Senior FullStack Code Review
Senior-reviewer-style PR and diff review driven by your own team's knowledge base — correctness, security, data integrity, performance, design, reuse and readability, with evidenced findings every time.
$5
Works with the AI Agents you already use
Senior FullStack Code Review
Example session with this skill installed
review PR 123
- Read your context and instructions
- Compiled the senior fullstack code
Verdict: Changes requested
Blockers
src/wallet/service.js:88— withdrawal amount read from the request body, not re-validated against the ledger (S2) → scope the lookup to the caller's account and re-derive the amount server-side.
Should-fix
src/orders/repo.js:41— N+1 query inside a loop (P2) → batch into onefindMany.
Security pass
Confirmed
- SEC-1
src/wallet/routes.js:12— IDOR:GET /wallets/:idhas no owner scope. Fix: addWHERE user_id = :callerId.
Production impact: none until merged.
Connects securely to your tools. The creator never sees your data.
About this skill
An AI code-review skill that reviews pull requests the way your team's senior reviewers do. The review method is shared and built-in; what your team specifically knows — business rules, decisions (ADRs), conventions, recurring review comments — comes from a knowledge base you keep in your own repo.
What you get
- team-code-review — reviews a PR or working diff in ordered passes (correctness, data integrity, queues/crons, performance, design, reuse, input validation, readability, tests, your house rules). It runs a dedicated six-stage security pass on every review (map → hunt → challenge → record → verify → report), sweeps the whole diff for repeat instances of the same issue, and reports evidenced findings by severity (Blocker / Should-fix / Nit) with file:line and concrete fixes.
- team-code-review-setup — one-time setup per repo. It detects your stack and existing docs, asks for your knowledge base (or builds one with you from a template), can draft "house rules" from your team's own past PR review comments, and can configure optional read-only database access. It writes
.code-review/config.mdand.code-review/knowledge-base.mdfor the whole team to share.
Works with Claude Code, Codex, Cursor and any other agent that supports SKILL.md skills.
Source and license (MIT): https://github.com/AlisiaReveli/code-review-kit
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.
Needs the one-time team-code-review-setup pass (knowledge base) to apply your own business rules, conventions and house rules — without it, team-code-review falls back to generic rules only. Security verification only runs locally, never against staging or production.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 days ago
- Software
Git
Node.js
- Optional
- GitHub CLI (gh) - for house rulesRead-only DB MCP/CLI
Needs an AI coding agent that supports SKILL.md-style skills (Claude Code, Codex, Cursor, or anything installable via skills.sh).