deep-review Skill
Multi-agent deep code review for regorus. Three diverse parallel discovery agents with context asymmetry, risk-triggered micro-passes, adversarial gap-finder, and verification with disproval mandates. Use for high-stakes changes. Published by microsoft in regorus.
Decision snapshot
Is this a fit?
Security review, Includes SKILL.md, Reusable instructions
Compatibility not yet detected.
Shell access
Copy skill directory
2 months ago · NOASSERTION license
Access note: Shell access.
What is deep-review Skill?
Multi-agent deep code review for regorus. Three diverse parallel discovery agents with context asymmetry, risk-triggered micro-passes, adversarial gap-finder, and verification with disproval mandates. Use for high-stakes changes. Published by microsoft in regorus. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement. See how SkillIndex evaluates profiles.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Security review
- Security review use cases
Declared skill metadata
- Source file: .github/skills/deep-review/SKILL.md
Allowed tools declared by source
These fields retain source and confidence evidence from the indexed SKILL.md.
Compatibility and setup
- Install or run with Copy skill directory
- Shell access
Requirements and access
Security and permissions
Review permissions before connecting any MCP server to an agent. Pay special attention to whether it can read local files, write data, call external services, or perform destructive actions.
When to use deep-review Skill
- Use it for security review.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/regorus
- Skill file: .github/skills/deep-review/SKILL.md
What it does
Multi-agent deep code review for regorus. Three diverse parallel discovery agents with context asymmetry, risk-triggered micro-passes, adversarial gap-finder, and verification with disproval mandates. Use for high-stakes changes.
Skill instructions
Deep Review Skill You orchestrate a deep code review in phases: 1. Phase 1 — Parallel Discovery: 3 agents with different methodologies, models, and context (broad scanner, value-flow tracer, safety/API specialist) 2. Phase 2 — Risk-Triggered Micro-Passes: Narrow specialist agents launched only when uncovered code matches risk predicates 3. Phase 3 — Adversarial Verifier: 1 cold-start agent that BOTH verifies Phase 1 findings (tries to disprove them) AND hunts what everyone missed When to use this vs code-review: Use deep-review for high-stakes changes (evaluation logic, FFI, security-sensitive code, large diffs 200 lines). Use code-review for everyday reviews. Do not run cargo, clippy, tests, or build commands. Diff-review only. CRITICAL EXECUTION RULE: You MUST complete ALL steps before producing your final report. Do NOT return results after Phase 1 alone. The full pipeline is: Phase 1 → Phase 2 (if triggered) → Phase 3 → Report. Use readagent with wait: true to wait for each backgro
Verified compatibility and discovery
Frequently asked questions
What is deep-review?
deep-review is a open-source AI agent skill with Copy skill directory. Multi-agent deep code review for regorus. Three diverse parallel discovery agents with context asymmetry, risk-triggered micro-passes, adversarial gap-finder, and verification with disproval mandates.
Who is deep-review best for?
deep-review is best for reusing agent instructions, scripts, and references, security review workflows.
How do I install deep-review?
Install or run deep-review using Copy skill directory. Check deep-review for the latest setup command.
Is deep-review actively maintained?
deep-review may need a closer maintenance check before production use.
Project health auto-fetched from the source repository.
Maintain this resource?
Review this source-backed profile, send a correction with evidence, or link to it from your documentation. Claims verify your relationship to the project; profile facts still require source evidence and editorial review.
