agentleFS
phoenixvnphoenixvn/claude-code-agency/.claude/skills/proposal/SKILL.md

proposal

Skill0 starsChanged 7 months agoMITView on GitHub

Take a client brief and produce a professional project proposal with scope, timeline, deliverables, and investment. Each should present 2-3 approach options with pros/cons via AskUserQuestion. USER APPROVAL GATE — User selects preferred approach. Ask: "Ready to present to the client, or would you like to adjust anything?" On approval, suggest /kickoff to begin the project.

16 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, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 1

    Distinctive

    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 client brief from briefs/.

    line 11
  2. Very specific:

    Read template from .claude/docs/templates/proposal.md.

    line 28
  3. Distinctive:

    Ask: "Ready to present to the client, or would you like to adjust anything?"

    line 44

“Common” is measured: kept by at least 6 in 10 of the 14 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 — Generate Project Proposal

Take a client brief and produce a professional project proposal with scope, timeline, deliverables, and investment.

Prerequisites

A brief must exist in briefs/. If none found, redirect to /intake.

Instructions

Phase 1: Brief Analysis

Read the client brief from briefs/. Spawn the account-director agent to:

  • Analyze all requirements
  • Identify which departments and deliverables are needed
  • Estimate overall scope (Small / Medium / Large / Enterprise)
  • Flag any ambiguities or risks

Phase 2: Solution Design

Based on project needs, spawn relevant directors (in parallel if both needed):

  • technical-director (if development work): Propose tech stack, architecture approach, hosting
  • creative-director (if design/brand work): Propose creative approach, design methodology

Each should present 2-3 approach options with pros/cons via AskUserQuestion.

USER APPROVAL GATE — User selects preferred approach.

Phase 3: Proposal Draft

Read template from .claude/docs/templates/proposal.md. Spawn account-director to compile the proposal:

  • Executive summary
  • Understanding of requirements (show we listened)
  • Proposed solution with selected approach
  • Detailed scope of work by phase
  • Deliverables checklist
  • Timeline with milestones
  • Team composition
  • Investment (2-3 pricing tiers if appropriate)
  • Terms and next steps

Phase 4: Review

Present the complete proposal to the user. Save to deliverables/docs/[client-name]-proposal.md.

Ask: "Ready to present to the client, or would you like to adjust anything?"

On approval, suggest /kickoff to begin the project.

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.