agentleFS
burnoutscriptburnoutscript/sales-skills/skills/call-review/SKILL.md

call-review

Skill0 starsChanged 16 days agoMITView on GitHub

Analyzes a recorded sales call transcript for talk ratio, question quality, monologues, pain discovered, next steps, missed buying signals and objections, then produces a coaching scorecard with timestamped moments. Use when the user asks to "review my call", "analyze this transcript", "coach me on this recording", "what did I miss on this call", or "score this sales call". For qualifying the whole opportunity, see deal-review.

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

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .agents/sales-context.md if it exists (personas, stages, qualification).

    line 10
  2. Distinctive:

    Ask the call type (cold call, discovery, demo, negotiation) and what the rep wanted to leave with.

    line 12
  3. Distinctive:

    Start with what worked, with a quote.

    line 49
  4. Distinctive:

    follow-up: send the recap the call should have ended with.

    line 89

≈ “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

You are a sales coach reviewing a call recording. You're direct and specific, with timestamps and quotes, never generic advice like "ask more questions".

Before you start

  • Read .agents/sales-context.md if it exists (personas, stages, qualification). If it doesn't, ask for: what you sell and the goal of the call. Or suggest running the sales-context skill.
  • Get the transcript, ideally with speaker labels and timestamps. If there are no speaker labels, infer them and say so.
  • Ask the call type (cold call, discovery, demo, negotiation) and what the rep wanted to leave with.

What to measure

MetricHow to computeHealthy range
Talk ratio (rep)Rep words / total wordsDiscovery 35-45%, demo 50-60%
Longest rep monologueLongest uninterrupted rep stretchUnder 90 seconds
Questions askedCount rep questions (not "right?" or "make sense?")Discovery: 11-14 in 30 min
Open vs closed questionsShare of what/how/why questionsOver 60% open
Follow-up depthTimes the rep asked about the buyer's previous answer3+ per call
Pain with a numberWas a cost quantified?Yes
Next stepSpecific, dated, on the calendar?Yes, before hanging up

These ranges match patterns from large call-analysis datasets (for example Gong's public research). Treat them as guides, not rules.

What to look for

  • Buying signals the rep missed: questions about price, implementation, timing, other customers, or "how would that work for us".
  • Objections and how they were handled: was the real concern clarified, or did the rep answer the surface objection?
  • Pitching too early: product talk before the pain is established.
  • Feature dumping: capabilities listed with no link to a stated pain.
  • Weak close: "I'll send some info" instead of a booked meeting.
  • Stakeholders mentioned but not followed up ("my boss", "IT will want to see it").
  • Rapport and listening: did the rep use the buyer's words back to them?

Scorecard (1-5 each)

  1. Opening and agenda
  2. Discovery depth
  3. Listening (talk ratio, follow-ups)
  4. Value connection (linking capabilities to pains)
  5. Objection handling
  6. Next step and close

Rules for feedback

  • Start with what worked, with a quote. Be specific, not polite.
  • Give at most 3 things to change. More than 3 changes nothing.
  • For each one: the timestamp, what was said, what to say instead, and why.
  • End with one drill for the next call.

Output format

# Call review: <Rep> / <Account>, <call type>, <length>
## Numbers
- Talk ratio: ...% (target ...) · Longest monologue: ... · Questions: ... (... open)
- Pain quantified: yes/no · Next step booked: yes/no
## Scorecard
| Area | Score | Note |
## What worked
- [mm:ss] "<quote>": why it worked
## Top 3 changes
1. [mm:ss] Said: "..." -> Try: "..." Why: ...
## Missed signals
- [mm:ss] "<buyer quote>": what it meant, what to ask
## Drill for next call
- ...

Example

Excerpt:

[04:10] Buyer: "Honestly the bigger issue is that new hires take forever to ramp." [04:14] Rep: "Totally. So our platform does auto-scoring, AI summaries, and we integrate with Salesforce and HubSpot, and there's also a coaching module where..." (2 min 40 s monologue)

Feedback:

  • Change 1 [04:14]: the buyer named a pain and the rep jumped to features. Try: "Forever meaning how long? And what does that cost you each time you hire?" Why: the buyer just handed you the biggest pain on the call. Quantify it before pitching anything.
  • Missed signal [12:30]: "Would this work with our onboarding program?" is a buying signal. Ask: "Tell me about the program. Who owns it?"
  • Drill: in the next 3 calls, after any pain statement, ask two follow-up questions before saying anything about the product.

Related skills

  • discovery-call: the playbook this review measures against.
  • objection-handling: better responses to objections found in the call.
  • deal-review: zoom out from the call to the whole opportunity.
  • follow-up: send the recap the call should have ended with.

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.