From backend-factory
Deep-zoom into a specific component for a detailed 'day in the life' view
How this skill is triggered — by the user, by Claude, or both
Slash command
/backend-factory:focusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Deep-zoom into a single component (node) in the factory for a detailed station profile, upstream/downstream map, activity log, and first-person narration.
Deep-zoom into a single component (node) in the factory for a detailed station profile, upstream/downstream map, activity log, and first-person narration.
$ARGUMENTS should contain a component identifier. Match strategy priority:
id fieldtype (auth, database, queue, cache, cron, worker)namemetadata.stationLabelIf $ARGUMENTS is empty, list all available nodes and ask the user to pick one.
curl -s http://localhost:7777/api/architecture > /tmp/factory-focus-arch.json
If the server is not running, inform the user to run /backend-factory:start first.
Search all actions for flows that pass through the target node.
If the target node has metadata.filePath, read the source file and up to 5 related files.
[Upstream Components] → [THIS COMPONENT] → [Downstream Components]
A first-person narrative (3-5 paragraphs) from this station's worker, grounded in real code details.
POST a focus mode overlay to highlight this component.
Present the complete focus report and suggest:
/backend-factory:trace <flow_name> to trace any passing flow/backend-factory:focus <upstream_component> to zoom into a connected stationnpx claudepluginhub randyquaye/backend-come-alive --plugin backend-factoryGenerates interactive HTML architecture diagrams with animated step-by-step flows, mode toggles, and side panel details. For service maps, CI/CD pipelines, data flows, and workshop diagrams.
Traces feature, request, or data flows through codebase from entry points (API routes, UI handlers, jobs) to storage, documenting layers, transformations, side effects, and dependencies via graphs or grep.
Audits a single service/module end-to-end for production readiness (ACID, resilience, observability). Not for diff/PR review or bug-finding sweeps.