agentleFS
Sign inStart free
alebgl77alebgl77/claude-inc/skills/proposal-builder/SKILL.md

proposal-builder

Skill21 starsChanged 4 months agoMITView on GitHub

Builds proposals, quotes and offers that close — problem restatement in the client's words, scoped options, anchored pricing, timeline, terms and next step. Use when the user says "write a proposal", "send them a quote", "build an offer for X", or after a successful discovery or demo call.

10 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

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 2

    Distinctive

    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:

    After call-prep + the call itself.

    line 15
  2. Distinctive:

    Harvest the inputs: call notes, agreed pains, stated budget signals, decision process, deadline.

    line 19
  3. Distinctive:

    Timeline & responsibilities: start date, milestones, what you need from them (the hidden deal-killer).

    line 23

“Common” is measured: kept by at least 6 in 10 of the 9 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

Proposal Builder — Rainmaker

"A proposal is the call you already had, written down."

When to use

  • "Write the proposal for {client}"
  • "They asked for a quote"
  • "Turn these call notes into an offer"
  • After call-prep + the call itself; hand the notes over — the proposal should contain zero new ideas

Workflow

  1. Harvest the inputs: call notes, agreed pains, stated budget signals, decision process, deadline. Missing a pain confirmed by the client? Stop and say so — a proposal without confirmed pain is a brochure.
  2. Restate the problem in their words (verbatims from the call). This section wins or loses the deal.
  3. Design 3 options (Good/Better/Best): the middle one is the one you want them to pick; the small one makes it safe, the big one makes it look reasonable. Each option = outcome, scope bullets, what's excluded, price.
  4. Anchor value before price: quantify the cost of the problem or value of the outcome using THEIR numbers when given.
  5. Timeline & responsibilities: start date, milestones, what you need from them (the hidden deal-killer).
  6. Terms: validity date (7-14 days), payment schedule, the one guarantee you can honour. Flag anything for review-contract (legal) before sending.
  7. Close with a single next step: signature link / kickoff date / reply "option B" — one action, dated.
  8. Format: deliver as a clean markdown file ready for PDF/docx conversion.

Output format

## Proposal — {client} · valid until {date}
### 1. Where you are (your words)     ← verbatims
### 2. Where you want to be           ← outcome, quantified
### 3. Options
| | Good | Better ★ | Best |
|Outcome|...|...|...|
|Scope|...|...|...|
|Not included|...|...|...|
|Price|...|...|...|
### 4. Timeline & who does what
### 5. Terms (validity · payment · guarantee)
### 6. Next step: {one dated action}

Quality bar

  • Problem section uses the client's actual words from the call
  • Exactly 3 options; the target option is visibly the rational choice
  • Exclusions explicit — scope creep dies here
  • Price appears AFTER value, never in the first screen
  • Validity date + one single next step
  • Nothing promised that Legal or the product can't back

Example

Ask: "Proposal for the agency pilot we discussed — they said 'we lose 2 days a week on reporting'." Produced: proposal opening on that verbatim, 3 options (pilot / pilot+training ★ / full rollout), value anchor (2 days × loaded cost), 14-day validity, next step "reply with your option by Friday, kickoff Monday".

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