- Home
- Skills
- Code Quality & Review
- CodeProMax
Works with the AI Agents you already use
CodeProMax
Turn technical debt into prioritized engineering initiatives, tech specs, and implementation-ready tickets.
$6
CodeProMax
Example session with this skill installed
Analyze this repository and show me the top improvement opportunities. Focus on performance and maintainability.
- Read your context and instructions
- Compiled the codepromax
- Generated the document
Illustrative example on a sample repository; your output depends on your own codebase.
I have completed a reconnaissance pass of the repository. Based on the file structure, dependency graph, and recent git history, I have identified 5 high-value engineering initiatives.
Initiative Register
| ID | Initiative | Problem | Evidence | Value | Effort |
|---|---|---|---|---|---|
| 001 | Redux to React Query Migration | Prop drilling and stale state in src/store/ | dashboard-slices.ts has 12 nested reducers with no cache invalidation. | High | Med |
| 002 | Component Memoization Audit | Excessive re-renders in heavy list views | InventoryTable.tsx re-renders 60+ children on simple sort toggle. | Med | Low |
| 003 | Barrel File Removal | Slow dev startup and circular dependencies | src/components/index.ts triggers 150+ unnecessary imports on load. | High | Med |
| 004 | Vitest Integration | Slow CI pipeline due to legacy Jest suite | tests/heavy-integration.test.js takes 45s per run. | Med | Low |
| 005 | API Error Boundary Strategy | Unhandled promise rejections in UI | AuthService.ts lacks consistent catch blocks for 401/403 errors. | Low | Low |
Analysis Summary
The primary bottleneck is the state management layer. The src/store/ directory shows significant complexity and frequent commits to fix state sync issues. Initiative #001 offers the highest ROI for both developer experience and runtime performance.
Next steps
- Run
create the initiative for #1to generate the full migration tech spec. - Run
expand #3if you want to see the dependency graph evidence for barrel file bloat. - Call
/code-pro-max review <branch>on your current work to check for these patterns.
InventoryTable.tsx
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Codebases accumulate technical debt that never gets prioritized because the business case is thin or the implementation path is vague. This skill bridges the gap by transforming raw repository evidence into structured engineering initiatives and implementation-ready tickets. It moves from discovery to execution without the usual manual overhead of writing specs and decomposing stories.
What it does
- Evidence-based discovery scans architecture, dependencies, and performance to find high-value technical debt.
- Automated prioritization ranks opportunities using impact, urgency, and effort scores.
- Document generation builds a full package including technical specs, ADRs, and stakeholder reports.
- Ticket decomposition breaks epics into individual, testable tickets that pass the INVEST gate.
- Branch operations provides automated code reviews and onboarding documentation for active branches.
How it works
- Use
analyze this repositoryto generate the initial initiative register and discovery report. - Run
create the initiative for #3to expand a specific recommendation into a full planning package. - Call
ticket-to-promptto convert a planned ticket into a structured build prompt for implementation. - Execute
/code-pro-max review <branch>to get an evidence-backed review of a specific diff.
Frameworks & tools
The skill uses standard shell tools for repository reconnaissance, including git, grep, and dependency manifest analysis. It outputs standard Markdown files and follows the AICraft prompt schema for build instructions.
Why this beats prompting it yourself
Generic prompts fail to connect high-level goals with specific lines of code. This tool enforces a strict evidence-before-initiative rule, ensuring every recommendation is backed by facts rather than hallucinations.
Use cases
- Auditing a legacy codebase to find the most critical architectural improvements.
- Converting a loose product epic into a concrete technical specification and set of Jira-ready tickets.
- Generating self-contained build prompts for other AI agents to execute.
- Automated peer review and onboarding for new feature branches.
Known limitations
Does not perform silent code implementation without explicit approval. Requires repository access to gather evidence. Missing data is marked with placeholders rather than assumed.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.
Requires repository access. Uses [PLACEHOLDER] for unknown data. Does not automatically commit code or open remote MRs. Multi-item scopes require manual validation of ticket coverage.
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 27 days ago
- Software
Git