agentleFS
Sign inStart free
jaskiel123jaskiel123/operators-brain/.claude/skills/proposal/SKILL.md

proposal

Skill0 starsChanged 5 months agoMITView on GitHub

Writes a client proposal or reply in your voice, using your real context and past wins.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use audit.

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.
  • OpenAISkill

    audit

    Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 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.

  • 5

    Very specific

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

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

    Ask which client/project this is for (or read it from the command, e.g.

    line 11
  2. Very specific:

    Read context/clients.md for that client: their situation, concerns, budget, decision-maker, history.

    line 12
  3. Very specific:

    Read context/about-you.md voice samples and context/about-business.md (offers, pricing, positioning).

    line 13
  4. Very specific:

    If past proposals exist in outputs/proposals/, read 1-2 recent ones to match structure and what closed.

    line 14
  5. Distinctive:

    Never invent client facts, prices, or commitments.

    line 30
  6. Very specific:

    If the client is not in context/clients.md, offer to add them first.

    line 33

“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

Goal

Produce a ready-to-send proposal or client reply written in the user's voice, grounded in real client context and what has worked before — not a generic template.

Process

  1. Ask which client/project this is for (or read it from the command, e.g. /proposal Brightwell).
  2. Read context/clients.md for that client: their situation, concerns, budget, decision-maker, history.
  3. Read context/about-you.md voice samples and context/about-business.md (offers, pricing, positioning).
  4. If past proposals exist in outputs/proposals/, read 1-2 recent ones to match structure and what closed.
  5. Confirm the essentials with the user in one short message: scope, price/range, deadline, any must-include. Do not stall — propose sensible defaults from context and let the user correct.
  6. Draft the proposal/reply:
    • Open referencing their actual situation (from context/clients.md), not "I hope this finds you well".
    • State the outcome and scope in the user's voice.
    • Price clearly. Mirror structure of past winning proposals.
    • Close with a single clear next step.
  7. Save to outputs/proposals/{{date}}-{{client}}.md and show it for review.

References

  • context/clients.md — the specific client.
  • context/about-you.md — voice.
  • context/about-business.md — offers, pricing.
  • outputs/proposals/ — past wins to mirror.

Rules

  1. Never invent client facts, prices, or commitments. Pull from context or ask. Mark assumptions clearly.
  2. Match the user's voice from their samples — not a generic "professional" tone.
  3. Ready-to-send, not a sketch. One clear next step, never multiple CTAs.
  4. If the client is not in context/clients.md, offer to add them first.

Improvement

  • Last updated: 2026-06-13
  • Next: learn which proposal structures closed vs stalled and weight toward winners.

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