agentleFS
nthnclrknthnclrk/enablement-skills/skills/call-review-coach/SKILL.md

call-review-coach

Skill14 starsChanged 8 months agoMITView on GitHub

Review one sales call and turn recording, transcript, or notes evidence into clear coaching priorities and next-practice actions. Use for single-call coaching across discovery, demo, objection handling, technical validation, or closing, including a single discovery call. Route practice-drill creation to roleplay-scenario-builder and multi-call discovery baselines, comparisons, or trend audits to discovery-rubric-auditor.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 11 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use evidence from one call to help a rep practise a specific change for their next comparable conversation.

    line 8
  2. Distinctive:

    If a manager cannot hear the change on the next comparable call, it is not coaching.

    line 16
  3. Distinctive:

    Ask only for the inputs that change the review:

    line 20
  4. Distinctive:

    Call type, intended outcome, and who was in the room

    line 23
  5. Distinctive:

    If the recording is not reachable, work from what you have and say so.

    line 31
  6. Distinctive:

    Read the relevant sections of references/call-coaching-rubric.md when checking feedback or scoring a review.

    line 35
  7. Distinctive:

    Use the most direct accessible source appropriate to the judgment.

    line 42
  8. Distinctive:

    Keep 1-3. Connect each priority to its evidence and include a buyer-facing question or response to practise.

    line 48
  9. Distinctive:

    Call type, segment, rep level, and the review objective

    line 60
  10. Distinctive:

    Keep employee details relevant to the coaching purpose.

    line 69
  11. Distinctive:

    Every score cites a moment you could access.

    line 73

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 review coach

Use evidence from one call to help a rep practise a specific change for their next comparable conversation.

A review covers one conversation, a few moments, and one to three things to try next time. A sample of discovery calls is discovery-rubric-auditor. A practice drill is roleplay-scenario-builder.

Next-call behavior. "When the buyer says manual reporting takes half a day, stay with what that delays before you show dashboards. Try: 'What does that work stop your team from doing?' Success on the next call: the buyer explains a consequence and you check your understanding."

Generic note. "Be more consultative and tighten discovery. Work on active listening and next-step control."

If a manager cannot hear the change on the next comparable call, it is not coaching.

Inputs

Ask only for the inputs that change the review:

  1. The source you can actually access: recording, transcript, notes, or summary
  2. Call type, intended outcome, and who was in the room
  3. Rep role, tenure, and segment
  4. The team's sales methodology or coaching rubric, if available
  5. What the coach wants to change, if they already know
  6. Whether names must be anonymized

Lead with what happened on the call and the most useful change for the rep. Use the team's rubric or methodology to inform your judgment when it is available. A familiar sales concept can help explain a coaching point, but the advice should make sense in plain language. Organise ordinary feedback around the conversation and the rep's next move; reserve an element-by-element framework assessment for an explicit request.

If the recording is not reachable, work from what you have and say so. Never imply you heard a moment you could not access.

Supporting material

Read the relevant sections of references/call-coaching-rubric.md when checking feedback or scoring a review. It covers coaching language, call-type applicability, and scoring anchors. A supplied team rubric takes precedence over the generic anchors.

Procedure

  1. Name the job of the call. What was this conversation supposed to produce? Done when the intended next step fits in one sentence.
  2. Set evidence coverage. Use the most direct accessible source appropriate to the judgment. Audio can support tone or timing; a transcript supports wording, subject to transcription errors. Notes support narrower conclusions. Flag missing sections and speaker uncertainty so every judgment has an explicit evidence basis.
  3. Log the few moments that decided the call. Give a timestamp or source location, speaker, and observed action. Explain what the exchange established or left untested and why it matters to this call's objective. Mention a methodology concept only when it helps explain the coaching. Select enough moments to support the priorities; do not pad the review to a fixed count or infer the eventual deal outcome.
  4. Score only what this call type made observable. Score when requested or needed for an agreed coaching process. Use the supplied rubric or the reference anchors. Distinguish an observed miss from insufficient evidence or no opportunity to demonstrate the behaviour (N/O). Every score needs an accessible example.
  5. Pick the next-call behaviors. Keep 1-3. Connect each priority to its evidence and include a buyer-facing question or response to practise. Drop anything a manager cannot hear next time. One call is directional, not a verdict on the rep.
  6. Write the practice. Replay or reconstruct the relevant moment from accessible evidence. Ask the rep what they intended, practise a different response, and compare the retry with the target behaviour. Include an in-call cue and a success signal the manager can check.
  7. Set the follow-up. Agree the next comparable opportunity and what evidence to review. If the behaviour is absent, check whether the opportunity occurred before drawing a conclusion about progress.

For a practice drill use roleplay-scenario-builder. For a multi-call discovery baseline use discovery-rubric-auditor. For a reusable talk track use talk-track-builder.

What to return

Match the format to the request. For a short coaching note, weave the evidence, what to keep, and what to try into direct feedback. Keep evidence limits brief when they matter. A fuller manager review can include:

  • Call type, segment, rep level, and the review objective
  • Evidence coverage: source, accessible portion, speaker limits, confidence
  • The few decisive moments, located
  • Scores only when requested or useful to the agreed process, with evidence and N/O where appropriate
  • Strengths to keep
  • 1-3 next-call behaviors with evidence, why they matter, a question or response to practise, cue, and success signal
  • A short rehearsal and a follow-up check on the next comparable opportunity
  • Assumptions, if you had to make any

Keep employee details relevant to the coaching purpose. A short rehearsal belongs in this review; a full scenario pack, team baseline, or readiness assessment is separate work. Sharing coaching records requires explicit approval.

Quality bar

  • Every score cites a moment you could access.
  • Unobserved dimensions are N/O, not zeros.
  • Coaching is 1-3 next-call behaviors, not an issue list.
  • Each behavior is something a manager can hear on the next comparable call.
  • Feedback sounds like coaching for this conversation. Methodology references clarify a point rather than define the outline.
  • Unknown deal information stays unknown; a coaching suggestion is not a finding about the rest of the deal.
  • A single call is labeled directional, not a rep-level verdict.
  • The review supports development; it does not infer team trends or certify readiness from one 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.