agentleFS
JakeschincariolJakeschincariol/closer-skill/contract-writer/SKILL.md

contract-writer

Skill33 starsChanged 11 days agoMITView on GitHub

Contract Writer. Creates the contract and sends it over for you, after your yes. Turns what was agreed on the call into a plain-English services agreement (services, fee, term, launch, payment, ownership, liability, signature lines), checks the fee against what was actually said on the call or in the proposal, writes a print-ready PDF, drafts the email to send it, and marks the deal won when the signed copy comes back. Use when the user says "write the contract", "send the agreement", "draft a services agreement", "send the paperwork", "they said yes", or "they signed".

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. GstMirabal/Token-Optimized-Agent-Pipeline★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository10 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are 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.

  • 2

    Very specific

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

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

    Read the call notes (/record-keeper timeline) and the proposal if there was one.

    line 33
  2. Very specific:

    Read any CHECK: line out loud to the user.

    line 37
  3. Distinctive:

    Ask: "Send this to Dana with the agreement attached?

    line 43
  4. Distinctive:

    Never sends the agreement without the user's yes for that exact email and attachment.

    line 65
  5. Distinctive:

    Never signs, or adds anyone's signature, name-as-signature or initials.

    line 66
  6. Distinctive:

    Never puts a price, discount or promise in the agreement that was not agreed.

    line 67
  7. Distinctive:

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

    line 75

≈ “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

contract-writer

The Contract Writer closes the loop the same day: the call ends, the agreement goes out within the hour while they still remember why they said yes.

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

python3 "${CLAUDE_SKILL_DIR}/contract.py" draft --deal harbor-lane-website \
    --services "A booking-ready website and a managed Google Ads campaign for Harbor Lane Dental." \
    --fee "\$399 per month, no setup fee, billed monthly." \
    --term "Month to month. Cancel anytime with 30 days notice." \
    --launch "Website live within 14 days of signing." --date "October 29, 2026"
python3 "${CLAUDE_SKILL_DIR}/contract.py" pdf --deal harbor-lane-website
python3 "${CLAUDE_SKILL_DIR}/contract.py" record --deal harbor-lane-website --approval "yes" --at 2026-10-29T14:31
python3 "${CLAUDE_SKILL_DIR}/contract.py" signed --deal harbor-lane-website --today 2026-11-02

Steps

  1. Read the call notes (/record-keeper timeline) and the proposal if there was one. Write the four deal sections from what was agreed, in plain words: Services, Fee, Term, Launch.
  2. contract.py draft. It adds the standard sections (payment, ownership, confidentiality, liability, changes) and signature lines, and writes closer/contracts/<company>-agreement.md and .html.
  3. Read any CHECK: line out loud to the user. The fee must be an amount that was said on the call or in the proposal. If it is not, ask; never "fix" it silently.
  4. Show the agreement. Ask: "Is this exactly what you agreed with Dana? Reply yes or no."
  5. contract.py pdf (headless Chrome), or the user opens the .html and prints to PDF.
  6. Draft the email: short, warm, what is attached, what happens next. "Hi Dana, great talking today! Here's the agreement for the $399 monthly plan. Sign whenever you're ready and we'll start Monday." Ask: "Send this to Dana with the agreement attached? Reply yes or no."
  7. On a yes: a Gmail draft with the PDF attached from the user's account, which the user sends (or sent through the Gmail connector right after that yes). Then contract.py record --approval "<their yes>".
  8. For e-signature, the user can upload the PDF to the e-sign tool they already use; this skill never signs for anyone. When the signed copy comes back, contract.py signed.

The user's own terms

The standard sections in contract.py (STANDARD) are a sensible starting point for a small services business, not legal advice. The first time, suggest the user has a lawyer read them once and edit STANDARD to match. Every agreement after that uses the same reviewed terms.

Example from the reel

At 2:31 PM, seventeen minutes after Dana's "too expensive", the Services Agreement between Your Agency and Harbor Lane Dental, dated October 29, 2026: a booking-ready website and a managed Google Ads campaign; $399 per month, no setup fee, billed monthly; month to month, cancel anytime with 30 days notice; website live within 14 days of signing. Sent as Harbor-Lane-Dental-Agreement.pdf with the subject "Your agreement with Your Agency". (Illustrative: both businesses are fictional.)

What it never does

  • Never sends the agreement without the user's yes for that exact email and attachment.
  • Never signs, or adds anyone's signature, name-as-signature or initials.
  • Never puts a price, discount or promise in the agreement that was not agreed.

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".
  • Contracts are templates, not legal advice.
  • Never invent a number, a result, a client 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.