post-call
Skill1 starsChanged 4 months agoMITView on GitHub
Turn raw post-call notes into a structured HubSpot log, a qualification verdict, and the same-day follow-up email. Use when the rep says "log this call", "just got off a call with...", "here's what happened", or dumps call notes right after a meeting.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- chacosoldier/compabobtheir own version, first seen Oct 23, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- chacosoldier/compabob★ 34same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- account-briefSkill
- battlecardSkill
- build-listSkill
- dojoSkill
- draft-sequenceSkill
- handle-replySkill
- meeting-prepSkill
- reactivateSkill
- setupSkill
- signal-watchSkill
- voice-interviewSkill
- what-worksSkill
- work-inboundSkill
- write-emailSkill
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
- Very specific: line 12
Read ${CLAUDE_PLUGIN_ROOT}/references/icp.md and references/guardrails.md if not already in context.
- Distinctive: line 43
No recap-everything emails.
≈ “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.
Files
Post Call
Run this within 30 minutes of hanging up — details decay fast and the follow-up email loses power by the hour. Input: your brain-dump, in any form (rambling voice-to-text is fine; messy beats delayed). If anything critical is missing, ask ONE batch of short questions, not a drip.
Before you process
Read ${CLAUDE_PLUGIN_ROOT}/references/icp.md and references/guardrails.md if not already in context. Look for voice-profile.md and the meeting-prep output for this call in the working folder.
Step 1 — Structure the notes
Extract into fixed fields (mark anything you didn't cover as [not discussed] — visible gaps beat silent ones, and they seed the next call):
- Outcome — next step agreed, in the prospect's words
- Pain — the problem as THEY stated it (verbatim phrases in quotes — these are gold for the follow-up and for
learnings.md) - Stack / situation — their relevant tools, current solution or status quo, and anything competitive mentioned
- Trigger/urgency — why now (or the absence of a why-now, which is its own answer)
- Buying picture — who else is involved, timeline, budget shape (never push to invent what wasn't said)
- Objections raised — and whether the response landed (feeds what-works)
- Personal/rapport notes — the human details that make touch #6 feel like a relationship
Step 2 — Qualification verdict
Re-score against the 10-point rubric using what the call revealed. Verdict: advance (meets the bar → what's the AE handoff / next meeting), nurture (real fit, no urgency → concrete comeback date + the current campaign), or disqualify (say why plainly — a clean DQ is a good outcome, guardrail #6 applies to pipeline too). If advancing: draft the 3-sentence internal handoff note (context, pain, next step) for the AE / your marketing lead.
Step 3 — HubSpot log
Produce the log entry ready to paste (or write via connector if available): call logged with the structured fields, next-step task with a DATE, and any stack/competitor facts as contact/company property updates. Guardrail #5: the call did not happen until it's in HubSpot.
Step 4 — Follow-up email (same day)
Drafted per write-email rules, in your voice, but follow-up shape not cold shape:
- One line anchored in something specific from the call (not "great chatting!")
- The pain in THEIR words, played back in one sentence
- The agreed next step with date/logistics — or the calendar link if that's the ask
- Optional: ONE resource genuinely tied to what they raised (e.g. a relevant asset, a trial, or the current campaign)
No recap-everything emails. ≤90 words. AI-writing check applies.
Output format
# Post-call: [Contact] @ [Company] · [date]
**Verdict:** [ADVANCE / NURTURE / DISQUALIFY] — [one sentence]
## HubSpot log [structured fields, paste-ready]
## Next-step task [action + owner + date]
## Follow-up email [full draft + word count + checks line]
## Handoff note [if advancing — 3 sentences for the AE]
## For what-works [objections heard + what landed/didn't]End with: "Send the follow-up before end of day. Anything here worth drilling? run the dojo on the objection that stung."
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
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.

