bug-screenshot-annotation

# Bug Screenshot Annotation Reference/utility skill (same tier as `/playwright-cli`): loaded INSIDE the subagent that is already executing a testing stage — it does not spawn agents of its own and has no dispatch strategy. Typical caller: `/sprint-testing` Stage 2, when a bug found during exploration is visual/positional (see `../sprint-testing/references/exploration-patterns.md` §"Bugs found during exploration"). ## Why 100% local — the security rationale (binding) An earlier design routed screenshots through external generative image-editing services. Both attempts failed, one dangerously: - A quota-walled image MCP was simply unavailable (429 across every tier). Not a design problem — just dead. - A second generative service got hard-blocked by the agent runtime's own data-exfiltration classifier, because QA screenshots carry real product/customer/competitor data and the destination was not a trusted host. Critically, **explicit user authorization in chat did not lift the block** — and one screenshot had already leaked to the service's public S3/CloudFront bucket before the second attempt was caught. The standing lesson: **QA evidence containing real product or customer data never routes through an external image service, generative or otherwise.** This skill sidesteps the risk entirely — everything happens with HTML+CSS rendered by an HTTP server bound to `127.0.0.1`, captured by a local browser-automation CLI; nothing leaves the machine. If a genuinely unhandleable ...