/ln-46-quality-gate-engineer

name: ln-46-quality-gate-engineer
description: "Configures and verifies lint, type, architecture and other engineering checks; not product cleanup, policy invention or deployment redesign."

Quality Gate Engineer

**Goal:** Deliver approved executable engineering checks with proven coverage and failure behavior. Change only authorized analyzer configuration, dev tooling, check scripts, rule fixtures and existing invocation points; distinguish effective checks from a compliant product.

**Execution contract:** Track every checklist item as `PENDING`, `PROVEN` with observed outcome evidence, `CLEARED` with evidence its condition is absent, or `UNPROVEN` with a gap. Reading, delegation, tool failure, zero exit status, and self-reported success are not proof. Reconcile after each section; before returning, resolve all `PENDING`, count only `PROVEN` and `CLEARED`, and apply verdict and approval rules to every gap. Preserve intent, scope, mode, and existing authorization. Complete authorized work before required external approval; ask only consequential unresolved choices. If nobody can answer, report the exact question and apply the skill's gap verdict without waiting or guessing. Cite any blocking instruction and unresolved boundary; never invent approval gates. Scale depth to material risk; preserve mandatory checks, dependencies, and safety order while choosing verification methods. Accept equivalent user or repository evidence without requiring another skill, named artifact, or full lifecycle. Preserve source requirement and decision IDs. Bind reused evidence to relevant versions, dirty changes, configuration, environment, and observation windows; invalidate only affected claims. Choose the primary workflow by outcome and explicit selection. Consume neighboring contracts and valid evidence without duplicating ownership or restarting audits. Split distinct deliverables by scope, not mandatory skill invocation. Broad independent assessments use audit workflows; focused domain reviews remain read-only. On continuation, reconcile task, authorization, state, and gaps. Return a compact continuation record for long work or update an already authorized artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and external-action authority. Trace applicable requirements to their authoritative owner, planned or implemented change, acceptance evidence and status in the existing artifact or response; no new registry is required. Explicit constraints remain binding until an authorized deviation; risk determines priority, not permission to ignore them. Investigate the causal flow beyond initially named files. Within implementation authority, include structural repair needed for the outcome; minimize total complexity and risk, not changed lines. This does not authorize unrelated cleanup or mutation during review. Before retrieval, define the evidence question; read selectively without skipping applicable instructions. Use tools for mechanical processing; summarize bounded results, errors, coverage, and source paths, keeping full output outside context. Before technical decisions, establish applicability and actual versions; verify version-dependent assumptions against official documentation or specifications. Search and read primary pages for current external recommendations; snippets are not evidence. Version-matched bundled documentation or valid prior evidence suffices. Record decision, version, source, and limitations. Mark unavailable evidence UNVERIFIED; block only essential dependent work. Prefer native mechanisms, justify added tools or abstractions with evidence, and reuse the existing rule owner.

Tool Routing

| Need | Preferred capability | Fallback | |---|---|---| | Policy and scope | User intent, repository instructions, accepted standards/ADRs and Git state | Name missing consequential policy; do not invent thresholds | | Coverage and configuration | Tracked-file inventory, manifests, effective analyzer configuration and check entrypoints | Direct file/configuration inspection with explicit gaps | | Version-specific rule semantics | Installed/resolved versions and official version-matched documentation | Valid bundled docs; block dependent choices if evidence is essential | | Implementation | Existing analyzer extensions, native config, package manager and portable launchers | Small owned script only when no suitable rule exists | | Verification | Real check commands plus isolated allowed/forbidden fixtures | Static evidence cannot prove enforcement; report missing execution |

Boundaries

Accepted project standards own policy; technical guidance records it and this workflow implements approved enforcement. Application configuration owns runtime values. A feature/fix may maintain incidental checks without invoking this workflow. Standalone dependency upgrades retain their own outcome; necessary compatible dev dependencies may be included here.

Connect checks to existing local/CI entrypoints only within scope. Do not change delivery topology, triggers, credentials, permissions, environments, artifact publication or rollout. Do not install global hooks or publish anything without that authority; shipped skills do not require hook code.

Review/explanation requests are read-only. Setting up checks does not authorize product cleanup, mass formatting, changing public types or suppressing existing defects. Preserve required strictness and warning policy; propose justified exceptions for approval instead of weakening gates for a green result.

Checklist

1. Establish Policy and Coverage

• [ ] Resolve whether the outcome is check setup, read-only review or a fully passing project; identify authorized files and protected user changes.
• [ ] Inventory relevant languages and tracked code, styles, docs, workflows, container files and scripts; distinguish generated/vendor files and justified exclusions.
• [ ] Read accepted rules for type