Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyzes RFP responses for coverage gaps, builds competitive feature matrices, and plans proof-of-concept engagements for pre-sales engineering
.claude/skills/borghei-sales-engineer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 124% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 333% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 135% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 173% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 234% | 0% |
The agent operates as an expert sales engineer, delivering technical discovery, tailored demonstrations, RFP responses, proof-of-concept management, competitive positioning, and technical objection resolution throughout the sales cycle.
Before generating, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
markdown# Technical Discovery: [Company Name] ## Company Overview - Industry: [Industry] - Size: [Employees] - Tech maturity: [Low/Medium/High] ## Current State - Systems: [List of current tools and platforms] - Pain points: [Specific problems with current approach] - Workflows: [Key processes affected] ## Requirements ### Must Have 1. [Requirement with measurable criteria] 2. [Requirement with measurable criteria] ### Nice to Have 1. [Requirement] ## Technical Environment - Cloud: [AWS/GCP/Azure/On-prem/Hybrid] - Languages: [Languages and frameworks] - Integrations needed: [Systems to connect] ## Success Criteria - [Metric 1]: [Specific target] - [Metric 2]: [Specific target] ## Timeline - Decision: [Date] - Implementation: [Date] - Go-live: [Date]
markdown# Demo Plan: [Company Name] ## Attendees | Name | Role | Top Priority | |------|------|-------------| | [Name] | [Role] | [What they care most about] | ## Agenda (60 min) 1. Discovery recap (5 min) 2. Solution overview (10 min) 3. Use case demonstrations (30 min) 4. Q&A (10 min) 5. Next steps (5 min) ## Use Cases to Demo 1. [Use case] -> addresses [specific pain point from discovery] 2. [Use case] -> addresses [specific pain point from discovery] ## Competitive Differentiators to Highlight - vs [Competitor]: [Our specific advantage] ## Anticipated Objections | Objection | Prepared Response | |-----------|------------------| | [Objection] | [Response with evidence] | ## Demo Environment - Instance: [URL] - Test data: [Description of realistic data loaded] - Features to show: [Prioritized list] ## Success Criteria - [What makes this demo successful -- e.g., "Champion confirms technical fit"]
1. CONNECT (5 min)
Recap discovery findings. Confirm priorities have not changed. Set agenda.
2. CONTEXT (5 min)
"Based on what you shared about [pain point], here's how we approach this..."
Frame the solution in their language.
3. SHOW (30 min)
Lead with the highest-impact use case ("wow" moment first).
Tell their story, don't feature-dump.
Map every feature shown to a specific pain point or requirement.
Pause for questions and involve the audience.
4. SUMMARIZE (5 min)
Recap value demonstrated. Address any open concerns.
Transition to trial or POC discussion.
5. CLOSE (5 min)
Define next steps with owners and dates.
Confirm timeline alignment with their evaluation process.markdown# POC Plan: [Company Name] ## Objectives - Primary: [Objective with measurable outcome] - Secondary: [Objective with measurable outcome] ## Success Criteria | Criteria | Target | How to Measure | |----------|--------|----------------| | [Criteria] | [Target] | [Method] | ## Scope ### In Scope - [Item] ### Out of Scope - [Item] -- rationale: [why excluded] ## Timeline | Phase | Duration | Dates | |-------|----------|-------| | Setup | 1 week | [Dates] | | Testing | 2 weeks | [Dates] | | Evaluation | 1 week | [Dates] | ## Check-in Schedule - Kickoff: [Date] - Weekly sync: [Day/Time] - Final review: [Date] ## Risks | Risk | Mitigation | |------|------------| | [Risk] | [Specific mitigation plan] |
| Category | Meaning | |----------|---------| | Full | Fully meets this requirement today | | Partial | Partially meets, with explanation of gap | | Roadmap | Planned for specific timeframe] | | Partner | Addressed via named partner integration] | | N/A | Not applicable to the solution |
| ID | Requirement | Response | Detail | |----|-------------|----------|--------| | R1 | SSO via SAML 2.0 | Full | Native SAML 2.0 support with all major IdPs | | R2 | On-premise deployment | Partial | Available as private cloud; bare-metal on roadmap Q3 | | R3 | Real-time analytics | Full | Sub-second dashboards with custom metrics | | R4 | HIPAA compliance | Roadmap | BAA available Q2 2026 |
The agent applies LAER for every technical objection:
| Objection | Response Approach | |-----------|-------------------| | "Too expensive" | Value justification with ROI calculation from their own metrics | | "Missing feature X" | Workaround demonstration + roadmap commitment with timeline | | "We use Competitor Y" | Differentiation on specific technical capabilities + migration ease | | "Security concerns" | Present certifications, architecture documentation, and pen test results | | "Implementation risk" | Reference similar customer success stories + support model details |
markdown# Battle Card: [Competitor Name] ## Quick Profile - Founded: [Year] | Employees: [Number] | Funding: $[Amount] ## Their Strengths - [Strength 1] - [Strength 2] ## Their Weaknesses - [Weakness 1] - [Weakness 2] ## Head-to-Head Comparison | Capability | Us | Them | |-----------|-----|------| | [Area] | [Our approach] | [Their approach] | ## Landmine Questions - "How does [Competitor] handle [area where they're weak]?" - "Ask them to show [capability they lack] in a live demo." ## Win Stories - [Customer] switched from [Competitor] because [reason]. Result: [outcome].
bash# Demo environment setup python scripts/demo_setup.py --customer "Customer Name" --use-cases uc1,uc2 # RFP analyzer python scripts/rfp_analyzer.py --rfp rfp.pdf --output requirements.csv # POC tracker python scripts/poc_tracker.py --customer "Customer Name" --status update # Competitive comparison python scripts/competitive_compare.py --competitor "Competitor Name"
| Problem | Root Cause | Resolution | |---------|-----------|------------| | Demo falls flat; audience disengaged | Feature dump instead of pain-based storytelling; wrong use cases selected | Always map demo flow to discovery findings. Lead with highest-impact use case. Pause every 10 minutes for interaction. If discovery was incomplete, reschedule with a mini-discovery first. | | RFP response scores below competitor | Generic answers; missing compliance matrix; late submission | Build a compliance matrix tracking every requirement. Use structured response categories (Full/Partial/Roadmap/Partner/N/A). Start executive summary with customer-specific value proposition. Complete draft 3+ days before deadline for review. | | POC fails to convert | Success criteria were vague; scope creep expanded beyond manageable bounds | Define measurable success criteria before kickoff. Lock scope with explicit in-scope/out-of-scope boundaries. Run weekly check-ins to catch drift early. If scope changes, renegotiate timeline. | | Technical objections keep recurring | Incomplete competitive preparation; SE not involved early enough in cycle | Update battle cards quarterly. Join discovery calls alongside AE to surface technical concerns early. Maintain a shared objection log with proven responses. | | Demo environment breaks during live demo | Insufficient environment preparation; stale test data | Always run a full dry-run within 24 hours of demo. Use isolated demo tenants with stable test data. Have a backup recording ready for critical demos. | | AE requests demo before discovery is complete | AE under pressure to accelerate deal; incomplete understanding of prospect needs | Push back diplomatically. Run a 15-minute technical pre-qualification call with the prospect. Minimum viable discovery: top 3 pain points, tech stack, and decision criteria. | | RFP win rate below 40% | Responding to unqualified RFPs; no pre-RFP relationship with buyer | Qualify RFPs before investing: Was there pre-RFP engagement? Do you know the decision criteria? Is the RFP wired for a competitor? Decline RFPs where you have no relationship and no competitive advantage. |
| Metric | Target | Measurement Method | |--------|--------|--------------------| | Demo-to-advance rate | 70%+ | Deals advancing to next stage after demo / Total demos delivered | | POC conversion rate | 60%+ | POCs resulting in proposal or closed-won / Total POCs | | RFP win rate | 45%+ | RFPs won / RFPs submitted (qualified only) | | Technical win rate | 80%+ | Deals where technical evaluation was won / Total technical evaluations | | Demo NPS / feedback score | 4.0+ out of 5 | Post-demo survey from attendees | | Time-to-demo | Under 5 business days from request | Days from demo request to demo delivery | | RFP response time | 100% on-time submission | Submissions before deadline / Total RFPs | | Battle card currency | Updated within last 90 days | Percentage of battle cards reviewed in current quarter |
In Scope:
Out of Scope:
Limitations:
| Integration | Direction | Purpose | Handoff Artifact | |-------------|-----------|---------|-----------------| | Account Executive | AE -> SE | Demo requests, discovery context, deal strategy alignment | Discovery notes, stakeholder map, competitive landscape, demo requirements | | Solutions Architect | SE -> SA | Complex enterprise deals requiring deep architecture design | Technical discovery output, integration requirements, security assessment needs | | Product Team | SE -> Product | Feature gaps surfaced during evaluations, competitive intel | Feature request log, RFP gap analysis, competitive capability comparison | | Customer Success Manager | SE -> CSM | Technical context for post-sale onboarding | POC results, technical configuration, integration specs, known limitations | | Sales Operations | SE -> Ops | Technical win/loss data, demo activity metrics | Technical win/loss reports, demo conversion data | | Marketing | Bidirectional | Technical content needs (whitepapers, solution briefs); competitive positioning | Content requests, competitive analysis, technical differentiation points | | Engineering | SE -> Eng | Escalation for deep technical questions; product feedback | Technical escalation tickets, product feedback summaries |
Workflow Handoff Protocol:
references/demo_playbook.md -- Demo best practicesreferences/objections.md -- Objection handling guidereferences/competitive.md -- Competitive intelligencereferences/rfp_templates.md -- RFP response templates| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 25,044 | 17,196 | -31% | 1 | 1 | 0% | 3,663 | 6,202 | +69% | 0 | 0 | — |
case-02 | fail→fail | 22,979 | 24,475 | +7% | 1 | 1 | 0% | 3,450 | 7,404 | +115% | 0 | 0 | — |
case-03 | fail→fail | 17,870 | 18,639 | +4% | 1 | 1 | 0% | 2,455 | 6,149 | +150% | 0 | 0 | — |
case-04 | fail→pass | 19,707 | 17,674 | -10% | 1 | 1 | 0% | 2,757 | 6,164 | +124% | 0 | 0 | — |
case-05 | fail→pass | 6,581 | 5,858 | -11% | 1 | 1 | 0% | 1,045 | 4,524 | +333% | 0 | 0 | — |
case-06 | fail→pass | 15,791 | 11,868 | -25% | 1 | 1 | 0% | 2,170 | 5,102 | +135% | 0 | 0 | — |
case-07 | fail→fail | 12,171 | 12,468 | +2% | 1 | 1 | 0% | 1,869 | 5,362 | +187% | 0 | 0 | — |
case-08 | pass→pass | 19,684 | 11,550 | -41% | 1 | 1 | 0% | 2,866 | 5,141 | +79% | 0 | 0 | — |
case-09 | fail→pass | 16,065 | 18,639 | +16% | 1 | 1 | 0% | 2,216 | 6,039 | +173% | 0 | 0 | — |
case-10 | fail→pass | 12,539 | 12,545 | +0% | 1 | 1 | 0% | 1,601 | 5,348 | +234% | 0 | 0 | — |
case-11 | pass→pass | 7,152 | 6,413 | -10% | 1 | 1 | 0% | 1,014 | 4,419 | +336% | 0 | 0 | — |
case-12 | fail→pass | 12,016 | 10,896 | -9% | 1 | 1 | 0% | 1,738 | 5,086 | +193% | 0 | 0 | — |
case-13 | pass→pass | 13,327 | 13,740 | +3% | 1 | 1 | 0% | 1,996 | 5,437 | +172% | 0 | 0 | — |
case-14 | pass→pass | 10,690 | 10,218 | -4% | 1 | 1 | 0% | 1,548 | 5,039 | +226% | 0 | 0 | — |
case-15 | fail→fail | 5,445 | 8,782 | +61% | 1 | 1 | 0% | 969 | 5,046 | +421% | 0 | 0 | — |
case-16 | pass→pass | 12,186 | 19,990 | +64% | 1 | 1 | 0% | 1,728 | 6,337 | +267% | 0 | 0 | — |
case-17 | pass→pass | 9,628 | 13,668 | +42% | 1 | 1 | 0% | 1,409 | 5,540 | +293% | 0 | 0 | — |
case-18 | pass→pass | 10,429 | 13,903 | +33% | 1 | 1 | 0% | 1,526 | 5,546 | +263% | 0 | 0 | — |
case-19 | pass→pass | 11,263 | 9,988 | -11% | 1 | 1 | 0% | 1,583 | 4,852 | +207% | 0 | 0 | — |
case-20 | fail→fail | 18,528 | 11,256 | -39% | 1 | 1 | 0% | 2,691 | 5,248 | +95% | 0 | 0 | — |
case-21 | fail→pass | 17,179 | 6,049 | -65% | 1 | 1 | 0% | 2,838 | 4,399 | +55% | 0 | 0 | — |
case-22 | fail→pass | 19,545 | 8,428 | -57% | 1 | 1 | 0% | 3,034 | 4,790 | +58% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +36 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.