agentleFS
Kikobazz123Kikobazz123/lordgen-competition-demo/.claude/skills/proposal-generator/SKILL.md

proposal-generator

Skill0 starsChanged 3 months agoMITView on GitHub

Turn score.json's top_opportunity into a concise business proposal, keeping the confidence caveats from research/scoring visible rather than smoothing them over. Use after opportunity-score has produced data/score.json.

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use cold-outreach and content-engine.

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.
  • vijpatel7Skill

    cold-outreach

    Write highly effective cold emails and LinkedIn messages to recruiters, hiring managers, founders, and engineers at target companies. Based on Ben Lang's proven cold outreach framework (Next Play). Use when the user wants to: (1) write a cold email to someone at a company they want to work for, (2) craft LinkedIn messages or InMail to recruiters or hiring managers, (3) reach out about unadvertised positions, (4) follow up on outreach or applications, (5) network with founders or executives for job opportunities, (6) prepare an outreach campaign to multiple companies. Triggers on: cold email, outreach, reach out to, contact recruiter, email founder, write to hiring manager, job email, networking email, LinkedIn message, InMail.

    Also in 3 projects that use this

  • indranilbanerjeeSkill

    content-engine

    Draft content in brand voice through a gated pipeline: blogs, ads, emails. Brief only → content-brief. \"write a blog post about X\"

    Also in 3 projects that use this

The file

Files
SKILL.md

Proposal Generator

Purpose

Turn the top-scored opportunity into a concise, judge/client-readable proposal: problem, proposed AI solution, expected impact, why it matters, recommended next step (LORDGEN_competition_demo.md §4). Structured data first, prose second — the prose must not say anything the structured data doesn't support.

Input

data/score.json → top_opportunity, plus its matching entry in scores for reasoning/risks/research_confidence. Cross-reference data/research.json for the supporting facts and docs/demo-business.md for the locked business identity.

Rule

Do not upgrade confidence. If research_confidence on the top opportunity is low, the proposal must say so explicitly — e.g. "evidence-suggested, not confirmed" — rather than writing persuasive copy that reads as if the problem were proven. This is the same rule as Phase 2/3 (CLAUDE.md §11): inference stays labeled as inference all the way downstream.

Required Output

Two artifacts:

  1. data/proposal.json — structured, for the execution-plan skill (Phase 5) to consume without re-parsing prose:
{
  "company": "",
  "problem": "",
  "evidence": [""],
  "opportunity": "",
  "score": 0,
  "tier": "",
  "reasoning": "",
  "proposed_solution": "",
  "workflow_concept": "",
  "expected_benefits": [""],
  "implementation_approach": "",
  "risks": [""],
  "confidence_caveat": "",
  "recommended_next_step": "",
  "approval_required": true
}

approval_required is true here — not because writing the document is consequential, but because presenting or sending it externally is, and that gate must stay visible in the artifact itself, not just in process.

  1. proposal.md (repo root, per docs/architecture.md's repo structure) — the human-readable version of the same content, for judges/handoff. Must include a visible confidence/evidence note; must not contradict data/proposal.json.

Validation (run before reporting results)

  • proposal.json.opportunity and .score exactly match score.json.top_opportunity.
  • proposal.json.company matches the locked business in docs/demo-business.md.
  • confidence_caveat is non-empty whenever research_confidence on the source opportunity was low or medium.
  • proposal.md does not contain overstatement language ("confirmed", "proven", "guaranteed") applied to the problem/evidence — scan for it.

Out of Scope

This skill does not populate the execution-plan template — that's execution-plan (Phase 5), which takes data/proposal.json as input.

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.