agentleFS
Sign inStart free
heypastelheypastel/pastel-outbound-system/skills/outbound-brief/SKILL.md

outbound-brief

Skill2 starsChanged 56 days agoMITView on GitHub

Writes or updates outbound-brief.md, the one-page brief every outbound skill reads (what we sell, who buys, off-limits, proof, tone, autopilot), mostly from the Pastel workspace plus a few questions. Use on first run, when the brief is missing, or when the user's positioning, market, or sending rules change.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask what's left, all at once, five questions at most: Always confirm these four unless already known: results we can cite publicly, who is …

    line 16
  2. Very specific:

    Compare with Pastel: If the user's answers contradict an ICP definition or agent in Pastel, list the differences and offer market-map to …

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Outbound brief

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

Pastel already knows a lot about the user's business. Read it first, ask only for what's left.

Steps

  1. Pull from Pastel: pastel_get_workspace_context (positioning, keywords, competitors, market), pastel_list_icp_definitions, pastel_list_agents (what their agents already watch), pastel_list_connected_accounts (who sends). If the user shares their website, read the homepage and pricing page.
  2. Fill ../command-center/shared/outbound-brief.template.md. After each line filled from a source, add where it came from: <!-- from: pastel workspace -->.
  3. Ask what's left, all at once, five questions at most. Always confirm these four unless already known: results we can cite publicly, who is off-limits, what we ask for, autopilot on or off.
  4. Save outbound-brief.md in the project root unless the user prefers .codex/. Unanswered lines stay [missing].
  5. Compare with Pastel. If the user's answers contradict an ICP definition or agent in Pastel, list the differences and offer market-map to update Pastel.
  6. Check the workspace with the empty-result check. New users usually arrive during Pastel's first run: tell them it's running and roughly when leads will be ready.

Done when the file is saved, every line is filled or [missing], and autopilot is explicitly on or off.

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.

Check your setup, free