← ClaudeAtlas

loom-code-review-and-qualitylisted

Use when a code diff, branch, PR, worker output, or implementation-complete ticket needs a code-focused quality review across correctness, tests, architecture, security, performance, scope, and evidence before audit or closure.
z3z1ma/agent-loom · ★ 15 · Code & Development · score 80
Install: claude install-skill z3z1ma/agent-loom
# loom-code-review-and-quality Code review is an audit-oriented playbook for changed source and records. It reviews intent, tests, implementation, risk, and evidence, then routes durable findings into `loom-audit` or the consuming ticket. ## Loom Routing Common routes use these Loom skills for durable records or follow-up workflow: `loom-audit`, `loom-evidence`, `loom-tickets`, `loom-specs`, `loom-ralph`, `loom-research`, `loom-constitution`, `loom-retrospective`, and `loom-knowledge`. Follow any named Loom skill fully. This playbook adds workflow pressure; it does not shorten target-skill requirements. When code review is delegated to a worker and will support ticket closure, audit, or durable findings, launch it from the ticket and linked records as a bounded Ralph review run. ## Use This Playbook When Use this playbook when: - reviewing a diff, branch, pull request, or worker output - a ticket appears implementation-complete - another agent produced code that needs independent review - refactor, bug fix, package, security, or performance work needs a quality gate - closure depends on code and evidence telling the same story ## Route Use this route: ```text intent -> tests -> implementation -> risks -> evidence -> findings -> disposition ``` ## Intent Start from the target record: - ticket scope and `ACC-*` - spec `REQ-*` and `SCN-*` - plan execution unit - ticket scope and worker output - linked evidence and audit records Name what the change claims to acco