Skip to content

DangQuangSE/team-development-skills / .cursor/skills/ck-quality

ck-quality

Verified

Independent senior-engineering quality auditor — architecture, ownership, domain integrity, abstraction, and maintainability. Use as `--gate` inside the ck:cook pipeline (blocks a phase on BLOCKER/HIGH/current-change MEDIUM findings) or call directly with `--audit`, `--diff`, `--changed` on any repository, directory, or file. Never writes tests and never edits production code — it returns structured findings only; ck:cook or ck:fix apply the fix.

FileKindSize
SKILL.mdskill md7.6 KB
agents/openai.yamlconfig264 B
references/adapters.mdmarkdown4.4 KB
references/core-contract.mdmarkdown14.3 KB
references/receipt-schema.jsonconfig3.5 KB
references/report-schema.jsonconfig3.2 KB
scripts/receipt.pyscript10.8 KB

references/report-schema.json

View on GitHub
{
  "_comment": "Example ck:quality report. One report is written per --gate/--verify call, or per --audit call with --save. Not a JSON-Schema document — an annotated canonical instance, matching this pack's plan-schema.json convention.",

  "mode": "gate",
  "_mode_values": ["gate", "audit", "diff", "changed", "verify"],

  "target": "phase-02-receipt-gate",
  "_target": "phase file stem (no extension) for gate/verify, e.g. phase-02-receipt-gate for phase-02-receipt-gate.md; path, diff ref, or 'working-tree' for audit/diff/changed. The receipt this report yields, if any, is derived from this exact string.",

  "verdict": "CHANGES_REQUIRED",
  "_verdict_values": ["APPROVED", "CHANGES_REQUIRED"],
  "_verdict_rule": "APPROVED requires zero open findings with severity BLOCKER or HIGH, and zero open MEDIUM findings where introduced_by_current_change is true. audit mode still computes a verdict but it is informational only — it never blocks anything by itself.",

  "reviewed_at": "2026-07-10T10:30:00Z",
  "reviewed_files": [
    "src/orders/create-order.ts"
  ],
  "_reviewed_files": "Exact file list the reviewer actually read and evaluated. This is what a later receipt (added by the completion-gate phase) hashes against.",

  "summary": {
    "blocker": 0,
    "high": 1,
    "medium": 2,
    "low": 0,
    "noted": 1
  },

  "findings": [
    {
      "id": "QUAL-007",
      "severity": "HIGH",
      "_severity_values": ["BLOCKER", "HIGH", "MEDIUM", "LOW", "NOTED"],
      "rule": "DOM_SINGLE_SOURCE",
      "_rule": "Stable rule ID from core-contract.md or adapters.md — never a paraphrase.",
      "status": "OPEN",
      "_status_values": ["OPEN", "RESOLVED", "ACCEPTED_DEBT"],
      "introduced_by_current_change": true,
      "_introduced_by_current_change": "true = new in this diff/phase; false = pre-existing debt the reviewer is only noting, not blocking on (unless BLOCKER/HIGH).",
      "applicable": true,
      "confidence": "high",
      "_confidence_values": ["high", "medium", "low"],
      "location": "src/orders/create-order.ts:48",
      "evidence": "The eligibility rule duplicates OrderPolicy.isEligible",
      "why_it_matters": "Two implementations of the same business rule will drift and produce inconsistent eligibility decisions.",
      "required_action": "Reuse the existing domain policy instead of reimplementing it here.",
      "owner": "cook"
    },
    {
      "id": "QUAL-011",
      "severity": "NOTED",
      "rule": "RDB_SINGLE_LEVEL_FUNCTION",
      "status": "OPEN",
      "introduced_by_current_change": false,
      "applicable": true,
      "confidence": "medium",
      "location": "src/orders/legacy-pricing.ts:120",
      "evidence": "Pre-existing 140-line function mixing pricing calculation and logging.",
      "why_it_matters": "Pre-existing debt; not something this phase introduced or is scoped to fix.",
      "required_action": "Out of scope for this phase — track separately if it becomes a blocker for future work.",
      "owner": "none"
    }
  ],

  "report_path": "plans/{slug}/quality/{target}-quality-report.json",
  "_report_path": "Set only when the report is actually written to disk (--gate always; --audit/--diff/--changed only with --save <path>)."
}
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: 194kUpdated Claude CodeCodexVerifiedInstall