agentleFS
Sign inStart free
JakeschincariolJakeschincariol/closer-skill/sales-coach/SKILL.md

sales-coach

Skill33 starsChanged 11 days agoMITView on GitHub

Sales Coach. Listens to your sales call and tells you exactly what to say next. Reads the call's live captions (Google Meet's own captions, read off the page by Claude in Chrome, or any captions file), and the moment the other side raises an objection ("it's too expensive", "let me think about it", "I need to ask my partner", "we already have someone") it shows you, and only you, the answer to say next, filled from your real offer. Also flags buying signals and questions you still owe an answer, and reviews the call afterwards (talk time, questions asked, next step). Use when the user says "coach me on this call", "listen to my call", "I have a sales call", "what do I say if they say it's too expensive", "objection", "handle objections", or "review my call".

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. poorvith-mp/skills-sales-support★ 0same 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 repository10 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Run /researcher on the prospect and read the brief together.

    line 35
  2. Very specific:

    Check me.plan_b and me.value_line are set and TRUE.

    line 36
  3. Very specific:

    After each new line from the other side, run coach.py listen --captions closer/calls/live.txt on the new lines and show the card in big, …

    line 46
  4. Distinctive:

    Keep it to the card. No paragraphs mid-call.

    line 55
  5. Distinctive:

    Never speaks, types or acts on the call.

    line 82
  6. Distinctive:

    Never keeps audio. The captions text stays in the user's project.

    line 83
  7. Distinctive:

    Never suggests a lie, a fake deadline, a fake discount or pressure.

    line 84
  8. Distinctive:

    Never invent a number, a result, a client, a review or a deadline.

    line 94

≈ “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

sales-coach

The coach sits beside the user on a live call, reads the captions as they appear, and answers one question the whole time: what do I say next? It never speaks on the call. It only shows the user a card.

${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).

python3 "${CLAUDE_SKILL_DIR}/coach.py" listen --captions closer/calls/live.txt --me You
python3 "${CLAUDE_SKILL_DIR}/coach.py" listen --captions closer/calls/live.txt --me You --follow
python3 "${CLAUDE_SKILL_DIR}/coach.py" card --objection price
python3 "${CLAUDE_SKILL_DIR}/coach.py" review --captions closer/calls/live.txt --me You

The answers come from objections.json filled with the user's own offer from closer/pipeline.json (me.offer, me.price, me.plan_b, me.value_line, me.proof). If a field is missing, the card shows [your value line] instead of making one up.

Before the call

  1. Run /researcher on the prospect and read the brief together.
  2. Check me.plan_b and me.value_line are set and TRUE. The price answer is only as good as they are.
  3. Agree the opening line with the user: "Mind if I keep captions on so I can take good notes?" Everyone on the call hears that before anything is captured.

During the call (Google Meet)

  1. The user turns on captions in Meet (the CC button). The captions appear on the page with the speaker's name.
  2. With Claude in Chrome, read the captions area every few seconds (get_page_text or read_page on the Meet tab) and append each NEW finished line to closer/calls/live.txt as Name: text. Never click anything in the meeting, never unmute, never type in the chat.
  3. After each new line from the other side, run coach.py listen --captions closer/calls/live.txt on the new lines and show the card in big, plain text:
Objection: price  (Dana: "It looks great, but honestly, it's too expensive for us right now.")
Say this next: Totally fair. Most practices win the cost back with 2 new patients a month.
Want to start on the $399 monthly plan instead, with no setup fee?
  1. Keep it to the card. No paragraphs mid-call. The user is talking.

Zoom, Teams or a phone call: any captions or live transcript the user can see works the same way. Or the user runs coach.py listen --follow in a terminal while the lines are appended.

The objections it knows

price, timing, needs to think, someone else decides, already has someone, does it work, send me info. Each has the words it listens for, the answer, and why that answer works. Add the user's own: edit objections.json with what their customers really say and what really works for them.

After the call

coach.py review: how much of the call the user talked (aim for under half), how many questions they asked, every objection and buying signal, and whether a next step was agreed. Then /record-keeper call with the notes, and /proposal-writer or /contract-writer for the next step.

Example from the reel

On the Thursday call at 2:14 PM, after "So that's the site, with online booking built in," Dana Ortiz said, "It looks great, but honestly, it's too expensive for us right now." The card: Objection: price, "Totally fair. Most practices win the cost back with 2 new patients a month. Want to start on the $399 monthly plan instead, with no setup fee?" Then "How soon could we start?": Buying signal, agree the next step. The transcript is call.example.txt (illustrative: Dana and Harbor Lane Dental are fictional).

What it never does

  • Never speaks, types or acts on the call. It only shows the user a card.
  • Never keeps audio. The captions text stays in the user's project.
  • Never suggests a lie, a fake deadline, a fake discount or pressure. If the true answer is "we're not the right fit", it says so.

Consent and truth

  • Calls: tell everyone on the call that captions or notes are on, before you start. Some places (for example California, Florida, Washington, and many countries) need every person's consent to record. The coach reads live captions as text, keeps no audio, and is shown only to the user. It never speaks on the call.
  • Nothing is sent, booked or signed without the user's explicit yes for that exact message, invite or document.
  • Never invent a number, a result, a client, a review or a deadline. Fill in only what is true and ask when something is missing.

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