Skip to content

aiskillstore/marketplace / skills/2389-research/fresh-eyes-review

fresh-eyes-review

Verified

This skill should be used as a mandatory final sanity check before git commit, PR creation, or declaring work done. Triggers on "commit", "push", "PR", "pull request", "done", "finished", "complete", "ship", "deploy", "ready to merge". Catches security vulnerabilities, logic errors, and business rule bugs that slip through despite passing tests.

FileKindSize
SKILL.mdskill md6.2 KB
skill-report.jsonconfig20.6 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-06T01:46:23.829Z",
    "slug": "2389-research-fresh-eyes-review",
    "source_url": "https://github.com/2389-research/claude-plugins/tree/main/fresh-eyes-review/skills",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "13ad1e7ea68545aa3aee1b5e49e005c07bfb1159a69ffc62ee5c7f8512de842c",
    "tree_hash": "0da5e3970a9c56863b8a25d7465549c366ae7d8ff1dcf61bab507ec0b734f8db",
    "provenance": {
      "model_requested": "gpt-5.5:high",
      "model_effective": "codex:gpt-5.5:high",
      "fallback_chain": [
        {
          "agent": "codex",
          "model": "gpt-5.5",
          "effort": "high",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "fresh-eyes-review",
    "description": "Guides a final fresh-eyes review before commits, pull requests, or release handoff. It focuses on security vulnerabilities, logic errors, business rules, and performance issues that tests can miss.",
    "summary": "Run a focused final code review before committing or shipping changes.",
    "icon": "📦",
    "version": "1.0.0",
    "author": "2389-research",
    "license": "MIT",
    "tags": [
      "code-review",
      "pre-commit",
      "security-review",
      "quality-assurance",
      "bug-prevention"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "filesystem"
    ],
    "category": "coding"
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All static findings are false positives caused by Markdown code fences, inline code formatting, and educational TypeScript examples. I found no evidence of executable shell commands, filesystem access, data exfiltration, or prompt injection in SKILL.md.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 42,
            "line_end": 42
          },
          {
            "file": "SKILL.md",
            "line_start": 48,
            "line_end": 50
          },
          {
            "file": "SKILL.md",
            "line_start": 50,
            "line_end": 54
          },
          {
            "file": "SKILL.md",
            "line_start": 54,
            "line_end": 62
          },
          {
            "file": "SKILL.md",
            "line_start": 62,
            "line_end": 63
          },
          {
            "file": "SKILL.md",
            "line_start": 63,
            "line_end": 63
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 74
          },
          {
            "file": "SKILL.md",
            "line_start": 74,
            "line_end": 87
          },
          {
            "file": "SKILL.md",
            "line_start": 87,
            "line_end": 93
          },
          {
            "file": "SKILL.md",
            "line_start": 93,
            "line_end": 117
          },
          {
            "file": "SKILL.md",
            "line_start": 117,
            "line_end": 120
          },
          {
            "file": "SKILL.md",
            "line_start": 120,
            "line_end": 153
          },
          {
            "file": "SKILL.md",
            "line_start": 153,
            "line_end": 176
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 42,
            "line_end": 42
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 42,
        "line_end": 42,
        "snippet": "| **Path Traversal** | File paths are validated, `../` sequences rejected or normalized |"
      },
      {
        "id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 48,
        "line_end": 50,
        "snippet": "```typescript"
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 50,
        "line_end": 54,
        "snippet": "const user = await db.query(`SELECT * FROM users WHERE id = '${userId}'`);"
      },
      {
        "id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 54,
        "line_end": 62,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 62,
        "line_end": 63,
        "snippet": "| **Null/undefined** | Every `.` chain could throw; defensive checks present? |"
      },
      {
        "id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 63,
        "line_end": 63,
        "snippet": "| **Type coercion** | `==` vs `===`, implicit conversions |"
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 74,
        "snippet": "```typescript"
      },
      {
        "id": "external_commands:SKILL.md:74:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 74,
        "line_end": 87,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 87,
        "line_end": 93,
        "snippet": "```typescript"
      },
      {
        "id": "external_commands:SKILL.md:93:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 93,
        "line_end": 117,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:117:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 117,
        "line_end": 120,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 120,
        "line_end": 153,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:153:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 153,
        "line_end": 176,
        "snippet": "```"
      },
      {
        "id": "filesystem:SKILL.md:42:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 42,
        "line_end": 42,
        "snippet": "| **Path Traversal** | File paths are validated, `../` sequences rejected or normalized |"
      },
      {
        "id": "blocker:SKILL.md:50:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 50,
        "line_end": 50,
        "snippet": "const user = await db.query(`SELECT * FROM users WHERE id = '${userId}'`);"
      },
      {
        "id": "blocker:SKILL.md:53:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 53,
        "line_end": 53,
        "snippet": "const user = await db.query('SELECT * FROM users WHERE id = $1', [userId]);"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The backticks appear around the literal path pattern ../ inside a Markdown checklist. This is documentation telling reviewers to reject traversal, not shell execution."
      },
      {
        "id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 48 is a Markdown code fence for a TypeScript example. It is not executable code and does not invoke a shell."
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The template literal is inside an illustrative TypeScript SQL injection example in documentation. It is not Ruby or shell backtick execution in an installable script."
      },
      {
        "id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 54 closes a Markdown code fence. No executable command or shell invocation is present."
      },
      {
        "id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The backticks format a dot operator in a Markdown checklist about null checks. This is prose guidance, not executable command text."
      },
      {
        "id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The backticks format JavaScript comparison operators in a Markdown table. There is no shell or Ruby command execution context."
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 68 is a Markdown TypeScript code fence opener. It only marks an example block and is not executable."
      },
      {
        "id": "external_commands:SKILL.md:74:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 74 closes a Markdown code fence after a pagination example. It does not execute commands."
      },
      {
        "id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 87 opens a Markdown TypeScript example block. The text is documentation and contains no command execution."
      },
      {
        "id": "external_commands:SKILL.md:93:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 93 closes a Markdown code fence after a tax calculation example. It is not executable shell syntax."
      },
      {
        "id": "external_commands:SKILL.md:117:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 117 opens a Markdown block showing expected review output. It is not a command or script."
      },
      {
        "id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 120 closes a Markdown output example. It does not contain executable command text."
      },
      {
        "id": "external_commands:SKILL.md:153:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 153 opens a Markdown example workflow block. It is static documentation, not a shell execution primitive."
      },
      {
        "id": "filesystem:SKILL.md:42:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The ../ sequence is mentioned as a path traversal pattern that reviewers should reject or normalize. The skill does not read files or construct paths from this text."
      },
      {
        "id": "blocker:SKILL.md:50:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The SELECT statement is a short vulnerable SQL example used to teach review behavior. It is not executed by the skill and does not perform reconnaissance."
      },
      {
        "id": "blocker:SKILL.md:53:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The SELECT statement is the safe parameterized version of the preceding example. It is documentation only and has no runtime database access."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 176,
    "audit_model": "codex",
    "audited_at": "2026-07-06T01:46:23.829Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Review Code Before Commit",
    "value_statement": "Teams ship bugs when final changes are trusted too quickly. This skill adds a focused pre-commit review for security, logic, business rules, and performance.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "fresh eyes review",
      "pre commit review",
      "code review checklist",
      "security checklist",
      "logic bug detection",
      "pull request quality",
      "AI coding audit"
    ],
    "actual_capabilities": [
      "Guides a final review before commit, pull request, deployment, or completion handoff.",
      "Checks common security issues, including SQL injection, XSS, path traversal, command injection, IDOR, and auth bypass.",
      "Prompts review of logic errors, business rules, performance issues, and edge cases.",
      "Directs users to fix findings, add tests, and rerun validation before declaring work done.",
      "Provides time guidance and a required completion summary for review accountability."
    ],
    "limitations": [
      "It does not execute tests, linters, or scanners by itself.",
      "It depends on the reviewer having access to the changed files and project context.",
      "Its examples are TypeScript oriented, though the checklist applies broadly.",
      "It can add process time for very small or urgent changes."
    ],
    "use_cases": [
      {
        "title": "Pre-Commit Quality Gate",
        "description": "Run a short final review before committing code to catch missed security and logic issues.",
        "target_user": "Software developer"
      },
      {
        "title": "Pull Request Readiness Check",
        "description": "Verify that a change is ready for review by checking edge cases, business rules, and validation steps.",
        "target_user": "Tech lead"
      },
      {
        "title": "Security-Focused Final Pass",
        "description": "Use the checklist to look for injection, authorization, traversal, and output handling problems before release.",
        "target_user": "Security-minded reviewer"
      }
    ],
    "prompt_templates": [
      {
        "title": "Start a Basic Review",
        "scenario": "Beginner review after finishing a small code change.",
        "prompt": "Run a fresh-eyes review on my changed files before I commit. Focus on security, logic errors, and missing validation."
      },
      {
        "title": "Check Pull Request Readiness",
        "scenario": "Intermediate review before opening a pull request.",
        "prompt": "Review this branch for pull request readiness. Check the changed files for business rules, edge cases, performance, and test gaps."
      },
      {
        "title": "Audit a Sensitive Feature",
        "scenario": "Advanced review for authentication, billing, or data access changes.",
        "prompt": "Perform a fresh-eyes review of this sensitive feature. Prioritize auth bypass, IDOR, injection, data leakage, and incorrect authorization boundaries."
      },
      {
        "title": "Validate Release Readiness",
        "scenario": "Advanced final pass before deployment or merge.",
        "prompt": "Do a release-readiness fresh-eyes review. List each issue found, the fix needed, validation steps, and any residual risk before I ship."
      }
    ],
    "output_examples": [
      {
        "input": "Review a four-file authentication change before commit.",
        "output": [
          "Fresh-eyes review started for four files.",
          "Found missing email validation and an authorization check that depended only on a request parameter.",
          "Recommended adding validation, enforcing server-side ownership checks, and rerunning tests."
        ]
      },
      {
        "input": "Check a pagination update for pull request readiness.",
        "output": [
          "Reviewed security, logic, business rules, and performance concerns.",
          "Found an off-by-one pagination condition and a missing maximum page size.",
          "Suggested boundary tests and a response size limit before opening the pull request."
        ]
      },
      {
        "input": "Run a final pass on a billing calculation change.",
        "output": [
          "Checked rounding, zero values, error messages, and test coverage.",
          "Found currency rounding applied after aggregation instead of per line item.",
          "Recommended matching the documented billing rule and adding regression coverage."
        ]
      }
    ],
    "best_practices": [
      "Run the review after implementation and tests, but before commit or pull request creation.",
      "Review only the changed files and directly related code to keep the pass focused.",
      "Fix findings immediately and add tests that prove the issue stays fixed."
    ],
    "anti_patterns": [
      "Skipping the review because tests already pass.",
      "Using the checklist as a substitute for automated tests or security scanners.",
      "Declaring the review complete without recording issues found, fixes made, and validation run."
    ],
    "faq": [
      {
        "question": "When should I use this skill?",
        "answer": "Use it after implementation and tests, before a commit, pull request, deployment, or completion handoff."
      },
      {
        "question": "Does it replace normal code review?",
        "answer": "No. It is a final self-review step that helps catch issues before human review or release."
      },
      {
        "question": "Does it run security tools automatically?",
        "answer": "No. It provides a review process and checklist. You still need to run project tests, linters, and scanners."
      },
      {
        "question": "What kinds of bugs does it target?",
        "answer": "It targets injection, access control, path traversal, logic errors, business rule mistakes, and performance problems."
      },
      {
        "question": "Can it be used outside TypeScript projects?",
        "answer": "Yes. The examples use TypeScript, but the review categories apply to most software projects."
      },
      {
        "question": "How long should the review take?",
        "answer": "The skill suggests about two minutes for small changes and up to five minutes for larger focused reviews."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 176
    }
  ]
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall