gz-adr-audit
Executes formal ADR audits to transition architectural decisions from COMPLETED to VALIDATED status.
Install
mkdir -p .claude/skills/gz-adr-audit && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10457" && unzip -o skill.zip -d .claude/skills/gz-adr-audit && rm skill.zipInstalls to .claude/skills/gz-adr-audit
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Gate-5 audit templates and procedure for ADR verification. GovZero v6 skill.Key capabilities
- →Execute reproducible ADR verification
- →Verify ledger proof for OBPIs
- →Reproduce key evidence of ADR assertions
- →Assess ADR package structural coherence
- →Document audit findings in AUDIT.md
- →Attest to the presence of proof from Layer 1 tools
How it works
The skill orchestrates a sequenced audit ceremony, dispatching independent subagents to verify ledger proof, reproduce key evidence, and assess structural coherence, culminating in documentation and attestation.
Inputs & outputs
When to use gz-adr-audit
- →Verify ADR proof for validation
- →Run formal audit procedure on architectural decisions
- →Validate ADR thesis against system assertions
About gz-adr-audit
Performs sequenced verification of ADR assertions. Uses independent subagents to trace requirements and reproduce architectural outcomes to ensure the integrity of the design ledger.
Gate-5 audit templates and procedure for ADR verification. GovZero v6 skill.
When not to use it
- →When not transitioning an ADR from COMPLETED to VALIDATED
- →When not performing Gate-5 audit for ADR verification
- →When not needing to re-verify the ADR thesis against the running system
Prerequisites
Limitations
- →Requires ADR to be in COMPLETED state
- →Trusts Layer 1 ledger proof for mechanical checks
- →Does not involve code writing during the audit ceremony
How it compares
This skill provides a formal, persona-driven audit procedure for ADR verification, ensuring independent checks and re-verification of the ADR's thesis against the running system, unlike a simple checklist review.
Compared to similar skills
gz-adr-audit side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| gz-adr-audit (this skill) | 0 | 3mo | Review | Advanced |
| agent-v3-security-architect | 3 | 7mo | Review | Advanced |
| audit-workflow | 0 | 4mo | No flags | Intermediate |
| harness:recon | 0 | 2mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by tvproductions
View all by tvproductions →You might also like
agent-v3-security-architect
ruvnet
Agent skill for v3-security-architect - invoke with $agent-v3-security-architect
audit-workflow
FlorianDrevet
Use when: code audit, technical audit, security audit, performance audit, scalability audit, database audit, audit markdown, GitHub audit issues, findings reconciliation, labels sync.
harness:recon
acatl
>-
architect-review
sickn33
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.
solid-principles
SmidigStorm
Enforce SOLID principles (Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, Dependency Inversion) in object-oriented design. Use when writing or reviewing classes and modules.
codex
Lucklyric
Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. This skill should be invoked when users explicitly mention "Codex", request complex implementation challenges, advanced reasoning, or need high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.