tvproductions/gzkit / .agents/skills/gz-adr-audit
gz-adr-audit
VerifiedUse for an ADR's Gate-5 audit; provides the audit templates and procedure.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.2 KB |
| assets/AUDIT.template.md | markdown | 2.1 KB |
| assets/AUDIT_PLAN.template.md | markdown | 2.1 KB |
assets/AUDIT.template.md
View on GitHub# AUDIT TEMPLATE (Gate-5) — Live Annotation
| Field | Value |
|-------|-------|
| ADR ID | {{ADR_ID}} |
| ADR Title | {{ADR_TITLE}} |
| ADR Dir | {{ADR_DIR}} |
| Audit Date | {{AUDIT_DATE}} |
| Auditor(s) | {{AUDITORS}} |
## Fidelity Gate (Step 3 — MANDATORY)
`uv run gz adr fidelity {{ADR_ID}}` — one row per assertion in the ADR's `## Fidelity Assertions` block.
| Claim | Command | Expected exit | Observed exit | Result |
|-------|---------|---------------|---------------|--------|
| (claim) | `(command)` | (n) | (n) | ✓/✗ |
---
## Execution Log
Annotate each planned check with result symbols:
- ✓ Passed
- ✗ Failed (include command output snippet + remediation note)
- ⚠ Warning (non-blocking discrepancy; capture rationale)
| Check | Command / Method | Result | Notes |
|-------|------------------|--------|-------|
| (Copy from AUDIT_PLAN) | (exact command run) | __PENDING__ | (results/proof path) |
| (ADR-specific check 2) | (exact command run) | __PENDING__ | (results/proof path) |
| (Add rows for all planned checks) | | | |
## Dataset Spot Examples
Paste short console snippets or attach artifact hashes when relevant.
```text
(Example output from key commands)
(Or reference: "See {{ADR_DIR}}/audit/proofs/output.txt")
```
## Summary Table
| Aspect | Status |
|--------|--------|
| Implementation Completeness | __PENDING__ |
| Data Integrity | __PENDING__ |
| Performance Stability | __PENDING__ |
| Documentation Alignment | __PENDING__ |
| Risk Items Resolved | __PENDING__ |
## Evidence Index
List all proof logs saved under `{{ADR_DIR}}/audit/proofs/`.
- {{ADR_DIR}}/audit/proofs/file1.json
- {{ADR_DIR}}/audit/proofs/file2.txt
- {{ADR_DIR}}/audit/proofs/chores/
## Recommendations
Document any shortcomings or misimplementations found:
- **Issue 1:** (Description of gap/problem)
- **Remedy:** (Recommended fix)
- **Issue 2:** (If none, state "No blocking issues found")
## Attestation
I/we attest that ADR {{ADR_ID}} is implemented as intended, evidence is reproducible, and no blocking discrepancies remain.
Accepted: _g0 (operator's verbatim acceptance is in the `validated` receipt), <date>_
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |