Menú
Use when prior notes, durable project knowledge, or vault-backed context should influence the current task.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Use as the canonical first-stage Agmo workflow when the user wants idea exploration, design tradeoffs, or requirement shaping before planning or implementation.
Run a Codex-native structured code review using agmo-critic and agmo-verifier where evidence is needed.
Harvest `debt:` markers across the repo into a read-only ledger without modifying code.
Audit and maintain the vault-backed llm-wiki knowledge base, including stale pages, low-confidence or contested captures, superseded captures, missing frontmatter, and broken wikilinks.
Use when one execution lane is no longer enough and work should escalate to the durable `agmo team ...` runtime.
Use when the user wants a GitHub issue created from the current conversation or repo context. Triggers on requests like "이슈 만들어", "깃허브 이슈", "create issue", or "new issue". If the source artifact is an existing vault note, use `note-to-issue` instead.
| name | wisdom |
| description | Use when prior notes, durable project knowledge, or vault-backed context should influence the current task. |
| argument-hint | [knowledge question, doc task, or note synthesis ask] |
Use this when durable knowledge should shape the current run.
Agmo treats the vault-backed llm-wiki as the startup-context SSOT. Session start injects a compact manifest by default; use agmo wiki context --project <project> --full for lazy full-body loading, agmo wiki maintain --project <project> for health checks, and agmo wiki migrate-wisdom --scope <user|project> --project <project> --dry-run before migrating legacy .agmo/memory/wisdom.json entries.
The main session should delegate this workflow to agmo-wisdom, then integrate the result back into the active workflow.
After the delegated result is integrated, call close_agent for the agmo-wisdom lane so the completed native subagent session releases its thread slot.
Use it for:
Prefer one of these explicit shapes instead of a loose freeform answer:
retrieve — find the best prior note candidatessynthesize — summarize or compare durable contextprepare-save — shape the result so it can become a durable noteA good wisdom result should usually include:
Before ending a meaningful wisdom stage, make the final response or delegated result save-ready:
If multiple note candidates overlap heavily: