Multi-pass deep code review — security, quality, and test gaps
Scanned 9/2/2026
Install to Claude Code
npx -y skills add Smart-AI-Memory/attune-ai --skill deep-review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Deep Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/smart-ai-memory-deep-review)More formats (shields.io, HTML) on the badges page.
---
name: deep-review
description: Multi-pass deep code review — security, quality, and test gaps
---
# deep-review
Multi-pass code review that runs security, quality, and
test gap analysis on a target. Uses subagents to keep
context clean.
## Context (pre-computed)
```bash
git diff --name-only main...HEAD 2>/dev/null || git diff --name-only HEAD~3 2>/dev/null
```
## Instructions
Use `AskUserQuestion` to scope:
- Which path or files to review?
- Focus: security, quality, test gaps, or all three?
Then run three passes using the Task tool with subagents:
### Pass 1: Security
```bash
uv run attune workflow run security-audit --path <target>
```
### Pass 2: Quality
```bash
uv run attune workflow run code-review --path <target>
```
### Pass 3: Test Gaps
Analyze which functions in the target lack test coverage
by cross-referencing source files with test files.
### Output
Consolidate findings into a single summary table:
| File | Issue | Severity | Category |
|------|-------|----------|----------|
Group by severity (high → medium → low). End with
actionable recommendations.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.