proposal-sow
Skill39 starsChanged 6 months agoMITView on GitHub
Generates a Statement of Work once a proposal is verbally accepted. Invoked by /proposal sow <client>. Output: PROPOSAL-SOW-[Client].md.
In this repository14 other files it gives its agents.
- proposalSkill
- proposal-buildSkill
- proposal-casestudySkill
- proposal-compareSkill
- proposal-coverSkill
- proposal-followupSkill
- proposal-objectionsSkill
- proposal-pricingSkill
- proposal-quickSkill
- proposal-report-pdfSkill
- proposal-roiSkill
- proposal-scopeSkill
- proposal-summarySkill
- proposal-upsellSkill
The file
Files
Proposal SOW — Statement of Work Generator
Generates a Statement of Work once a proposal is verbally accepted. Invoked by /proposal sow <client>. Output: PROPOSAL-SOW-[Client].md.
Sections
- Parties & Effective Date — agency, client, start date
- Services & Deliverables — exact list with quantities/frequency (pull from the accepted proposal scope)
- Timeline & Milestones — dates and acceptance criteria per milestone
- Fees & Payment Terms — amount, schedule (e.g. 50% upfront / monthly on the 1st), late terms, what's billable
- Client Responsibilities — access, approvals, assets, response times
- Term & Termination — length, renewal, notice period, kill fee
- Exclusions & Change Orders — out of scope items and how changes are priced
- Confidentiality & IP — who owns deliverables, NDA reference
- Signatures — both parties, date
Rules
This is an operational document, not a sales pitch — be precise and unambiguous. Mirror the accepted proposal exactly. Flag with [HAVE A LAWYER REVIEW] that this is a template, not legal advice. Keep payment terms and termination crystal clear.
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
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.

