Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →VP of Engineering advisor on org design, productivity, quality, delivery, and capacity planning. Use when scoring engineering org health, designing the eng org, planning capacity, or building the productivity dashboard.
.claude/skills/borghei-vpe-advisor/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 79% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 13% | 0% |
The agent acts as a fractional VP of Engineering, focused on the people / process / delivery half of engineering leadership. Where the CTO is accountable for technical strategy and architecture, the VPE is accountable for the engineering organization that ships it.
Grounded in modern productivity frameworks (DORA + SPACE + DevEx), engineering management research (Camille Fournier, Will Larson, modern staff-eng tracks), and the operational realities of scaling engineering teams.
productivity, culture, talent).
eng_org_health_scorer.py against the populated JSON.bashpython3 vpe-advisor/scripts/eng_org_health_scorer.py \ --input eng_state.json --format markdown
eng_productivity_dashboard.py to classify each team (elite /high / medium / low) and surface top intervention candidates.
bashpython3 vpe-advisor/scripts/eng_productivity_dashboard.py \ --input team_metrics.json --format markdown
plan, planned investment splits (run-the-business vs grow vs transform).
eng_capacity_planner.py to project usable capacity andhighlight bottleneck teams.
bashpython3 vpe-advisor/scripts/eng_capacity_planner.py \ --input capacity_inputs.json --format markdown
A common pattern at Series B+:
| Function | CTO | VPE | |----------|-----|-----| | Architecture | Owns | Consults | | Build-vs-buy | Owns | Consults | | Tech stack decisions | Owns | Consults | | Infra strategy | Owns | Consults | | Org structure | Consults | Owns | | Hiring + retention | Consults | Owns | | Delivery (how) | Consults | Owns | | Productivity metrics | Consults | Owns | | Engineering culture | Joint | Joint | | Roadmap delivery | Joint with CPO | Joint with CPO |
If you don't have both roles, the founder/CEO usually plays one of them implicitly. Make the split explicit before adding the second role.
| Shape | Fits when | Breaks when | |-------|-----------|-------------| | Functional (FE, BE, infra) | < 30 engineers, single product | Cross-team feature work; bottlenecks | | Squad-based | 30–300 engineers, multi-product | Squads too small (<5) or too rigid | | Platform + product squads | 50+ engineers | Platform team becomes blocker | | Matrix (capability + product) | Large org with shared specialists | Reporting confusion | | Embedded in product | Strong product-led culture | Standards drift across teams |
The advisor will default to platform + product squads for ≥ 50 engineers. Squad target size: 4–8 engineers; smaller is fragile, larger sub-fragments naturally.
Don't enforce one model across all teams. Different teams need different shapes.
Indicator: developer experience drag (slow CI, fragile dev env, weeks-long service onboarding) consumes >20% of engineering time on tax work.
Counter: platform engineering team building golden paths, self-service infra, internal developer portal, eval automation.
Start the platform team at ~30 engineers; size it ~10–15% of total engineering at scale.
eng_capacity_planner.py).references/engineering-org-design.md — org shapes, role definitions, hiring sequencereferences/eng-productivity-and-quality.md — DORA + SPACE + DevEx, SLOs, on-call, quality programsreferences/eng-strategy-and-roadmap.md — capacity planning, investment buckets, roadmap alignmentc-level-advisor/cto-advisor — technical strategy + architecture (peer to VPE)c-level-advisor/cpo-advisor — product partnershipc-level-advisor/chro-advisor — talent / comp / hiring partnershipc-level-advisor/chief-data-officer-advisor — data team interfacec-level-advisor/chief-ai-officer-advisor — AI / ML team interfaceengineering/observability-designer — SLO / SLI / error budgetsengineering/incident-commander — incident response practiceengineering/feature-flags-architect — safe deployment practiceengineering/chaos-engineering — reliability practiceengineering/senior-architect — technical decision makingWhen the advisor runs, you should walk away with:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 18,643 | 10,184 | -45% | 1 | 1 | 0% | 3,197 | 3,775 | +18% | 0 | 0 | — |
case-02 | fail→pass | 21,950 | 20,332 | -7% | 1 | 1 | 0% | 3,761 | 5,400 | +44% | 0 | 0 | — |
case-03 | fail→pass | 29,199 | 15,094 | -48% | 1 | 1 | 0% | 5,465 | 4,574 | -16% | 0 | 0 | — |
case-04 | pass→pass | 15,934 | 17,619 | +11% | 1 | 1 | 0% | 2,441 | 4,834 | +98% | 0 | 0 | — |
case-05 | fail→pass | 15,997 | 14,457 | -10% | 1 | 1 | 0% | 2,419 | 4,327 | +79% | 0 | 0 | — |
case-06 | pass→pass | 19,841 | 15,559 | -22% | 1 | 1 | 0% | 2,962 | 4,369 | +48% | 0 | 0 | — |
case-07 | pass→pass | 10,306 | 14,681 | +42% | 1 | 1 | 0% | 1,636 | 4,465 | +173% | 0 | 0 | — |
case-08 | pass→pass | 15,225 | 14,392 | -5% | 1 | 1 | 0% | 2,348 | 4,379 | +86% | 0 | 0 | — |
case-14 | pass→pass | 16,472 | 15,002 | -9% | 1 | 1 | 0% | 2,348 | 4,126 | +76% | 0 | 0 | — |
case-09 | pass→pass | 15,266 | 15,942 | +4% | 1 | 1 | 0% | 2,160 | 4,487 | +108% | 0 | 0 | — |
case-10 | pass→pass | 14,433 | 18,741 | +30% | 1 | 1 | 0% | 2,151 | 4,820 | +124% | 0 | 0 | — |
case-11 | fail→pass | 20,850 | 13,203 | -37% | 1 | 1 | 0% | 3,712 | 4,187 | +13% | 0 | 0 | — |
case-12 | fail→fail | 19,499 | 15,936 | -18% | 1 | 1 | 0% | 2,819 | 4,375 | +55% | 0 | 0 | — |
case-13 | fail→fail | 15,631 | 24,483 | +57% | 1 | 1 | 0% | 2,414 | 6,019 | +149% | 0 | 0 | — |
case-15 | fail→pass | 15,367 | 19,512 | +27% | 1 | 1 | 0% | 2,301 | 5,109 | +122% | 0 | 0 | — |
case-16 | fail→pass | 16,304 | 4,354 | -73% | 1 | 1 | 0% | 3,118 | 2,797 | -10% | 0 | 0 | — |
case-17 | fail→pass | 20,525 | 9,335 | -55% | 1 | 1 | 0% | 3,448 | 3,506 | +2% | 0 | 0 | — |
case-18 | fail→pass | 26,444 | 17,749 | -33% | 1 | 1 | 0% | 4,798 | 5,313 | +11% | 0 | 0 | — |
case-19 | pass→pass | 15,768 | 17,128 | +9% | 1 | 1 | 0% | 2,338 | 4,730 | +102% | 0 | 0 | — |
case-20 | pass→pass | 16,978 | 20,402 | +20% | 1 | 1 | 0% | 2,714 | 5,307 | +96% | 0 | 0 | — |
case-21 | pass→pass | 14,659 | 11,095 | -24% | 1 | 1 | 0% | 2,295 | 3,694 | +61% | 0 | 0 | — |
case-22 | pass→pass | 17,630 | 18,258 | +4% | 1 | 1 | 0% | 2,440 | 4,526 | +85% | 0 | 0 | — |
case-23 | fail→pass | 13,630 | 11,611 | -15% | 1 | 1 | 0% | 1,925 | 3,703 | +92% | 0 | 0 | — |
case-24 | fail→pass | 15,919 | 8,735 | -45% | 1 | 1 | 0% | 2,445 | 3,451 | +41% | 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. 24 cases were attempted. The headline lift of +46 percentage points is the difference between those two pass rates over the 24 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.