菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 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.
| name | distill-from-pattern |
| description | 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 this when pattern_observed, local_pattern_observed, pattern_aggregated, or pattern_pending_synthesis appears in the event stream. The Python layer only emits facts; Claude performs the judgment.
scripts/synthesis_events.py is the deterministic packaging boundary. It can append pattern_pending_synthesis and synthesis_job_ready facts for a selected event window, but it does not choose whether the pattern matters, call an LLM provider, smoke-test generated code, or materialize a pipeline.
When the stream only contains pattern_observed, local_pattern_observed, or pattern_aggregated, inspect the facts first. If they justify distillation, package or reference the selected window as synthesis facts, then continue from pattern_pending_synthesis / synthesis_job_ready. Do not reintroduce a Python coordinator.
events/events-<profile>.jsonl, events/events-local.jsonl, or events/events.jsonl.NOTES.md and optional synthesis_hints.yaml.connector.mode.name intent.__result for reads or __action for writes.icc_exec with explicit intent_signature and representative args.Return a concise report with intent signature, source events inspected, icc_exec verification result, and any remaining blocker.