AGENT SKILL

domain-reviewer

Coordinate deep-dive reviews via specialized sub-agents as critics. Use for deep review of a specific module or domain (not general code review), when multiple specialized perspectives are needed (e.g. security plus performance plus correctness), or for pre-release review of critical system components.

使用场景代码审查
License 许可
MIT
所属仓库
muratovv/ai-hats
最近更新
2026-11-05
Stars
★ 3
Forks
1

01 前言 Front Matter

name
domain-reviewer
license
MIT
description
Coordinate deep-dive reviews via specialized sub-agents as critics. Use for deep review of a specific module or domain (not general code review), when multiple specialized perspectives are needed (e.g. security plus performance plus correctness), or for pre-release review of critical system components.

03 SKILL.md 正文

Domain & Module Reviewer

Coordinate deep-dive reviews of specific system domains or modules by engaging specialized sub-agents as critics.

When to Use

Reach here when one module or domain needs several specialist lenses at depth (security + performance + correctness), coordinated via sub-agent critics. Don't spin up its sub-agents for a routine diff: a change that only reshapes a public contract is interface-design, and one that only widens scope is drift-detection.

Workflow

  1. Scope: Define boundaries of the module/domain to review (e.g., "The Payment Gateway Service", "The Authentication flow").

  2. Select Critics: Identify sub-agents for the review based on tech stack and concerns (e.g., Go code quality, security, SQL performance).

  3. Formulate Prompts: Draft clear, scoped prompts for each sub-agent, asking them to evaluate specific aspects against architectural contracts.

  4. Delegate: Execute sub-agent calls in parallel if possible.

  5. Synthesize: Collect reports. Do not copy-paste output. Extract critical architectural flaws and document them in an ADR or action plan.

Completion

  • All sub-agent reviews collected and synthesized
  • Critical findings documented in ADR or action plan
  • No copy-pasted sub-agent output — findings are curated

Anti-Patterns

  • Dumping raw sub-agent output without synthesis — the value is in curation
  • Overly broad scope — review one domain at a time, not the entire system
  • Skipping parallel execution — sub-agents are independent, run them concurrently

04 同仓库更多 Skills

muratovv
muratovv/ai-hats

tool-evaluation-protocol

Time-bounded protocol for evaluating new tools, libraries, or methodologies before adoption. Use when evaluating a candidate dependency for the project, researching a methodology (e.g. ML/LLM frameworks, testing approaches), or following up on a hype-driven recommendation.

★ 3
muratovv
muratovv/ai-hats

systematic-debugging

4-phase bug-fix protocol (evidence, pattern, hypothesis, verify). Use when investigating any error, failure, or unexpected behavior, handling bug reports from users or monitoring, or diagnosing test failures with non-obvious causes.

★ 3
muratovv
muratovv/ai-hats

skill-template

Canonical template and validation guide for ai-hats skills. Use when creating a new skill, reviewing an existing one for structural compliance, or deciding which pattern fits a new behavior.

Skill与智能体开发
★ 3
muratovv
muratovv/ai-hats

skill-optimization

Audit and refactor library components to eliminate redundancy and staleness. Use during periodic library maintenance, after adding multiple new skills or rules, when a role's token budget is too high, or after retrospectives identify component issues.

Skill与智能体开发
★ 3
muratovv
muratovv/ai-hats

silent-fallback-gate

PreToolUse hook — refuses an Edit or Write that adds an inert broad except. Use when a Python edit was blocked for a silent fallback.

★ 3
muratovv
muratovv/ai-hats

retro-to-framework

Convert an observation about agent behavior — from a retrospective or from a single incident — into a framework-level change (hook, rule, skill, skill update). Use after a retrospective identifies problems that are not project-specific, after an incident where an agent misapplied a component it had read, when CLAUDE.md band-aids accumulate (more than 3 per-project rules that could be generic), or when the same problem recurs across multiple projects.

Skill与智能体开发
★ 3