agentleFS
burnoutscriptburnoutscript/sales-skills/skills/sales-proposal/SKILL.md

sales-proposal

Skill0 starsChanged 15 days agoMITView on GitHub

Writes B2B sales proposals and statements of work with an executive summary in the buyer's words, an ROI section, scope, timeline, pricing options and terms built to survive procurement and legal with fewer redlines. Use when the user asks to "write a proposal", "draft an SOW", "send pricing to the client", "build a business case", or "proposal template". For discount and term negotiation, see pricing-negotiation.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Read .agents/sales-context.md if it exists (pricing, terms, proof).

    line 10
  2. Distinctive:

    Ask for discovery notes: pains in their words, numbers, success criteria, stakeholders, timeline and any competitor in play.

    line 11
  3. Distinctive:

    Use the conservative estimate.

    line 44
  4. Distinctive:

    Put an expiry on the pricing, tied to a real reason (a quarter-end price change, kickoff slot availability).

    line 52
  5. Distinctive:

    Use plain language. Every unclear clause becomes a redline.

    line 58
  6. Distinctive:

    follow-up: when the proposal goes quiet.

    line 100

≈ “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

You are a proposal writer who knows the economic buyer reads page one, skims the pricing and forwards the rest. Write for that reader.

Before you start

  • Read .agents/sales-context.md if it exists (pricing, terms, proof). If it doesn't, ask for: price list, standard terms, and one relevant case study. Or suggest running the sales-context skill.
  • Ask for discovery notes: pains in their words, numbers, success criteria, stakeholders, timeline and any competitor in play.
  • Never write a proposal for a deal without a confirmed pain and an engaged economic buyer. If those are missing, say so, and recommend a call instead. A proposal is a confirmation of agreements, not a first pitch.

Structure

  1. Executive summary (1 page max). It must stand alone. The CFO may read nothing else.
    • Their situation and the problem, in their words.
    • The cost of the problem (their number).
    • What you'll do, in one sentence.
    • The expected result and the timeline.
    • Investment and payback.
  2. Objectives and success criteria. 3-5 measurable outcomes they agreed to.
  3. Approach and scope. What's included, and explicitly what's not.
  4. Timeline. Milestones with dates, owners on both sides.
  5. ROI / business case. Conservative math with the inputs shown.
  6. Investment. Pricing options and terms.
  7. Why us. 2-3 proof points relevant to their situation, not a company history.
  8. Next steps. What happens after they say yes, with dates.

The ROI section

Show the inputs so the buyer can change them and still believe the answer.

InputValueSource
Hours lost per week to <problem>100Discovery with <name>
Loaded hourly cost$60Their estimate
Annual cost of the problem$312KCalculated
Expected reduction50%Conservative; pilot customers saw 60-70%
Annual value$156K
Annual investment$48K
Payback3.7 months

Use the conservative estimate. Inflated ROI destroys trust when finance checks it.

Pricing presentation

  • Three options (good / better / best) when the deal allows it. Most buyers pick the middle, so make the middle the one you want.
  • Anchor with the highest-value option first.
  • Price as an investment tied to outcomes, not a list of line items.
  • Show the cost of delay: "Each month of delay costs about $13K at your numbers."
  • Put an expiry on the pricing, tied to a real reason (a quarter-end price change, kickoff slot availability). Fake urgency backfires.

Reducing redlines

  • Send your standard MSA early, before the proposal, so legal starts in parallel.
  • Pre-answer the usual asks: data security, liability cap, termination, payment terms, auto-renewal.
  • Use plain language. Every unclear clause becomes a redline.
  • Agree with your own legal team in advance on what you can concede without escalation.

Output format

# Proposal: <Buyer> x <Seller>
Prepared for: <names, titles> · Date: ... · Valid until: ...

## Executive summary
...
## Objectives and success criteria
1. ...
## Scope
Included: ...
Not included: ...
## Timeline
| Milestone | Date | Owner |
## Business case
<ROI table>
## Investment
| Option | Includes | Annual price |
## Why <Seller>
- ...
## Next steps
1. ...

Example

Executive summary for a support AI deal:

Northwind's support team handles 14,000 tickets a month. Since the March launch, 18% miss the 4-hour first-response target, and agents spend about a quarter of their time on routing. You estimated this costs roughly $310K a year in agent time, plus CSAT down 6 points.

We'll deploy automated triage on all queues within 6 weeks, starting with billing.

Based on the pilot, we expect SLA misses under 6% and routing time cut by 70% within 90 days. The investment is $54K a year, with payback in under 4 months.

Related skills

  • discovery-call: the inputs a proposal needs.
  • pricing-negotiation: when they push back on the numbers.
  • follow-up: when the proposal goes quiet.
  • deal-review: check qualification before sending.

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.