agentleFS
volodymyrkhodonovychvolodymyrkhodonovych/claude-sales-skills/skills/call-prep-brief/SKILL.md

call-prep-brief

Skill1 starsChanged 10 days agoMITView on GitHub

Builds a one-page pre-call brief for a B2B sales or partnership call from a company name, attendee list and any prior notes. Use whenever the user mentions an upcoming call, meeting, demo or intro with a prospect or partner and wants to prepare, even if they only say "I have a call with X tomorrow".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask only for what is missing:

    line 15
  2. Distinctive:

    Search the web for the company and each attendee: role, tenure, public statements, recent news.

    line 21
  3. Distinctive:

    Read any prior notes or threads the user provides.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Call prep brief

The best calls start from what the prospect said, not from what we want to pitch. A one-page brief keeps the focus on their situation and makes the desired next step explicit before the call starts.

Inputs

Ask only for what is missing:

  • Company, attendee names and roles, call date and length
  • The goal of the call (discovery, demo, negotiation, partnership)
  • Prior notes or email history, if any

Steps

  1. Search the web for the company and each attendee: role, tenure, public statements, recent news. Record sources.
  2. Read any prior notes or threads the user provides. Separate what the prospect said from what we assumed, because assumptions presented as facts steer the call wrong.
  3. Build the brief in the format below, on one page.
  4. Flag what is unverified or inferred.

Format

Call: [Company], [date], [length], goal in one line

  • Who is on the call: name, role, one relevant fact each
  • Company snapshot: 3 bullets (what they do, size or stage if public, one recent event with source)
  • What we know they want: in their words, from prior notes. Write "unknown" if there are none.
  • Hypotheses to test: 2–3 things we think are true but haven't confirmed
  • Questions to ask: 5–7 open questions in order, starting with their situation before our offer
  • Likely objections: 2–3, each with a short, honest response
  • Desired outcome: the specific next step to ask for before hanging up
  • Do not raise: topics to avoid, for example pricing before discovery

Bullets are right here because the reader scans the page just before the call.

Rules, and why

  • Only sourced or user-provided facts, and mark inference as inference. A wrong fact said confidently on a call costs more than a gap in the brief.
  • No invented stats, funding rounds or quotes.
  • Professional context only for attendees. Skip personal or private information; it isn't needed and can feel intrusive.
  • One page. A longer brief won't be read before the call.

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.