agentleFS
me-workspaceme-workspace/orchestrator-operational-agent-skills/sales-pipeline/SKILL.md

sales-pipeline

Skill1 starsChanged 46 days agoMITView on GitHub

Use this skill for sales work - "prospek", "lead", "follow up klien", "buat proposal", "penawaran/quotation", "nego harga", "closing", pipeline review, or qualifying whether an opportunity is worth pursuing. Do NOT use for mass-audience marketing content (use marketing-growth) or invoice/AR work (use finance-analyst).

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Never pitch before the pain is quantified - the pain number becomes your pricing anchor.

    line 27
  2. Distinctive:

    Never discount without removing scope or changing terms (prepayment, longer commitment, testimonial).

    line 44

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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 Pipeline

Sell the outcome, qualify hard, and always leave with a next step that has a date.

Lead qualification (score before investing time)

Score 0-2 each; pursue at ≥ 6/10, nurture 4-5, drop < 4:

  • Budget: can they pay in your price range? Any signal (company size, current spend)?
  • Authority: talking to the decision maker, or know who is?
  • Need: pain is explicit and costs them money/time today (not "nice someday").
  • Timeline: an event forces a decision (deadline, contract ending, launch)?
  • Fit: you can genuinely deliver this well - overselling kills referrals.

Log the score and the evidence, not just the number.

Discovery call / chat - get these answers

  1. What are they doing today, and what does the current way cost them (hours, money, missed revenue)?
  2. What triggered them to look for a solution now?
  3. What does success look like in 90 days, in their words?
  4. Who else is involved in the decision, and what does that person care about?
  5. Budget range and decision timeline.

Never pitch before the pain is quantified - the pain number becomes your pricing anchor.

Proposal structure (short beats long)

1. Situasi & masalah (dalam kata-kata klien, dengan angka biaya masalahnya)
2. Solusi & scope - deliverable konkret, apa yang TIDAK termasuk
3. Hasil yang diukur (target 90 hari)
4. Timeline & milestone
5. Investasi: 2-3 opsi paket (anchor tinggi dulu), syarat bayar
6. Langkah berikutnya + masa berlaku penawaran

Scope exclusions are mandatory - undefined scope is where projects die.

Follow-up cadence (default; adapt to signals)

D+2 → D+7 → D+14, then monthly nurture. Each follow-up adds value (relevant insight, case, answer to their question) - never a bare "gimana kabarnya?". Three no-responses → move to nurture, tell them the door stays open.

Negotiation rules

  • Never discount without removing scope or changing terms (prepayment, longer commitment, testimonial).
  • Silence after stating price. First concession smallest.
  • Walk-away point decided before the call.

Pipeline review format

Per deal: stage · value · qualification score · next step + date · risk. Flag any deal with no dated next step - that's not a deal, it's a wish.

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.