Skip to content

AL-JANEF/janef-forge / skills/engineering/review-defect-first

review-defect-first

Verified

Independent review of a diff, PR, or file that hunts concrete defects introduced by the change: correctness, security, data loss, authorization or tenant escape, production failure, broken contracts, performance regressions, missing critical tests. Severity-ordered findings citing a real code path; no style inflation; "no qualifying defect" is valid. Use for code review and as the independent gate at high risk.

FileKindSize
SKILL.mdskill md2.1 KB
capability.jsonconfig1.9 KB
references/review-checklist.mdmarkdown2.2 KB

capability.json

View on GitHub
{
  "id": "review-defect-first",
  "name": "Defect-First Review",
  "version": "2.0.0",
  "domain": "engineering",
  "description": "Independent review of a diff, PR, or file that hunts concrete defects introduced by the change: correctness, security, data loss, authorization or tenant escape, production failure, broken contracts, performance regressions, missing critical tests. Severity-ordered findings citing a real code path; no style inflation; \"no qualifying defect\" is valid. Use for code review and as the independent gate at high risk.",
  "triggers": [
    "review",
    "code review",
    "review this",
    "review the",
    "review my",
    "pr review",
    "review pr",
    "review the pr",
    "review the diff",
    "audit the diff",
    "find defects",
    "defects",
    "critique",
    "second opinion",
    "look over",
    "look at this",
    "sanity check",
    "is this correct",
    "what is wrong with",
    "anything wrong",
    "feedback on",
    "approve",
    "lgtm",
    "merge request",
    "pull request review",
    "reviewer",
    "reviews"
  ],
  "negative_triggers": [
    "security review",
    "security pass",
    "security bug",
    "is this safe"
  ],
  "risk_level": "low",
  "context_cost": "small",
  "requires": [],
  "optional_with": [],
  "conflicts_with": [],
  "verification_requirements": [
    "each finding confirmed from a real code path, call site, invariant, or test gap",
    "residual risks and material verification gaps listed"
  ],
  "supported_hosts": [
    "claude-code",
    "codex"
  ],
  "references": [
    "references/review-checklist.md"
  ],
  "status": "stable",
  "responsibilities": [
    "independent-diff-review",
    "finding-quality"
  ],
  "priority": 54,
  "provenance": [
    "agent-engineering-stack 1.1.0 review-defect-first",
    "janefskills 1.2.0 engineering-standard references/review-and-gate.md (review checklist)"
  ]
}
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: 471kUpdated 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: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated 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: 194kUpdated Claude CodeCodexVerifiedInstall