
VPE Engineering Review
Pressure-tests engineering delivery, hiring, team structure and on-call plans like a VP of Engineering would.
- Repository
- alirezarezvani/claude-skills
- Stars
- 29,149
- Licence
- MIT
- Files
- 1 file
What it does
When installed, the agent reviews an engineering plan (for example a hiring wave, a team reorg, or a delivery commitment) through six pointed questions covering cycle time, DORA metrics, hiring funnel leaks, team sizing, production discipline and whether a separate VP of Engineering is needed. It then produces a structured report with a SHIP, SHARPEN or BLOCK verdict and next steps. The skill refers to helper Python scripts that analyse metrics files you supply, but the SKILL.md itself only describes the process and output format.
Great for
- Engineering managers or engineering leads preparing a sprint, OKR review or delivery commitment
- Founders or CTOs deciding whether to hire a VP of Engineering or approve a hiring plan or reorg
- Teams where incidents are rising or velocity is dropping and they want a structured diagnosis
Skip it if
- Teams without DORA or sprint metrics, since the skill's first rule is 'no DORA, no diagnosis' and its scripts need data files; the output would be generic advice (no legitimate use beyond general guidance)
- Legal, compensation or employment decisions that need HR or legal specialists, because the skill only gives an engineering-operations opinion
- Situations where the scripts are not installed in your environment, because the workflow calls Python files under a plugin path that may not exist outside the original plugin
Try asking
- “/c-level-agents:vpe-review we plan to hire 12 engineers next quarter across three new squads”
- “Review our reorg proposal: splitting the platform team into two squads with new managers”
- “Our cycle time has doubled and incidents are up; run a VPE review on our delivery process”
- “Should we hire a separate VP of Engineering or keep the CTO doing both roles at our 25-engineer company?”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
vpe-review.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip vpe-review.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip vpe-review.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Provide real sprint metrics, hiring funnel numbers and team headcount in your request so the scripts have data to analyse rather than guessing.
- Treat the verdict as a structured prompt for discussion; the thresholds it cites (such as 70% offer-to-accept or 5-9 ICs per squad) are generic rules of thumb, not verified benchmarks.
- Read the scripts before running them, since the workflow executes Python files from the plugin path.
What's inside
- SKILL.md
Redistributed unmodified from alirezarezvani/claude-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.