agentleFS
Sign inStart free
DataSift-Ty-PersonalDataSift-Ty-Personal/SiftStack/skills/closer-coach/SKILL.md

closer-coach

Skill22 starsChanged 53 days agoMITView on GitHub

Pull acquisitions/closing calls from your SmrtPhone account, transcribe with real tonality notes, and grade them against the DataSift closer rubric - discovery deepening, the money conversation, multi-option offer presentation, objection handling, commitment locking. Produces per-call coaching reports, closer scorecards, and an Excel workbook. Use when asked to review closing calls, offer calls, negotiation quality, or acquisitions call coaching.

  • Reads credentials

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
  1. Very specific:

    Read references/rubric.md fully (gate with the in-person variant, auto-fails, 6 categories weighted 15/25/20/25/10/5, anchors, template, …

    line 35
  2. Distinctive:

    Read the whole transcript once.

    line 38

≈ “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

Closer Coach

Grades acquisitions calls (offer presentation, negotiation, renegotiation, contract talk, in-person appointment recordings) against the DataSift Closer playbook. Same pipeline as the cold-call-coach skill; this skill applies the closing rubric to calls the triage step classified as closing.

Requirements, setup, and costs

Identical to the cold-call-coach skill (same scripts, same session, same .env): python scripts/smrtphone_login.py once, OPENROUTER_API_KEY in .env, optional roster.json. Transcription costs about $0.002 per audio minute.

Pipeline

python scripts/pull_calls.py --min-seconds 60 --days 14
python scripts/transcribe.py

Then take the closing group with worth_grading: true from output/call_coaching/review_queue.json. Closing calls are rarer and longer than cold calls; if the queue is empty, widen the window (--days 30) or drop --min-seconds to 45. Very long calls (over ~25 min) may need the MP3 split with ffmpeg (-f segment -segment_time 900) and the parts transcribed in order.

Grading procedure

  1. Read references/rubric.md fully (gate with the in-person variant, auto-fails, 6 categories weighted 15/25/20/25/10/5, anchors, template, the required SCORES JSON footer).
  2. Read the whole transcript once; verify AGENT/SELLER labels by content.
  3. Score criterion by criterion against the 0/3/5 anchors (quote required), compute the weighted /100 and band, and write one report per call to output/call_coaching/reports/closing/{call_id}_{caller}.md with the CRITERION SCORES table and SCORES JSON footer. Closing calls deserve depth: include a negotiation timeline (each price or term mentioned, who moved, what triggered the move) and a "the moment it was won or lost" section quoting the pivotal exchange.
  4. Export: python scripts/export_excel.py --dir output/call_coaching/reports/closing

Grading quality protocol (mandatory verify pass)

Same as cold-call-coach: verbatim quotes only, evidence per criterion, N/A discipline with listed redistribution (N/A when the situation never arose, e.g. renegotiation criteria on a first-offer call), math that foots exactly with a matching JSON footer, and call-audible content only.

Failure modes

Session expired: re-run python scripts/smrtphone_login.py. Key error: set OPENROUTER_API_KEY in .env. If a call is really lead management, grade it with that skill instead and note the reroute.

Related

First-touch dials: cold-call-coach. Qualification follow-ups: lead-manager-coach. This skill grades call QUALITY only.

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