app-deep-review
Deep analysis of an AinexSuite app with 6 parallel review agents. Use when you want comprehensive modernization recommendations for backend, frontend, UX, UI, AI enhancement, and security/performance. Includes severity ratings, code examples, and auto-fix suggestions.
npx skills add majiayu000/claude-skill-registry --skill app-deep-review --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill performs a deep, multi-domain review of a specified AinexSuite app, employing six parallel agents to assess Backend, Frontend, UX, UI, AI enhancement, and Security/Performance. It yields severity-rated findings with before/after code examples and optionally auto-fixes safe issues. It targets apps within the monorepo and validates the app name against a predefined list. It produces a metrics baseline and six structured agent prompts that focus on distinct aspects of the codebase.
How it works
- Accepts an app name and an optional --auto-fix flag; validates that apps/{app_name} exists and lists alternatives if missing.
- Collects pre-analysis metrics by running a set of shell commands to gather structure, lines of code, dependencies, and common usage patterns; formats results into a Markdown metrics baseline.
- Spawns six parallel review agents via the Task tool, each with a specialized prompt:
- Agent 1: Backend Modernization
- Agent 2: Frontend Modernization
- Agent 3: UX Review
- Agent 4: UI Review
- Agent 5: AI Enhancement Opportunities
- Agent 6: Security & Performance
- Each agent reports findings with a standardized schema (Severity, Location, Description, Before/After snippets, Why).
- After all agents finish, synthesizes a unified report with severity-based priorities and actionable checklists categorized as 🔴 Critical, 🟠 Important, 🟡 Suggested, 🟢 Positive.
- Identifies opportunities for moving code into shared packages as part of a package extraction step.
# App Deep Review Skill ## Overview This skill performs comprehensive deep analysis of any app in the AinexSuite monorepo. It uses extended thinking (ultrathink) and spawns 6 parallel sub-agents to review different aspects of the codebase, providing severity-rated findings with before/after code examples. ## Arguments - `app-name` (required): The name of the app to analyze (e.g., `notes`, `main`, `journal`) - `--auto-fix` (optional): Enable automatic fixing of safe, low-risk issues ## Available Apps | App | Port | Purpose | | -------- | ---- | --------------------- | | main | 3000 | Central dashboard | | notes | 3001 | Colorful notes | | journal | 3002 | Mood/reflections | | todo | 3003 | Task management | | health | 3004 | Body metrics | | album | 3005 | Memory curation | | habits | 3006 | Personal development | | mosaic | 3007 | Dashboard display | | fit | 3008 | Workout tracking | | projects | 3009 | Project management | | flow | 3010 | Visual automation | | subs | 3011 | Subscription tracking | | docs | 3012 | Rich documents | | tables | 3013 | Spreadsheets | | calendar | 3014 | Scheduling | | admin | 3020 | Admin dashboard | --- ## Execution Instructions ### Step 1: Parse Argu
- Overview
- Arguments
- Available Apps
- Execution Instructions
- Step 1: Parse Arguments
- Step 2: Collect Pre-Analysis Metrics
- Step 3: Spawn 6 Parallel Review Agents
- Step 4: Synthesize Agent Findings
- Step 5: Identify Package Extraction Candidates
- Step 6: Handle Auto-Fix Mode (if --auto-fix flag present)
- Step 7: Generate Final Report
- Extended Thinking Triggers
- Error Handling
- See Also
App structure metrics
find apps/{app}/src -name "*.tsx" 2>/dev/null | wc -l # Total TSX files
find apps/{app}/src -name "*.ts" 2>/dev/null | wc -l # Total TS files
find apps/{app}/src/components -name "*.tsx" 2>/dev/null | wc -l # Component count
find apps/{app}/src/hooks -name "*.ts" 2>/dev/null | wc -l # Custom hooks count
find apps/{app}/src/app/api -type d 2>/dev/null | wc -l # API route count
Code volume (lines of code)
find apps/{app}/src -type f \( -name "*.ts" -o -name "*.tsx" \) -exec wc -l {} + 2>/dev/null | tail -1
Dependencies count
jq '.dependencies | length' apps/{app}/package.json 2>/dev/nullWhat does the app-deep-review skill do?
Deep analysis of an AinexSuite app with 6 parallel review agents. Use when you want comprehensive modernization recommendations for backend, frontend, UX, UI, AI enhancement, and security/performance. Includes severity ratings, code examples, and auto-fix suggestions.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill app-deep-review --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.