extract-skill looks back at a run (or a pattern you describe) and harvests the
durable, reusable part of it, turning a one-off into an agent skill doc, a sketch
for a new workflow, and memory facts worth keeping. Reach for it right after a run
when you notice yourself doing the same thing again.
targetRunId to let the analysis read the real run state (bunx smithers-orchestrator inspect,
events, node); leave it null to harvest purely from the prompt and
context. When the pattern is skill-shaped, the workflow writes the skill to
.smithers/skills/<name>.md.
Stages
- analyze: read the run (if given) and decide what is worth harvesting: the repeated pattern, whether it is reusable as a skill and/or a whole workflow, and any durable memory facts.
- propose: turn the analysis into concrete proposals: a skill (name, description, body), a workflow sketch (id, sketch), and the polished memory facts to persist.
- scaffold-skill: when the pattern is reusable as a skill, write the proposed skill doc to
.smithers/skills/<name>.md.
Inputs
| Input | Type | Default |
|---|---|---|
targetRunId | string or null | null (analyze the prompt/context alone) |
prompt | string | "Describe the pattern or run you want to harvest into a reusable skill, workflow, or memory." |