Skip to content

aiskillstore/marketplace / skills/21pounder/code-review

code-review

Verified

Use this skill when user asks to "review code", "check for issues", "analyze code quality", "find bugs", or wants feedback on code implementation.

FileKindSize
SKILL.mdskill md2.7 KB
skill-report.jsonconfig9.3 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-04T16:28:29.086Z",
    "slug": "21pounder-code-review",
    "source_url": "https://github.com/21pounder/terminalAgent/tree/main/deepresearch/.claude/skills/code-review",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "1d46523c702007ecce02b6693bb65ff92ba776e58cc337d754030a75a5f6a376",
    "tree_hash": "bdefb4921026ccb66e1cddf563526f2edbba96ea71e3f1dbbfe481d08c80254e",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "code-review",
    "description": "Guides structured code reviews for bugs, security issues, performance concerns, maintainability, and actionable improvement suggestions.",
    "summary": "Review code with prioritized findings, line references, and concrete fixes.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "21pounder",
    "license": "MIT",
    "category": "coding",
    "tags": [
      "code-review",
      "security-review",
      "bug-finding",
      "maintainability",
      "developer-tools"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands"
    ]
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "The only static finding is a false positive caused by markdown fence backticks around a JSON parameter schema. No prompt injection, data exfiltration intent, or executable command behavior was found in SKILL.md.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 14,
            "line_end": 31
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:14:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 14,
        "line_end": 31,
        "snippet": "```json"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:14:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 14 opens a markdown fenced JSON block for parameter documentation, and lines 15-31 contain a JSON schema. No executable Ruby backticks, shell command, or command invocation is present."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 99,
    "audit_model": "codex",
    "audited_at": "2026-07-04T16:28:29.086Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Review Code for Bugs and Security Issues",
    "value_statement": "Code reviews can miss bugs, security flaws, and maintainability issues. This skill guides Claude, Codex, and Claude Code through structured review steps.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "code review",
      "security review",
      "bug finding",
      "maintainability analysis",
      "performance review",
      "AI coding assistant",
      "developer workflow"
    ],
    "actual_capabilities": [
      "Reviews a specified file, directory, or glob target for code issues.",
      "Checks logic, edge cases, security risks, performance, and style consistency.",
      "Prioritizes findings by severity so users can address important issues first.",
      "Provides line references and explains why each issue matters.",
      "Suggests concrete fixes and examples when they help clarify the review."
    ],
    "limitations": [
      "It cannot run tests or commands because the skill only allows reading and searching files.",
      "It depends on the user selecting the correct files or directories for review.",
      "It may miss runtime, integration, or environment-specific defects.",
      "It provides review guidance, not a replacement for expert security assessment."
    ],
    "use_cases": [
      {
        "title": "Security Review Before Merge",
        "description": "Identify authentication, injection, validation, and error-handling risks before a pull request is approved.",
        "target_user": "Application security engineer"
      },
      {
        "title": "Bug Review for Feature Code",
        "description": "Find logic gaps, edge cases, and missing error handling in a focused implementation.",
        "target_user": "Software developer"
      },
      {
        "title": "Maintainability Review for Shared Modules",
        "description": "Evaluate naming, structure, duplication, and style consistency in common utility code.",
        "target_user": "Engineering lead"
      }
    ],
    "prompt_templates": [
      {
        "title": "Review One File",
        "prompt": "Review src/auth.ts for bugs and security issues. Prioritize findings by severity and include line references.",
        "scenario": "Beginner review of a specific file"
      },
      {
        "title": "Review a Directory",
        "prompt": "Review the src/utils directory for maintainability, duplicate logic, and error handling. Suggest concrete improvements.",
        "scenario": "Focused review of a small code area"
      },
      {
        "title": "Security-Focused Review",
        "prompt": "Review the API handlers for injection, authorization, data exposure, and unsafe input handling. Include only evidence-backed findings.",
        "scenario": "Security review before release"
      },
      {
        "title": "Architecture and Risk Review",
        "prompt": "Review the changed files for correctness, performance, security, and long-term maintainability. Group findings by severity and explain tradeoffs.",
        "scenario": "Advanced review across multiple concerns"
      }
    ],
    "output_examples": [
      {
        "input": "Review src/auth.ts for security issues.",
        "output": [
          "High: Password reset tokens are accepted without checking expiration. Add an expiration check before account updates.",
          "Medium: Login errors reveal whether an email exists. Return a consistent authentication failure message.",
          "Low: The rate-limit constant is duplicated. Move it to a shared configuration file."
        ]
      },
      {
        "input": "Review src/utils for maintainability.",
        "output": [
          "Summary: The utilities are readable, but two helpers duplicate date parsing rules.",
          "Medium: Date normalization differs between two modules. Consolidate the behavior into one helper.",
          "Low: Several helper names hide side effects. Rename them to show that they mutate input."
        ]
      },
      {
        "input": "Review this pull request for correctness and performance.",
        "output": [
          "Critical: No evidence found.",
          "High: A cache key omits the user identifier, which can return another user's result.",
          "Medium: A loop performs one database lookup per item. Batch the lookup to reduce latency."
        ]
      }
    ],
    "best_practices": [
      "Provide the smallest file set that still includes the full behavior under review.",
      "Ask for a specific focus, such as security, performance, correctness, or maintainability.",
      "Share relevant tests or related modules so the review can check behavior in context."
    ],
    "anti_patterns": [
      "Do not ask for a broad repository review when only one feature needs attention.",
      "Do not treat the review as proof that the code is free of defects.",
      "Do not omit generated code, configuration, or tests when they affect the reviewed behavior."
    ],
    "faq": [
      {
        "question": "What does this skill review?",
        "answer": "It reviews code for bugs, security issues, performance problems, style concerns, and maintainability risks."
      },
      {
        "question": "Can it run the project tests?",
        "answer": "No. The skill is designed for reading and searching files, not executing commands."
      },
      {
        "question": "Does it support security reviews?",
        "answer": "Yes. It includes checks for common security issues such as injection, authorization gaps, and unsafe input handling."
      },
      {
        "question": "Can it review a whole directory?",
        "answer": "Yes. The documented target can be a file path, directory, or glob pattern."
      },
      {
        "question": "Will the output include line numbers?",
        "answer": "Yes. The skill instructs the assistant to provide specific line references when findings are reported."
      },
      {
        "question": "Which tools can use this skill?",
        "answer": "The report marks it as compatible with Claude, Codex, and Claude Code."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 99
    }
  ]
}
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall