Skip to content

mikeng-io/agent-skills / skills/deep-review

deep-review

Verified

Multi-agent quality improvement review with constructive feedback. Provides suggestions for best practices, code quality, alternatives, and performance optimization.

FileKindSize
README.mdmarkdown8.6 KB
SKILL.mdskill md16.4 KB
schemas/review-report-schema.jsonconfig6.3 KB

schemas/review-report-schema.json

View on GitHub
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://deep-review.dev/schemas/review-report.json",
  "title": "Deep Review Report Schema",
  "description": "JSON Schema for deep-review output validation",
  "type": "object",
  "required": [
    "review_type",
    "reviewed_at",
    "scope",
    "reviewers_count",
    "overall_assessment",
    "top_recommendations",
    "suggestions_by_priority"
  ],
  "properties": {
    "review_type": {
      "type": "string",
      "const": "quality-improvement",
      "description": "Type of review performed"
    },
    "reviewed_at": {
      "type": "string",
      "format": "date-time",
      "description": "ISO 8601 timestamp when review was performed"
    },
    "scope": {
      "type": "string",
      "description": "What was reviewed"
    },
    "reviewers_count": {
      "type": "integer",
      "const": 4,
      "description": "Number of expert reviewers"
    },
    "overall_assessment": {
      "type": "string",
      "enum": ["high-quality", "good-with-improvements", "needs-work"],
      "description": "Overall quality assessment"
    },
    "top_recommendations": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 3,
      "description": "Top 3 most important recommendations"
    },
    "suggestions_by_priority": {
      "type": "object",
      "required": ["high", "medium", "low"],
      "properties": {
        "high": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/suggestion"
          }
        },
        "medium": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/suggestion"
          }
        },
        "low": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/suggestion"
          }
        }
      }
    },
    "alternative_approaches": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/alternative"
      }
    },
    "performance_optimizations": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/optimization"
      }
    },
    "positive_aspects": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "What's already good"
    },
    "resources": {
      "type": "array",
      "items": {
        "type": "object",
        "required": ["category", "links"],
        "properties": {
          "category": {
            "type": "string"
          },
          "links": {
            "type": "array",
            "items": {
              "type": "string",
              "format": "uri"
            }
          }
        }
      }
    }
  },
  "$defs": {
    "suggestion": {
      "type": "object",
      "required": ["category", "severity", "suggestion", "rationale"],
      "properties": {
        "category": {
          "type": "string",
          "description": "Category of suggestion"
        },
        "severity": {
          "type": "string",
          "enum": ["CRITICAL", "HIGH", "MEDIUM", "LOW"]
        },
        "suggested_by": {
          "type": "array",
          "items": {
            "type": "string",
            "enum": ["best-practices", "code-quality", "alternatives", "performance"]
          },
          "description": "Which reviewers suggested this"
        },
        "current_approach": {
          "type": "string",
          "description": "What's being done now"
        },
        "suggestion": {
          "type": "string",
          "description": "Specific improvement to make"
        },
        "rationale": {
          "type": "string",
          "description": "Why this is important"
        },
        "example_before": {
          "type": "string",
          "description": "Current code pattern"
        },
        "example_after": {
          "type": "string",
          "description": "Improved code pattern"
        },
        "impact": {
          "type": "string",
          "description": "Expected benefit"
        },
        "resources": {
          "type": "array",
          "items": {
            "type": "string",
            "format": "uri"
          }
        }
      }
    },
    "alternative": {
      "type": "object",
      "required": ["name", "description", "pros", "cons", "when_to_use", "complexity"],
      "properties": {
        "name": {
          "type": "string",
          "description": "Name of alternative approach"
        },
        "description": {
          "type": "string",
          "description": "What this approach involves"
        },
        "pros": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "minItems": 1,
          "description": "Advantages"
        },
        "cons": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "minItems": 1,
          "description": "Disadvantages"
        },
        "when_to_use": {
          "type": "string",
          "description": "Scenarios where this is better"
        },
        "complexity": {
          "type": "string",
          "enum": ["HIGH", "MEDIUM", "LOW"]
        },
        "example": {
          "type": "string",
          "description": "Code example or reference"
        }
      }
    },
    "optimization": {
      "type": "object",
      "required": ["category", "severity", "opportunity", "suggestion", "expected_improvement", "effort"],
      "properties": {
        "category": {
          "type": "string",
          "enum": ["algorithm", "database", "caching", "resource", "scalability", "frontend"]
        },
        "severity": {
          "type": "string",
          "enum": ["CRITICAL", "HIGH", "MEDIUM", "LOW"]
        },
        "current_performance": {
          "type": "string",
          "description": "Current metrics or complexity"
        },
        "opportunity": {
          "type": "string",
          "description": "What can be optimized"
        },
        "suggestion": {
          "type": "string",
          "description": "Specific optimization"
        },
        "expected_improvement": {
          "type": "string",
          "description": "How much better"
        },
        "trade_offs": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "What you give up"
        },
        "effort": {
          "type": "string",
          "enum": ["HIGH", "MEDIUM", "LOW"]
        }
      }
    }
  }
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall