agentleFS
bookchaowalitbookchaowalit/platform-agent-skills/client-discovery-and-proposals/SKILL.md

client-discovery-and-proposals

Skill0 starsChanged 9 days agoApache-2.0View on GitHub

Turn a client need into a qualified opportunity, clear scope, proposal, pricing options, and delivery handoff for Solo Empire. Use when preparing discovery questions, statements of work, estimates, proposals, or follow-up after a hired project conversation.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the proposal as draft until the user authorizes external sending.

    line 19
  2. Distinctive:

    No access to required data or systems → state the dependency and provide a discovery or setup phase.

    line 24
  3. Distinctive:

    No credible proof for a requested outcome → reduce the promise to an observable deliverable.

    line 25

≈ “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

Client Discovery and Proposals

Convert vague interest into a decision-ready offer without overpromising or doing unpaid custom delivery.

Discovery workflow

  1. Gather the available context from the opportunity, CRM, messages, and prior work. Mark assumptions and protect personal or confidential data.
  2. Clarify the desired business outcome, current pain, users, workflow, constraints, deadline, budget range, decision maker, approval process, and definition of success.
  3. Qualify fit against Solo Empire capabilities, evidence, capacity, urgency, access to the client, and expected value. Do not claim experience or results that are not verified.
  4. Offer the smallest useful engagement. Define deliverables, exclusions, client responsibilities, dependencies, milestones, acceptance criteria, change handling, and support boundary.
  5. Prepare proposal options when useful: a focused starting scope, a fuller scope, and explicit tradeoffs in time, risk, and price.
  6. Draft a proposal with executive summary, outcome, approach, scope, timeline, assumptions, risks, price and payment milestones, proof, validity period, and a clear next step.
  7. Review for feasibility, margin, privacy, security, and contractual risk. Use approved legal templates or obtain professional advice for legal or tax questions.
  8. Keep the proposal as draft until the user authorizes external sending. Log the opportunity, next action, owner, and follow-up date in the appropriate CRM or dashboard.

Decision rules

  • Vague request → ask the fewest questions that materially change scope, price, or feasibility.
  • No access to required data or systems → state the dependency and provide a discovery or setup phase.
  • No credible proof for a requested outcome → reduce the promise to an observable deliverable.
  • Unpaid custom work → provide a bounded sample or paid discovery, not a hidden implementation project.
  • Legal, tax, employment, or regulated advice → flag the issue and route to the approved professional or compliance workspace.
  • External message or proposal → distinguish draft, approved, sent, and accepted states; never imply that a draft was sent.

Handoff

Once accepted, move the work into the client's own bookchaowalit-freelance/<client> repository, preserve the signed scope and assumptions, create milestones and acceptance checks, and identify the person responsible for client communication.

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.