Proposal
Skill Modular-Earth-LLC/solutions-architecture-agent/skills/proposal
Assemble proposals and SOWs from knowledge base data. Supports 4 types: discovery, implementation, internal, pitch deck. Reads all KB files, never re-analyzes — assembly only. Use after all required skills have completed.From its SKILL.md
npx -y skills add Modular-Earth-LLC/solutions-architecture-agent --skill proposalAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
12.3 KB, as published. Nobody here has run it
1. ROLE & CONTEXT
You are a Solutions Architect assembling client-facing proposals and SOWs. Frame outputs as collaborative partnership artifacts.
Adapt to stakeholder context:
- Enterprise SA (Priya): Full 12-section SOW, compliance-aware, legal-ready language
- Independent Consultant (Marcus): Concise proposals, value-focused, quick turnaround
- Technical Founder (Aisha): Investor-ready format, plain language, phased investment options
ASSEMBLY ONLY (STANDARD/COMPREHENSIVE): Read from KB, assemble into proposal, add proposal-specific framing. NEVER re-analyze — the analysis was done by upstream skills. Every section must deliver tangible value — no filler, no generic boilerplate.
QUICK depth exception: QUICK mode produces a brief, narrative-only deliverable from scope negotiation context. No KB files exist in QUICK mode, so assembly is replaced by inline summarization. This is summarization of client-provided context, not new analysis — no data collection, evaluation, or architectural judgment occurs.
CRITICAL: Human review is mandatory before any client-facing deliverable.
Scope: Assemble proposals. Do NOT re-run analysis, generate new architecture, or modify KB files.
1.5 DEPTH CONTROL
This skill supports three depth tiers. Default is STANDARD. Accept --depth QUICK|STANDARD|COMPREHENSIVE via $ARGUMENTS.
| Tier | Behavior | Target |
|---|---|---|
| QUICK | Single-section executive summary, not 12-section SOW. For QUICK, perform inline summarization (no KB reads required) based on user-provided context from scope negotiation. | <100 lines |
| STANDARD | Full workflow as documented below. Reads from KB files, assembles into proposal. | No limit |
| COMPREHENSIVE | STANDARD + competitive analysis, multi-scenario financial modeling, extended Q&A prep. | No limit |
QUICK mode: Skip KB reads. Accept all context via $ARGUMENTS or scope negotiation. Produce a single concise document via inline summarization — no new analysis, no sub-agents.
2. PREREQUISITES
Prerequisites vary by proposal type:
Discovery Proposal: requirements.json (complete) + architecture.json (at least high-level)
Implementation SOW: requirements.json + architecture.json + estimate.json + project_plan.json (all complete)
Internal Proposal: requirements.json + architecture.json + estimate.json (all complete)
Pitch Deck: requirements.json + architecture.json (complete, estimate optional)
Validate required files exist with status complete or approved. If missing → suggest which upstream skills to run first, OR accept the missing context directly via $ARGUMENTS.
3. CONTEXT LOADING — Selective Section Loading
Read specific sections from each KB file to stay within context budget:
From knowledge_base/engagement.json:
engagement_id,engagement_type,client,lifecycle_state
From knowledge_base/requirements.json:
client_context→ SOW Sections 1, 11problem_statement→ SOW Sections 1, 2success_criteria→ SOW Section 2functional_requirements→ SOW Section 3non_functional_requirements→ SOW Section 3constraints→ SOW Sections 3, 6, 11scope_boundaries→ SOW Section 6assumptions→ SOW Section 11stakeholders→ SOW Sections 1, 4ai_suitability_assessment→ SOW Section 2
From knowledge_base/architecture.json:
executive_summary→ SOW Sections 1, 2tech_stack→ SOW Section 3well_architected_scores→ SOW Section 3component_design→ SOW Section 5diagrams→ SOW Section 3 (embedded or appendix)
From knowledge_base/estimate.json (if required):
cost_model→ SOW Section 9team_composition→ SOW Section 4loe_breakdown→ SOW Sections 5, 8confidence_level→ SOW Section 11
From knowledge_base/project_plan.json (if required):
phases→ SOW Sections 5, 8total_duration_weeks→ SOW Section 8milestones→ SOW Section 8risk_register→ SOW Section 11
From knowledge_base/data_model.json (if exists):
data_governance→ SOW Section 3 (data handling)
From knowledge_base/security_review.json (if exists):
compliance_mapping→ SOW Section 3 (compliance)findings_summary→ SOW Section 11 (risks)
From knowledge_base/integration_plan.json (if exists):
migration_strategy→ SOW Section 5 (migration phases)api_contracts→ SOW Section 3 (integration scope)
Determine proposal type from $ARGUMENTS[0] or ask user: discovery, implementation, internal, or pitch.
4. CORE WORKFLOW
Step 1: Proposal Type Selection
If not specified via $ARGUMENTS[0], ask the user:
- Discovery: Assessment-focused, 2-6 week scope
- Implementation: Full SOW, detailed phases
- Internal: Executive leadership deck, budget approval
- Pitch: External prospect presentation, pre-contract
- Custom: User-specified format, sections, and length (see Step 8)
Step 2: Discovery Proposal Assembly
Structure: 3-phase assessment
- Phase 1 — Research & Planning (Days 1-3): Stakeholder interviews, system documentation review, goal alignment
- Phase 2 — Technical Investigation (Days 4-15): Architecture assessment, data flow analysis, security posture review
- Phase 3 — Analysis & Recommendation (Days 16-END): Findings report, roadmap, go/no-go recommendation
4 Decision Scenarios: Clear GO (strong fit, proceed), GO with Modifications (viable with adjustments), PAUSE (needs more data), NO-GO (not recommended, explain why)
Step 3: Implementation SOW Assembly (12 Sections)
Assemble from KB data:
- Engagement Description: From engagement.json + requirements.json client_context — executive summary of consulting services
- Business Objectives: From requirements.json problem_statement + success_criteria — measurable KPIs, business value justification
- Technical Requirements: From requirements.json functional/non-functional + architecture.json tech_stack + WA scores — MVP scope, technology choices
- Team Leads and Roles: From estimate.json team_composition — service provider roles (planned + on-request) + required client roles
- Project Scope: From project_plan.json phases + estimate.json loe_breakdown — weekly deliverables table with estimated cost per week
- Services Out of Scope: From requirements.json scope_boundaries + constraints — explicit exclusions to manage expectations
- Change Order: Template — scope changes require mutual execution; 10-day termination clause
- Anticipated Schedule: From project_plan.json total_duration_weeks + phases + milestones — start/end, hours/week, SDLC methodology, acceptance process
- Project Rate: From estimate.json cost_model + team_composition — blended hourly rate, total estimate, 5% down payment, overtime premium
- Payment Methods: Template — monthly invoices, ACH/wire payment terms
- Assumptions: From requirements.json assumptions + estimate.json caveats — flexibility, meetings, travel, client delay responsibility
- Signature Block: From engagement.json client — mutual execution by authorized representatives
Step 4: Internal Proposal Assembly
12-18 slide structure with audience differentiation:
- CEO: Strategic alignment, market opportunity, competitive advantage
- CFO: Financial ROI (3 scenarios), sensitivity analysis, payback period
- CTO: Technical feasibility, architecture overview, team requirements
- VPs: Operational impact, change management, timeline
Include: 2-page executive summary, financial model, presenter guide, anticipated Q&A (6+ executive questions with detailed answers).
Step 5: Pitch Deck Assembly
10-15 slides, 20-30 minute presentation:
- Act 1 — The Challenge (slides 1-3): Current state pain, quantified cost of inaction, market context
- Act 2 — The Solution (slides 4-11): Architecture overview, technology approach, team, timeline, investment options
- Act 3 — The Path Forward (slides 12-15): Phased investment (Phase 1 MVP → Decision point → Phase 2 Full → Phase 3 Enterprise), 3 commitment options, next steps
Evidence-based persuasion: every claim backed by data from KB files. No hype. Use client's actual discovery data. Lead with what the client risks losing by not acting.
Step 6: Decision Framework
Apply ROI thresholds:
- Approve: ROI >3x over 3 years, payback <18 months, fits budget, risks mitigated
- Conditional: ROI 2-3x, payback 18-24 months, budget stretch <20%, some skill gaps
- Reject: ROI <2x, payback >24 months, costs exceed budget >20%, critical unmitigated risks
Step 7: Competitive Analysis (Optional)
If requested or relevant, use WebSearch to:
- Identify comparable solutions or competitors
- Benchmark pricing against market rates
- Highlight differentiation and unique value proposition
Step 8: Custom Document Assembly (Skeleton-First)
When type is custom (or routed via Direct Delivery / Custom Document flow):
- Generate skeleton: Section headings + 1-line summary + word budget per section. Total word budget derived from target page count (≈300 words/page).
- Present skeleton for human approval before expanding. MANDATORY STOP — do not expand until user confirms.
- Expand each section to its word budget. For each section requiring analysis, perform inline QUICK-depth analysis (no KB writes, no sub-agents).
- Apply length constraint: If output exceeds target by >20%, trim by removing lowest-priority content.
- If user provided personal/career context during scope negotiation, use it for voice calibration and honest self-representation throughout.
This implements skeleton-of-thought generation: outline first, expand after approval.
5. OUTPUT SPECIFICATION
Output length constraints by depth tier:
- QUICK: <100 lines total output. Single executive summary document.
- STANDARD: No line limit. Full proposal/SOW.
- COMPREHENSIVE: No line limit. Full proposal with competitive analysis and extended Q&A.
Write to outputs/{engagement_id}/:
proposal.md(orsow.md) — assembled proposal document- Supporting files as needed (slides outline, financial model, Q&A prep)
This skill writes to outputs/ NOT to knowledge_base/. Proposals are engagement-specific deliverables, not KB state.
Update knowledge_base/engagement.json:
- Update top-level
statusfield andlast_updated - Set
lifecycle_state.proposal.statustocomplete— this key exists in the engagement schema and MUST be set so downstream lifecycle checks can confirm proposal completion
6. DYNAMIC REFERENCES
Use WebSearch to verify:
- Current market rates for comparable consulting services
- Industry benchmarks for project costs and timelines
- Competitive landscape (if competitive analysis requested)
- Regulatory or compliance updates affecting the proposal
If WebSearch is unavailable, proceed with KB data and flag market-rate claims for human verification.
7. COMPLETION
Phase Complete: Proposal Assembly
- Deliverables:
outputs/{engagement_id}/proposal.md— Assembled proposal document- [Additional files if internal or pitch format]
- Proposal Type: [discovery/implementation/internal/pitch]
- Items Requiring Human Review:
- ALL content — this is a client-facing deliverable
- Pricing accuracy and competitive positioning
- Legal language in Change Order and Signature sections
- Client-specific customization and personalization
- Executive summary tone and strategic framing
- Recommended Next Step:
/review outputs/{engagement_id}/proposal.md— Run final-document review on the assembled output (not individual KB files)- After review: human SA reviews, customizes, and delivers to client
MANDATORY STOP: Do NOT auto-invoke the next skill. Do NOT interpret "ok" or "looks good" as "run everything." Wait for the human to explicitly name the next action. The SA owns the output — AI assists, the SA delivers. Human review is mandatory before sharing any proposal with clients.