TenantAtlas/.agent/skills/workflows/browser-readonly-audit/SKILL.md

name	description
tenantpilot-browser-readonly-audit	Read-only browser audit workflow for TenantPilot product surfaces without mutating state.

Purpose

Use this skill to collect focused browser evidence for UI/product-surface audits while avoiding state mutation, destructive flows, fixture pollution, or overbroad readiness claims.

Activate When

• Running a browser smoke check, visual inspection, product-surface audit, full browser audit, or read-only surface review.
• Inspecting pages for console errors, Livewire/runtime failures, network failures, visible complexity, navigation, authorization presentation, or Product Surface conformance.
• The user asks for browser proof and the intended path can be read-only.

Do Not Activate When

• The task requires executing destructive/high-impact mutations.
• The user asks to implement fixes rather than audit.
• The relevant feature is backend/docs-only and browser proof is explicitly N/A - no rendered UI surface changed.

Maturity

L2/L3 checklist workflow.

Gate Type

workflow.

Source Evidence

• docs/product/standards/product-surface-contract.md
• docs/testing-guidelines.md
• .specify/README.md
• specs/400-product-contract-spec-completeness-audit/spec.md
• specs/407-full-browser-ux-runtime-audit/spec.md
• apps/platform/tests/Browser/Spec402ResourcePolicyAuthorizationSmokeTest.php
• apps/platform/tests/Browser/Spec412PilotReadinessRemediationSmokeTest.php
• apps/platform/tests/Feature/Console/TenantpilotSeedBackupHealthBrowserFixtureCommandTest.php

External Anchors

Not applicable.

Required Repo Context

• Audit target route/page/flow.
• Authentication fixture or browser harness.
• Whether fixtures are read-only or seeded for inspection.
• Expected workspace/environment context.
• Primary interaction to inspect, if any.
• Console, network, and Livewire/runtime error capture method.

Execution Checklist

• Define the exact read-only path and actor.
• Confirm no state-changing action will be executed.
• Open the relevant route or entry point.
• Confirm workspace/environment context and expected surface labels.
• Inspect the changed or audited UI element.
• Check console/runtime errors.
• Check failed network requests related to the tested path.
• Record route, actor, context, observations, limitations, and screenshots only when useful.
• Do not generalize a narrow read-only pass into full merge readiness.

Stop Conditions

• The path requires destructive or high-impact execution to prove the claim.
• A requested action would mutate state without a test fixture and explicit spec permission.
• Browser audit discovers an in-scope blocker that requires implementation before readiness can be claimed.
• The evidence is too narrow for the requested broad readiness claim.
• The user asks for fixes during audit and the active spec/workflow does not include implementation.

Required Evidence After Use

• Route/path tested.
• Actor and workspace/environment context.
• UI elements inspected.
• Console/runtime/network result.
• Mutations avoided.
• Scope limitation and whether the evidence is smoke, audit sample, or full browser proof.

Common Failure Modes

• Clicking a destructive action while trying to inspect its confirmation.
• Treating seeded demo data as production readiness.
• Reporting "browser passed" without route, actor, or context.
• Ignoring console errors as development noise without evidence.
• Expanding a read-only audit into implementation work.

Quarantined Rules

Full Spec 416 quarantine list applies. Especially quarantined here: historical audits as current truth; raw provider/evidence payload default display; Product Surface runtime framework; OperationRun as default customer proof.

Review / Expiry

Review when browser harnesses, fixture commands, Product Surface proof expectations, or browser lane governance change. No planned expiry.