- Home
- Skills
- Agents & Orchestration
- Production Code Readiness Reviewer
Works with the AI Agents you already use
Production Code Readiness Reviewer
A rigorous production-readiness auditor that identifies logic defects, security risks, and test gaps in code changes.
$11.99
Production Code Readiness Reviewer
Example session with this skill installed
Review this PR diff for a new multi-tenant billing endpoint. Ensure it handles concurrent requests and doesn't leak data between accounts. [diff attached]
- Read your context and instructions
- Compiled the production code readiness
Verdict: REVISE BEFORE RELEASE (Score: 72/100)
Critical Findings
- Race condition in 'update_balance.go:42': Row-level locking missing on credit deduction.
- Data Leak: 'GET /billing/history' lacks tenant_id filter in the raw SQL query.
Action: Add transaction locks and tenant scoping.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Linter passes and green tests don't guarantee production safety. Small logic errors in authentication, database migrations, or concurrent paths often bypass standard CI/CD but cause catastrophic outages at scale.
What it does
- Analyzes git diffs and PRs for logic defects, race conditions, and edge-case failures.
- Identifies security boundary risks including injection, tenant isolation, and secret exposure.
- Evaluates database migration safety and backward compatibility for public APIs.
- Maps code changes against requirements to find missing acceptance criteria and test gaps.
- Provides a concrete Ship, Revise, or Block verdict based on a structured risk rubric.
Why this beats prompting it yourself
Generic prompts often focus on surface-level style or naming conventions. This skill follows a rigorous multi-step inspection framework that traces execution paths, evaluates architectural alignment, and enforces a severity-based scoring model that prioritizes production stability over personal preference.
Use cases
- Pre-merge review for mission-critical core services and sensitive auth modules.
- Assessing the regression risk of refactors in legacy codebases.
- Verifying database schema changes and rollback safety before deployment.
- Identifying missing failure-path tests for new feature implementations.
Known limitations
Cannot execute code or perform runtime analysis. Review is limited to one coherent change set at a time rather than global repository audits.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Cannot execute scripts or migrations. Limited to static analysis of supplied diffs. Designed for single coherent PRs or patches, not whole-repo architectural audits.
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
This skill has been used 1 time.
Trust & safety
Security scan
Security scan passed 3 months ago