agentleFS
Sign inStart free
prosyo-aiprosyo-ai/gtm-skill/skills/call-coaching-scorecard/SKILL.md

call-coaching-scorecard

Skill13 starsChanged 23 days agoMITView on GitHub

Use this skill when a manager or rep wants feedback on sales calls: \"score this call\", \"review my discovery call transcript\", \"coaching feedback for my SDR\", \"build a call scorecard\". Scores a call transcript or notes on opening, discovery, listening, value, objection handling and next step, quotes the moments that mattered, picks the one skill to work on next, and gives a concrete drill. Also builds a team scorecard so coaching is consistent across managers.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Use this after calls worth learning from: a first call, a lost deal, a new rep's first week.

    line 16
  2. Distinctive:

    Call type (cold call, discovery, demo, negotiation) and its goal.

    line 21
  3. Distinctive:

    Read references/scorecard-rubric.md for the full rubric per call type and example quotes for each score.

    line 39
  4. Distinctive:

    MUST quote the call for every strength and miss.

    line 71
  5. Distinctive:

    MUST pick one focus skill.

    line 72
  6. Distinctive:

    MUST respect call-recording consent and keep transcripts private to the rep and their manager.

    line 73
  7. Distinctive:

    NEVER share a rep's scores publicly or compare reps by name in team settings.

    line 74

≈ “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

Use this after calls worth learning from: a first call, a lost deal, a new rep's first week. Coaching works when it is specific, quoted and focused on one thing at a time.

Inputs

  • The transcript (or detailed notes).
  • Call type (cold call, discovery, demo, negotiation) and its goal.
  • The rep's experience level.

The play

1. Measure the basics

Talk ratio (rep vs buyer), number of questions asked, longest rep monologue, whether a next step was booked. Talk ratio over 60% on a discovery call is a red flag on its own.

2. Score the dimensions (1-4)

DimensionWhat 4 looks like
OpeningClear agenda, buyer adds to it, permission to ask questions
DiscoveryLayered questions to impact and priority; follow-ups on answers
ListeningParaphrases, uses the buyer's words, does not interrupt
ValueConnects the product to the buyer's stated problem, with proof
ObjectionsClarifies before answering; calm; checks the answer landed
Next stepSpecific, dated, agreed on the call, with the right people

Read references/scorecard-rubric.md for the full rubric per call type and example quotes for each score.

3. Quote the moments

Two strengths and two misses, each with the exact quote and timestamp, and what a better line would have been.

4. Pick one focus

The single skill that would most change results on the next five calls. Usually the earliest weak stage: weak discovery causes weak value and weak next steps.

5. Give a drill

A 10-15 minute exercise for the focus skill: rewrite three questions, a role-play of the missed moment, or listen to a great call and note how the top rep handled the same moment.

Output format

Call: <type> | <rep> | <date>   Goal: <...>   Outcome: <next step or not>
Talk ratio: x% | Questions: N | Longest monologue: N min
Scores: Opening x | Discovery x | Listening x | Value x | Objections x | Next step x
Strengths: <quote - why it worked> x2
Misses: <quote - better line> x2
Focus for next calls: <one skill>
Drill: <exercise>

What good looks like

  • Feedback quotes the call; no "be more consultative" without an example.
  • One focus, not ten notes.
  • Praise is as specific as criticism.
  • The common mistake is scoring everything and changing nothing: a manager who gives seven pieces of feedback gets none of them applied.

Rules

  • MUST quote the call for every strength and miss.
  • MUST pick one focus skill.
  • MUST respect call-recording consent and keep transcripts private to the rep and their manager.
  • NEVER share a rep's scores publicly or compare reps by name in team settings.

Example prompts

  • "Score this discovery call transcript and give me one thing to work on."
  • "Build a call scorecard our 4 managers can use consistently."
  • "Review my cold calls from today; I keep losing them at 'send me an email'."

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