
CTO Architecture Review
Pressure-tests an architecture or scaling plan with six CTO-style questions before you commit
- Repository
- alirezarezvani/claude-skills
- Stars
- 29,149
- Licence
- MIT
- Files
- 1 file
What it does
Once installed, the agent reviews a proposed architecture, platform choice, or scaling plan by asking six hard questions: where it breaks under 10x load, the top tech debt item and its cost, team ramp time, whether building beats buying, what the reliability targets are, and what security exposure it creates. It then fills in a structured review ending in a SHIP, SHARPEN, or BLOCK verdict. The skill can also run two bundled Python scripts that estimate tech debt and team scaling.
Great for
- Engineering leads deciding whether to approve a major architecture change or platform switch
- Teams weighing a rebuild against buying a vendor product
- Founders or managers planning to double the engineering team
Skip it if
- Tiny projects or prototypes where a formal six-part review adds overhead without value
- Decisions that need real financial or legal review: the skill only routes to other reviews and does not replace them
- Anyone expecting precise cost or capacity numbers without supplying their own data, since the answers depend on inputs the user provides
Try asking
- “/c-level-agents:cto-review Migrate our monolith to microservices for 10x traffic next year”
- “Review my plan to build our own auth system instead of buying a vendor”
- “Pressure-test our decision to switch from Postgres to a new distributed database”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
cto-review.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip cto-review.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip cto-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
- Give the plan concrete numbers (current load, growth rate, budget, team size) so the scaling and build-vs-buy answers are grounded rather than guessed.
- Ask the agent to run a load test or define SLOs when it says it does not know the scaling cliff.
- Check the bundled scripts' source before running them, since they execute on your machine and their inputs determine the output.
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.