emerge

Use when Emerge emits pattern_aggregated facts and Claude must decide whether runner suggestions justify a follow-up distillation task.

Use when an Emerge intent is marked synthesis_ready and Claude must inspect successful WAL samples to create a conservative pending pipeline artifact.

Use when an Emerge event stream contains pattern_observed, local_pattern_observed, pattern_aggregated, or pattern_pending_synthesis and Claude must turn raw runner/operator facts into one conservative pipeline candidate through normal mechanism tools.

Use when wiring a generic connector to capture remote operator actions and convert repeated event facts into pending pipeline work through Claude Code skills.

Distill Emerge forward flywheel WAL samples into a parameterized pipeline result. Use when a lead agent receives a forward_synthesis_pending event or a job with skill_name=emerge-forward-synthesis.

Distill Emerge reverse flywheel raw operator events into a structured synthesis result. Use when a lead agent receives synthesis_job_ready with skill_name=emerge-reverse-synthesis.

Use when a user asks to initialize a domain flywheel from natural language context, especially when environment details are incomplete or mixed with execution assumptions.

Use when Emerge emits evidence_applied facts and Claude must review intent evidence before asking mechanism tools for an explicit stage transition.

Use when the operator monitoring pipeline appears broken: EventBus has no events, PatternDetector is not firing, elicitation dialog never appears, or OperatorMonitor is silent. Guides systematic diagnosis of the full pipeline.

Use when developing emerge plugin code that targets a remote runner — deploying script changes, managing runner/watchdog lifecycle, debugging execution environment issues (session isolation, tool availability, GUI access), or setting up a new runner on any platform.

Use when installing, deploying, checking, or batch-updating Emerge runners from admin commands or cockpit operator workflows.

Use when designing or revising Emerge cockpit presentation, summaries, filters, action labels, or empty/error states without changing the HTTP API contract.

Use when deciding whether a runner should interrupt the operator, how popup text should be phrased, and how timeout/failure classes should be interpreted.

Use when connector flywheel history is large/noisy and lightweight reflection is insufficient. Builds a deep reflection cache consumed by hooks.

Use when policy health needs tuning: too many explore pipelines, repeated failures, stalled promotions, or noisy rollback behavior. Produces a prioritized optimization plan with safe threshold recommendations.