API Design Reviewer

Systematic REST/GraphQL API review with P0-P3 prioritized findings, effort estimates, and a launch checklist.

Tested · Works

Test report

Verdict
Tested · Works
Score
8.4/10
Tested
Jul 15, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · ce08d16

Reviewed a deliberately sloppy 4-route Express file: a baseline pass already caught the blatant SQL injection and missing auth, but the skill's structured checklist additionally surfaced versioning, idempotency-key handling for the POST /orders endpoint, and rate limiting, then packaged everything into a prioritized P0-P3 report with effort estimates instead of a flat list. The frontmatter oversells gRPC coverage, though -- the body has zero gRPC-specific section (no streaming, proto-versioning, or service-definition checklist) despite GraphQL getting a full dedicated subsection.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 8/10
  • Docs & honesty 3/5

What API Design Reviewer does

Walks an API design or implementation through a fixed 10-section checklist (auth, resource design, errors, pagination, versioning, idempotency, performance, validation, docs, GraphQL specifics) and emits a structured report with critical/important/nice-to-have tiers, each finding scored P0-P3 with a time estimate. Triggers when designing, reviewing, or auditing REST/GraphQL/gRPC endpoints before a release.

How to install API Design Reviewer

git clone https://github.com/shahtuyakov/claude-setup
mkdir -p ~/.claude/skills
cp -r claude-setup/skills/api-design-reviewer ~/.claude/skills/api-design-reviewer

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger API Design Reviewer

  • /api-design-reviewer Systematic REST/GraphQL API review with P0-P3 prioritized findings, effort estimates, and a launch checklist.

It also activates on plain-language prompts like these:

  • Review my REST API endpoints for security and pagination issues.
  • Can you audit this GraphQL schema before we ship it to production?
  • Check my API design for versioning and idempotency gaps before launch.

Frequently asked questions

Is the API Design Reviewer skill free?
Yes. The skill itself is free from shahtuyakov/claude-setup. SkillProof publishes the install command and an independent test verdict at no cost.
Does API Design Reviewer work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Reviewed a deliberately sloppy 4-route Express file: a baseline pass already caught the blatant SQL injection and missing auth, but the skill's structured checklist additionally surfaced versioning, idempotency-key handling for the POST /orders endpoint, and rate limiting, then packaged everything into a prioritized P0-P3 report with effort estimates instead of a flat list. The frontmatter oversells gRPC coverage, though -- the body has zero gRPC-specific section (no streaming, proto-versioning, or service-definition checklist) despite GraphQL getting a full dedicated subsection.
What is the API Design Reviewer SkillProof Score?
8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.
How do I install API Design Reviewer?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use API Design Reviewer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.