agentleFS
Sign inStart free
JakeschincariolJakeschincariol/closer-skill/proposal-writer/SKILL.md

proposal-writer

Skill33 starsChanged 11 days agoMITView on GitHub

Proposal Writer. Turns the call into a priced proposal the same day. Uses the prospect's own words from the call notes and replies, lays out what you will do, gives two or three clearly priced options (a full build, a monthly plan) with first-year totals, says what it pays back in one true line, recommends one, and ends with a single next step. Drafts the email; it goes out on your yes. Use when the user says "write a proposal", "send pricing", "put together a quote", "they asked for prices", "send options", or after a good call.

29 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use sop-writer, weekly-report and 5 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Dokkabei97Skill

    sop-writer

    Creates Standard Operating Procedures for repetitive tasks. Generates step-by-step documentation with checklists, decision trees, and responsibility assignments to eliminate single points of failure.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    weekly-report

    **WORKFLOW SKILL** — Generate weekly executive reports for the azd team. Pulls PR/issue/release data from GitHub, reads changelogs, combines with team notes, and produces a polished markdown report.

    Also in 5 projects that use this

  • akhilkannurSkill

    content-repurposer

    Also in 4 projects that use this

  • claude-office-skillsSkill

    meeting-notes

    >

    Also in 3 projects that use this

  • LangChainSkill

    linkedin-post

    Write a LinkedIn post based on research findings or a given topic. Use this skill when asked to create LinkedIn content, professional posts, or thought leadership pieces.

    Also in 3 projects that use this

  • seikaikyoSkill

    interview-me

    需求不明時的意圖萃取訪談：一次一題、每題附上自己的猜測、聽出「真正想要 vs 覺得應該要」，直到能預測使用者反應（約 95% 信心）才動工。適用：需求缺少對象 / 動機 / 成功標準 / 約束，或使用者點名「訪談我」「先確認一下」「我們確定嗎」。明確自足的指示、純資訊查詢、機械性操作不適用。

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Read the deal's history (/record-keeper timeline) and the call notes in closer/calls/.

    line 28
  2. Very specific:

    Write the options file: 1 to 3 options, each {"name", "setup", "monthly", "includes", "recommended"}.

    line 29
  3. Very specific:

    When they pick an option, /contract-writer.

    line 39
  4. Distinctive:

    Never invents a price, a discount, a result or a client story.

    line 51
  5. Distinctive:

    Never sends without the user's yes for that exact proposal.

    line 52
  6. Distinctive:

    Never gives more than 3 options or hides a fee.

    line 53
  7. Distinctive:

    Never invent a number, a result, a client, a review or a deadline.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 21 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-writer

A proposal that arrives the same afternoon, in the customer's own words, with a clear price and one recommended option, gets signed. One that arrives next week with five options does not.

${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).

python3 "${CLAUDE_SKILL_DIR}/proposal.py" draft --deal bluebird-ads \
    --options "${CLAUDE_SKILL_DIR}/options.example.json" --today 2026-10-29
python3 "${CLAUDE_SKILL_DIR}/proposal.py" record --deal bluebird-ads --approval "yes" --at 2026-10-29T16:00

Steps

  1. Read the deal's history (/record-keeper timeline) and the call notes in closer/calls/.
  2. Write the options file: 1 to 3 options, each {"name", "setup", "monthly", "includes", "recommended"}. Prices come from the user, never from you. Recommend one at most.
  3. proposal.py draft. It writes closer/proposals/<company>.md with their words, an options table with first-year totals, the payback line from me.value_line, a next step and a 14-day valid-until date.
  4. Fill every [Claude: ...]: "What we'll do" in 3 to 5 plain lines with dates. Use their words for their problem. record refuses while any placeholder is left.
  5. Show it. Ask: "Send this proposal to Priya? Reply yes or no."
  6. On a yes: a Gmail draft with the proposal (pasted in, or attached as a PDF) from the user's account, which the user sends (or sent through the Gmail connector right after that yes). Then proposal.py record --approval "<their yes>".
  7. When they pick an option, /contract-writer.

Example

Priya Shah at Bluebird Pet Spa replied, "Maybe! Can you send me prices?" The proposal opens with that line, then two options from options.example.json: Full build, $2,500 setup, $2,500 in the first year; Monthly plan (recommended), $399/month, $4,788 in the first year, no setup fee, cancel anytime. It closes with "Reply with the option you want and I'll send the agreement the same day." (Illustrative: Bluebird Pet Spa is fictional.)

What it never does

  • Never invents a price, a discount, a result or a client story.
  • Never sends without the user's yes for that exact proposal.
  • Never gives more than 3 options or hides a fee.

Consent and truth

  • Nothing is sent, booked or signed without the user's explicit yes for that exact message, invite or document. Claude drafts, the user says "yes", then it goes out from the user's own accounts. One yes per message. Never "yes to all".
  • Proposals are templates, not legal or financial advice.
  • Never invent a number, a result, a client, a review or a deadline. Fill in only what is true and ask when something is missing.

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