BdM-15/capture-insights / skills/proposal-generator
proposal-generator
VerifiedShipley-methodology federal proposal outline and section drafter. USE WHEN the user asks to draft a proposal volume, build an outline from the proposal_instruction ↔ evaluation_factor traceability (UCF Section L/M or equivalent for non-UCF — FAR 16 task orders, FOPRs, BPA calls, OTAs, agency-specific formats), generate a compliance matrix, write win themes, draft an executive summary, propose FAB (Feature → Advantage → Benefit) chains, identify discriminators, or 'respond to this RFP'. Pulls requirements, evaluation factors, instructions, customer priorities, and pain points from the active Theseus workspace KG and produces an evidence-cited draft. Also ships govcon HTML render templates under assets/ — hand the rendered content off to the `huashu-design` skill for PPTX / PDF / animation export. Format-agnostic — never assumes UCF section labels are present. DO NOT USE FOR clause compliance auditing only (use compliance-auditor) or extracting new entities (use govcon-ontology + the Theseus pipeline).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.7 KB |
| assets/compliance_matrix.html | other | 2.7 KB |
| assets/compliance_matrix.md | markdown | 1.9 KB |
| assets/executive_summary.md | markdown | 1.1 KB |
| assets/fab_chain.md | markdown | 492 B |
| assets/one_pager.html | other | 1.5 KB |
| assets/slide_master.html | other | 1.9 KB |
| assets/theme_card.html | other | 1.3 KB |
| assets/theme_card.md | markdown | 850 B |
| assets/volume_outline.md | markdown | 653 B |
| evals/evals.json | config | 4.4 KB |
| references/anti_slop_checklist.md | markdown | 1.4 KB |
| references/critique_prompt.md | markdown | 797 B |
| references/govcon_design_tokens.md | markdown | 2.8 KB |
| references/page_budget_heuristics.md | markdown | 798 B |
| references/section_lm_traceability.md | markdown | 753 B |
| references/section_lm_visualization.md | markdown | 1.4 KB |
| references/shipley_glossary.md | markdown | 2.6 KB |
| references/win_theme_patterns.md | markdown | 1.1 KB |
references/shipley_glossary.md
View on GitHub# Shipley Glossary (Canonical Definitions)
These are the working definitions used across `proposal-generator`. Reject phrasing that doesn't conform.
## Discriminator
A capability **only we (or very few competitors) can credibly claim**, that the customer cares about. Must be:
- **Provable** with a proof point (past performance, certification, measurable result)
- **Relevant** to a `customer_priority` or `pain_point` in the workspace
- **Specific** — not "extensive experience" but "37 deployments of the same software stack on AFNET in the last 5 years"
## Win Theme
A short, verb-led, customer-language statement of how our solution wins. Format: `<verb> <customer outcome> by <our discriminator>`.
- Good: "Cut help-desk wait time in half by deploying our pre-trained AI triage model on Day 1"
- Bad: "Innovative AI-Powered Solutions"
## Hot Button
An **explicit** statement by the customer that something matters more than usual. Maps to `customer_priority` entity. Phrases: "paramount", "most critical", "highest priority", "non-negotiable".
## Ghost
Language placed in our proposal that **highlights a competitor's weakness without naming them**. E.g., if the incumbent has CPARS issues with cyber compliance: "We deliver continuous ATO compliance monitoring rather than annual recertification cycles."
## Proof Point
Concrete evidence backing a claim: contract number + outcome metric, certification + date, named personnel + clearance.
- Good: "Contract W912-1234, NAVAIR, $42M, 99.97% uptime over 36 months, CPARS Exceptional"
- Bad: "Extensive experience supporting DoD"
## FAB Chain (Feature → Advantage → Benefit)
- **Feature**: what the solution _is_ — capability, technology, process
- **Advantage**: what the feature _does_ better than alternatives
- **Benefit**: what the advantage _means to the customer_, in customer language
The Benefit must map to a `customer_priority` or `pain_point` entity. If it doesn't, the chain is decorative — discard it.
Example (good):
- F: Pre-trained AI triage model deployed on Day 1
- A: Skips 6-month training period typical for ML deployments
- B: Customer's mission readiness metric improves in Q1 instead of Q3 → maps to `customer_priority: Mission Readiness Priority`
Example (bad):
- F: Cloud-native architecture
- A: Scalable
- B: Better performance
(Benefit is a feature restated. Reject.)
## Compliance Matrix
Tabular L → M → C → Volume → Page traceability. Every row must trace to real entities. `GAP` is honest; invented links are not.
## Color Reviews (sequence)
Pink → Red → Gold → White. Skill output should be evaluated as if entering the next color review.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |