vpe-review
$
npx mdskill add alirezarezvani/claude-skills/vpe-reviewPressure-tests engineering plans for throughput and operational health
- Evaluates delivery plans, hiring, and team structure for bottlenecks
- Uses DORA metrics and cycle time analysis tools
- Applies six diagnostic questions to identify risks and inefficiencies
- Returns actionable insights for optimizing engineering throughput
SKILL.md
.github/skills/vpe-reviewView on GitHub ↗
--- name: "vpe-review" description: "/cs:vpe-review <plan> — Throughput-first VP of Engineering interrogation of any plan that touches delivery, eng hiring, team structure, or production discipline. Use when cycle time balloons, DORA metrics slide, or before committing to an eng hiring wave or a reorg." --- # /cs:vpe-review — VPE Forcing Questions **Command:** `/cs:vpe-review <plan>` The throughput-first VPE pressure-tests any plan touching eng operations. Six questions before any delivery commitment, eng hiring expansion, team restructure, or production-discipline change. ## When to Run - Before quarterly delivery commitment (sprint planning, OKR review) - Before approving an eng hiring plan - Before restructuring eng teams (splitting/merging squads, adding tribes) - Before deciding whether to hire a VPE separately from CTO (or merge them) - When production incidents are increasing - When sprint velocity is dropping but everyone says "we're working hard" ## The Six VPE Questions ### 1. What's the cycle time, and where does work wait? **No DORA, no diagnosis.** - Lead Time for Changes is the single best health metric - If you can't decompose cycle time into stages, you can't fix the bottleneck - Run `delivery_throughput_analyzer.py` ### 2. What's the DORA performance level on all 4 metrics? **One Elite metric and three Lows = bad. Four Highs = healthy.** - Deployment Frequency, Lead Time, MTTR, Change Failure Rate - The worst metric defines overall level - Fix lead time first; everything else follows ### 3. Where is the hiring funnel leaking? **"Can't find good engineers" is wrong.** - Specific stage is over-filtering OR top-of-funnel volume is too low OR offer-to-accept is broken - Run `eng_hiring_funnel_calculator.py` - If offer-to-accept < 70%, comp is below market or close discipline is weak ### 4. Is the team structure healthy for the headcount? **5-9 ICs per squad; 5-8 ICs per EM; 4-6 EMs per director.** - Run `eng_team_structure_designer.py` - Manager-trigger fires when 5+ ICs have no dedicated EM - Director-trigger fires when 3+ EMs report directly to VPE/CTO ### 5. What's the production discipline maturity? **Level 1-5; aim for Level 3 at growth stage.** - On-call rotation ≥ 6 people - Severity-defined incident response with blameless postmortems - SLOs on customer-facing services (pair with `engineering/slo-architect/`) - Continuous deployment OR scheduled — not "usually one, sometimes the other" ### 6. Are we adding a VPE separately, or is CTO doing both? **If CTO is spending > 50% on management vs strategy, VPE is needed.** - Or: VPE complement when CTO is co-founder more comfortable with strategy - VPE owns operating model; CTO owns architecture - At small scale (< 20 eng), one person can do both ## Workflow ```bash # 1. Delivery throughput python ../../../skills/vpe-advisor/scripts/delivery_throughput_analyzer.py sprint_metrics.json # 2. Hiring funnel python ../../../skills/vpe-advisor/scripts/eng_hiring_funnel_calculator.py funnel.json # 3. Team structure python ../../../skills/vpe-advisor/scripts/eng_team_structure_designer.py team.json ``` ## Output Format ```markdown # VPE Review: <plan> **Date:** YYYY-MM-DD ## The Decision Being Made [throughput | hiring | structure | production | VPE-vs-CTO] ## Delivery Throughput (if applicable) - DORA overall: Elite / High / Medium / Low - Worst metric: <DF | LT | MTTR | FR> - Bottleneck: <stage> (X% of cycle time) - Top fix: <action + owner> ## Hiring Funnel (if applicable) - End-to-end conversion: X% - Weakest stage: <stage> - Pipeline gap: +N candidates needed - Top fix: <specific action> ## Team Structure (if applicable) - Recommended: <informal pods / squads / tribes> - Manager trigger fired: yes/no - Director trigger fired: yes/no - Action: <hire EM | hire director | split squad> ## Production Discipline (if applicable) - Current maturity level: 1-5 - Next practice to add: <specific> - SLO coverage: X / Y services ## Verdict 🟢 SHIP | 🟡 SHARPEN | 🔴 BLOCK ## Next Steps [3 concrete actions] ``` ## Routing - `/cs:cto-review` — for architectural causes of throughput problems - `cs-chro-advisor` agent — for hiring funnel comp/leveling issues - `/cs:cfo-review` — for cost-per-hire envelope and eng budget - `/cs:ciso-review` — for production discipline + compliance overlap - `/cs:decide` — log the verdict - `/cs:freeze 30` — on multi-year hiring commitments ## Related - Agent: [`cs-vpe-advisor`](../../agents/cs-vpe-advisor.md) - Skill: [`vpe-advisor`](../../../skills/vpe-advisor/SKILL.md) - Adjacent: `../../../../engineering/slo-architect/`, `../../../../engineering/feature-flags-architect/`, `../../../../engineering/chaos-engineering/` --- **Version:** 1.0.0
More from alirezarezvani/claude-skills
- a11y-auditAccessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
- ab-test-setupWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
- ad-creativeWhen the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
- adversarial-reviewerAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
- aeoAnswer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
- agent-designerUse when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
- agent-protocolInter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.
- agent-workflow-designerDesign production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.
- agenthubMulti-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.
- agile-product-ownerAgile product ownership for backlog management and sprint execution. Covers user story writing, acceptance criteria, sprint planning, and velocity tracking. Use when writing user stories, creating acceptance criteria, planning sprints, estimating story points, breaking down epics, or prioritizing the backlog.