메뉴
Distill a reusable skill/gene from recent run history (optionally from an LLM response file). Use when the user asks to "distill skill", "extract gene", or "generalize lessons".
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Show Evolver health — evolution memory location & size, recent log, and whether the full engine is installed. Use when the user asks for "evolver status", "evolver health", or "check evolver".
Self-evolution workflow for the agent. Before a substantive task, recall what worked on similar past tasks from evolution memory; after it, record the outcome so future sessions learn from it. Use when the user starts non-trivial work (a feature, a fix, a refactor) or asks the agent to "evolve", "learn from this", or "remember how this went".
Run an evolution checkpoint — recall relevant past outcomes, reflect on the current task, and record what was learned. Use when the user requests an evolution checkpoint or asks to "evolve" or "checkpoint".
Review Evolver's pending evolved changes, then approve (solidify) or reject (roll back). Use when the user asks to "review changes", "accept evolver changes", or "discard/rollback evolver changes".
Run one Evolver self-evolution cycle on the current repo (collect signals → select/mutate genes → propose changes). Use when the user asks to "run evolution cycle", "start evolver loop", or "run evolver strategy".
Solidify the current working changes into a durable Evolver gene/capsule (with rollback safety). Use when the user requests to "solidify changes", "save gene", or "capture this capsule".
| name | evolver-distill |
| description | Distill a reusable skill/gene from recent run history (optionally from an LLM response file). Use when the user asks to "distill skill", "extract gene", or "generalize lessons". |
Distill a reusable, generalized skill or gene from recent run history or a response file.
When requested, follow these steps:
Prefer the Proxy conversation distiller when available — if evolver_distill_conversation is in the MCP tool list and the reusable lesson came from the current conversation, call it first with a concrete summary, signals, strategy steps, artifacts, and validation evidence. The Proxy applies the quality gate, writes the Gene/Capsule locally, and queues Hub publishing when configured.
Resolve CLI and execute as a fallback or for existing history:
EVOLVER="evolver"
command -v evolver >/dev/null 2>&1 || EVOLVER="npx -y @evomap/evolver"
Run the distill command passing any optional arguments (e.g. --response-file=<path>):
$EVOLVER distill
Report and explain — summarize what was distilled:
Remind the user that only assets produced through genuine Evolver self-evolution are eligible to be synced or published to the EvoMap skill store using the evolver-sync skill.