agentleFS
TrustPagerTrustPager/Business_Operating_System/skills/log-this-call/SKILL.md

log-this-call

Skill8 starsChanged 5 months agoMITView on GitHub

Log the call you just had — captures the recap, updates the opportunity, schedules the next step, and notifies anyone who needs to know.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 11 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After every customer call, three things need to happen and almost always don't:

    line 27
  2. Distinctive:

    If the user didn't say who they spoke to:

    line 36
  3. Distinctive:

    If multiple contacts matched: present a numbered list and ask which one.

    line 48
  4. Distinctive:

    Don't dump all four at once.

    line 59
  5. Distinctive:

    If they said "more interested" → suggest moving the opportunity to the next stage.

    line 83
  6. Distinctive:

    If they said "less interested" or "parked" → suggest adding a follow-up task for the next contact date.

    line 84
  7. Very specific:

    ALWAYS create a task for the next contact date (mcp__trustpager__create_task) with the agreed action as the title.

    line 86
  8. Distinctive:

    If the opportunity has other assigned users:

    line 90
  9. Very specific:

    If yes: send an internal email summary (use mcp__trustpager__send_email with mode: "internal" if available, else a task with a mention).

    line 93
  10. Distinctive:

    Never fabricate: If the user gave a one-liner, the note is a one-liner.

    line 97
  11. Distinctive:

    Stage moves are suggestions: Always confirm with the user before moving.

    line 100
  12. Distinctive:

    One task per call, max: Don't auto-create three tasks because the conversation mentioned three things.

    line 101
  13. Distinctive:

    If the user only had time for 2 of the 4 questions, log what we have and say so: "Logged partial — discussed + agreed.

    line 107

≈ “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

/log-this-call

After every customer call, three things need to happen and almost always don't:

  1. The CRM gets a useful recap (not "had a chat — call again next week")
  2. The opportunity moves to the right stage or gets a clear next action
  3. The next step is scheduled so it doesn't get forgotten

This skill captures all three from a single conversation with the user.

Step 1 — Identify the context

If the user didn't say who they spoke to:

"Who did you just speak to? (name, phone, or opportunity name)"

Once you have a name, phone, or email, run:

python ~/.claude/bos-run.py log-this-call --query "<what they said>"

The returned JSON gives you the matched contact(s), their open opportunities (with stage), recent activities, and open tasks — all in one call. No need to chain search_contacts + list_contact_deals + get_opportunity_activities separately.

If multiple contacts matched: present a numbered list and ask which one. If the chosen contact has multiple open opportunities, ask which one. Default to the most-recently-touched.

Step 2 — Capture the recap

Walk the user through 4 structured questions, ONE AT A TIME:

  1. What did you discuss? (the substance — not "we chatted")
  2. What's their position now? (more interested / less interested / parked / decided — and if they raised a concern, capture it verbatim: a concern that recycles across calls is the real one (business-method.md §12.5), and /prep-for-call surfaces it next time)
  3. What did you agree on? (the action they're taking, or the action you're taking)
  4. When's the next contact? (specific day if possible)

Don't dump all four at once. Wait for each answer before asking the next. Each answer is one short prompt to the user.

Step 3 — Update the workspace

Build a single structured note and post it via mcp__trustpager__add_note on the opportunity. Body shape:

📞 Call with {contact_name} — {duration_or_just_now}

Discussed:
- {discussed_points}

Their position: {their_position}

Concern on the table: {concern}

Agreed: {agreed_action}

Next contact: {next_date} — {next_action}

The "Concern on the table" line is optional — include it only when a concern was actually raised, verbatim.

Also:

  • If they said "more interested" → suggest moving the opportunity to the next stage. Show: "Move to Quote Sent stage? (y/n)"
  • If they said "less interested" or "parked" → suggest adding a follow-up task for the next contact date.
  • If they said "decided" → ask "Won or lost?" and either move to a won stage (mcp__trustpager__move_opportunity_card) or mark lost. On won: offer to draft the same-day personal welcome (buyer's remorse starts at the receipt, business-method.md §12.5/§11.3), and note this is also the referral-ask moment (§10.7). Draft only; the one-task-per-call rule stands.
  • ALWAYS create a task for the next contact date (mcp__trustpager__create_task) with the agreed action as the title.

Step 4 — Notify the right people

If the opportunity has other assigned users:

"This opp has {N} other people on it. Notify them?"

If yes: send an internal email summary (use mcp__trustpager__send_email with mode: "internal" if available, else a task with a mention).

Important behaviours

  • Never fabricate. If the user gave a one-liner, the note is a one-liner. Don't pad it.
  • Quote the user verbatim for "their position" and "agreed" — these are factual claims that may matter later.
  • No emojis in the note BODY except the leading 📞. Customer-facing tone, not chat tone.
  • Stage moves are suggestions. Always confirm with the user before moving. Never silently auto-move.
  • One task per call, max. Don't auto-create three tasks because the conversation mentioned three things. Pick the agreed next step.

Output shape

End with one line: "Logged. Note added to {opp_name}, task '{task_title}' scheduled for {date}, stage moved to {stage}."

If the user only had time for 2 of the 4 questions, log what we have and say so: "Logged partial — discussed + agreed. Their-position and next-contact left blank. /log-this-call again when you have a sec to fill those in."

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.