source anchors, and confidence labels.
  • When consuming upstream state, do not promote an assumption, inference, open

question, proposed action, or stakeholder position into a fact, decision, commitment, owner, or deadline without new source support.

  • Keep unresolved approvals, owners, timing, and blockers explicit in the brief.
  • Do not send, publish, update tickets, create events, or mutate systems unless explicitly asked.

Output

  • Conversation state
  • What changed
  • What needs response
  • Action state
  • Source confidence
  • Suggested next response
  • Meetings to prep for
  • Suggested follow-ups
  • Source gaps

When the user wants a fuller record, use the optional CONVERSATION_STATE.md template from this pack when it is available.

Success Standard

The user should be able to scan the brief and know what matters within 5 minutes.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.