agentleFS
heypastelheypastel/pastel-outbound-system/skills/morning-brief/SKILL.md

morning-brief

Skill2 starsChanged 58 days agoMITView on GitHub

Morning plan — what Pastel caught overnight, who replied, what's stuck, and the five moves worth making today, each with its draft ready to approve. Use for "morning brief", "what should I do today", "daily plan", or a scheduled daily run.

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use meeting-prep.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • OpenAISkill

    meeting-prep

    Use when creating Public Equity Investing meeting prep briefs. Do not use for private diligence, IB, FP&A, legal, or scheduling-only tasks.

    Also in 3 projects that use this

The file

Files
SKILL.md

Morning brief

House rules: ../command-center/shared/house-rules.md · Pastel tools: ../command-center/shared/pastel-tools.md

Fifteen minutes of outbound, decided in advance. The brief reads and drafts; each move waits for a "go".

Steps

  1. Can we send today? pastel_list_connected_accounts.
  2. Replies: pastel_list_conversations(unread_only=true), tagged the reply-desk way. Hot ones lead the brief.
  3. Stuck: pastel_list_sequence_runs(status="needs_attention").
  4. New signals: pastel_recommend_best_leads(created_since=<yesterday>, limit=10), quickly checked against outbound-brief.md. Nothing new → the empty-result check; during a first run, the brief says so and lists the set-up moves to do meanwhile. (pastel_get_crawl_status only shows crawls running right now; the newest lead's date tells you whether agents are producing.)
  5. Posts worth a comment: pastel_recommend_best_posts(limit=5).
  6. Choose five moves, in this order of value: answer hot replies → unblock stuck runs → comment on a strong post → first message to a new 🔥 lead → a scheduled nudge. Draft each with its skill, then human-voice.

Output

# Today — [weekday]
Sending: ok | blocked · New signals: n · Unread: n · Stuck: n · Posts: n

1. [Move] — [Person, role] — [why, in one line]
   > draft
   Reply "go 1" to approve
…

Waiting on you:
Open questions:

"go N" runs that move through campaign-launch, nudge, or social-warmup.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.