client-proposal-generator
Skill378 starsChanged 52 days agoMITView on GitHub
Generates full consulting proposals from a brief. Input client name, problem description, and rough scope. Outputs proposal.md with executive summary, problem statement, proposed approach, timeline, team, pricing tiers, and terms. Researches client company for personalization. Multiple pricing models. Professional formatting matching consulting standards.
In this repository229 other files it gives its agents.
- accessibility-auditorSkill
- agent-armySkill
- agent-eval-harnessSkill
- agent-swarm-deployerSkill
- agent-team-builderSkill
- agent-to-agentSkill
- ai-coding-guardrailsSkill
- ai-readiness-assessmentSkill
- animateSkill
- api-documentation-writerSkill
- api-endpoint-scaffolderSkill
- api-load-testerSkill
- athlete-social-media-managerSkill
- before-you-buildSkill
- bi-measure-builderSkill
- board-deck-generatorSkill
- bookkeeping-closeSkill
- bracket-predictorSkill
- brand-consistency-checkerSkill
- brand-voice-analyzerSkill
- browser-test-loopSkill
- budget-optimizerSkill
- cash-flow-forecasterSkill
- champion-identifierSkill
- churn-autopsySkill
- claude-design-criticSkill
- claude-design-system-architectSkill
- claude-landing-composerSkill
- claude-md-writerSkill
- client-health-dashboardSkill
- code-review-proSkill
- cold-email-sequence-generatorSkill
- color-palette-extractorSkill
- commercial-lease-analyzerSkill
- company-announcement-writerSkill
- competitor-content-analyzerSkill
- competitor-intel-agentSkill
- competitor-price-trackerSkill
- compliance-checkerSkill
- contact-hunterSkill
- content-repurposerSkill
- context-budgetSkill
- contract-analyzerSkill
- contract-redlinerSkill
- conversation-archaeologistSkill
- cowork-calendar-defragSkill
- cowork-contract-renewal-radarSkill
- cowork-data-room-builderSkill
- cowork-deal-roomSkill
- cowork-expense-auditSkill
- cowork-folder-organizerSkill
- cowork-hiring-screenerSkill
- cowork-home-inventorySkill
- cowork-inbox-triageSkill
- cowork-invoice-chaserSkill
- cowork-medical-bill-auditorSkill
- cowork-qbr-builderSkill
- cowork-rfp-responseSkill
- cowork-sop-writerSkill
- cowork-tax-prep-organizerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 32
Add terms and conditions. Insert the standard block, adjusting scope, IP, and assumptions to the engagement.
- Very specific: line 34
Run the quality check. Verify accuracy, consistency, no placeholders, and no fabricated facts.
- Distinctive: line 39
Never fabricate case studies, team bios, credentials, or client facts.
- Distinctive: line 40
If web research yields nothing, proceed without personalization and flag it.
- Distinctive: line 41
Leave no placeholder markers in the delivered document.
≈ “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.
Files
Client Proposal Generator
Transform a brief description into a complete, professionally formatted consulting proposal (proposal.md), researching the client company for personalization and structuring the document with proven consulting frameworks.
Contents
references/inputs.md-- Required and optional inputs, defaults, one-liner extractionreferences/research.md-- Client web research checklist and research brief templatereferences/problem-and-solution.md-- Problem decomposition, methodology selection, phase and deliverable templatesreferences/timeline.md-- Duration estimation and timeline formatreferences/team.md-- Role framework and team section formatreferences/pricing.md-- Pricing models, 3-tier framework, rate benchmarks, calibration, payment termsreferences/terms.md-- Standard terms and conditions blockreferences/output-template.md-- Full proposal document structure and delivery summaryreferences/tone-and-quality.md-- Tone variants, pre-delivery quality checklist, error handling
Workflow
- Gather input. Collect required fields (client name, contact, problem, firm name) and optional fields; infer the rest from context. See
references/inputs.md. - Research the client. Pull company overview, recent news, tech signals, industry context, and competitors; organize into a research brief. See
references/research.md. - Frame the problem and design the solution. Decompose into root problem, symptoms, business impact, stakeholders, and urgency; select a methodology and define phases and deliverables. See
references/problem-and-solution.md. - Construct the timeline. Estimate duration, lay out phases with milestones, and state dependencies and assumptions. See
references/timeline.md. - Compose the team. Map roles and allocations; use placeholder names if none provided and never fabricate credentials. See
references/team.md. - Build pricing. Select a model (default: 3-tier fixed), set tier prices from rate benchmarks or a supplied budget, and add payment terms. See
references/pricing.md. - Add terms and conditions. Insert the standard block, adjusting scope, IP, and assumptions to the engagement. See
references/terms.md. - Assemble and write the proposal. Combine all sections into the output structure and write the file. See
references/output-template.md. - Run the quality check. Verify accuracy, consistency, no placeholders, and no fabricated facts; match the selected tone. See
references/tone-and-quality.md. - Deliver and summarize. Write to the output path and present the delivery summary with personalization applied and review recommendations. See
references/output-template.md.
Guardrails
- Never fabricate case studies, team bios, credentials, or client facts. Omit rather than invent.
- If web research yields nothing, proceed without personalization and flag it.
- Leave no placeholder markers in the delivered document.
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.

