agentleFS
link7373link7373/agentic-sales-marketing/.claude/skills/close-deal/SKILL.md

close-deal

Skill1 starsChanged 3 months agoMITView on GitHub

Advance a specific deal to closed — discovery call plans, question arcs, proposals, objection prevention, commitment design. Run per-deal for B2B conversations; also produces B2C conversion assets (FAQs, objection sections, cart-recovery emails).

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. Distinctive:

    Debrief and record: After the call: needs stated (verbatim), commitments made, stakeholders discovered, honest read.

    line 17
  2. Very specific:

    Call plans, proposals, updated deal records, win-loss notes — or B2C conversion assets.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

/close-deal — Help Them Sell Themselves

Inputs: the deal file in knowledge/deals/<slug>.md (create from pipeline entry if missing), knowledge/offer.md, knowledge/positioning.md. Agents: deal-closer leads; copywriter polishes; the operator conducts live calls. Method: knowledge/methods/consultative-selling.md; knowledge/methods/persuasion-principles.md within ethics.

Steps

  1. Load the deal. Everything known: source, prior touches, stated problems (verbatim), stakeholders, stage. Fill research gaps about the account before any call.
  2. Plan the conversation. Build the question arc: minimal situation questions (research answered most), problem questions to surface pain, implication questions to size the pain's cost until it's explicit, and value questions that let the prospect articulate the payoff themselves. Write them out — specific to this account, not generic.
  3. Prep the operator. A one-page call plan: goal (the specific advance to propose), the question arc, likely objections with prepared responses, and what NOT to do (pitch early, quote price before value is explicit, accept "send me info" as progress).
  4. Debrief and record. After the call: needs stated (verbatim), commitments made, stakeholders discovered, honest read. Update the deal file — this record writes the proposal.
  5. Propose. templates/proposal.md from the prospect's own words: their situation, their stated costs, capability mapped to their expressed needs, investment from the offer sheet, and a dated next step that is an advance. No new arguments.
  6. Handle wobbles. Late objections usually mean a need was left implicit — go back a step and develop it rather than discounting. Discounts/custom terms are money decisions: escalate with a recommendation.
  7. Close or recycle. Won → handoff notes + trigger /grow-referrals post-purchase flow. Lost → reason logged honestly, future-touch scheduled if warranted.
  8. Win-loss writeback (every closed deal, won or lost). Fill templates/win-loss-note.md: why they bought / why they didn't, in their words; which objection decided it; what we'd do differently. Append to knowledge/results-history.md, and add one dated learning line to knowledge/methods/consultative-selling.md → What we've learned here. Product-marketer mines these notes for battlecards and case-study candidates.

B2C track — the page does the closing

Same psychology, asynchronous. Run these plays where buyers hesitate:

  • Objection mining: reviews of competing products, our own pre-sale questions, cart-abandon feedback → the ranked list of unresolved objections. Each gets answered where it occurs: FAQ/objection section, comparison guide, guarantee restatement at point of doubt.
  • Cart & checkout recovery: abandoned-cart sequence (via /launch-campaign): reminder → objection answer → deadline only if true. Checkout page audited for surprise costs and friction (with funnel-builder).
  • DM/chat selling: for businesses where buyers message first (marketplaces, Instagram, Etsy): response playbook — answer the real question, one relevant proof point, one clear next step; never a pitch wall. Templates approved once under the outbound gate.
  • Review-driven conversion: surface the best proof at the decision point (with /grow-referrals supplying fresh social proof).
  • Win-loss, B2C style: periodic "what almost stopped you?" post-purchase question and abandoned-checkout survey; findings feed the same win-loss writeback in step 8.

Before you start

  1. Required inputs: knowledge/offer.md + knowledge/positioning.md at seeded+; for B2B, the deal file (create from the pipeline entry if missing — slug: knowledge/deals/<company-or-person-slug>.md).
  2. Scan knowledge/decision-log.md for tags pricing, offer, pipeline — discount policy and disqualification rules are recorded decisions.
  3. Gate check: discounts/custom terms are money decisions — escalate with a recommendation; B2C sequences/DM templates fall under outbound/publishing gates via their executing skills.

If things go wrong

  • Operator can't take the call in time → offer to reschedule via the prospect's channel; a well-prepped delayed call beats an unprepped rushed one.
  • Prospect goes silent post-proposal → the method's re-engagement play (one value touch, one direct close-the-file note), then recycle honestly.
  • The offer genuinely doesn't fit their need → say so and disqualify; a forced sale becomes a refund and a bad review.

Outputs

Call plans, proposals, updated deal records, win-loss notes — or B2C conversion assets. Close with the report per templates/skill-report.md.

Writeback

knowledge/deals/<slug>.md, knowledge/pipeline.md; won/lost + win-loss note to knowledge/results-history.md; learning line to knowledge/methods/consultative-selling.md; pricing escalations (tag: pricing) to knowledge/decision-log.md.

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.