القائمة
Govern memory, episode, skill, and fact lifecycle maintenance through the unified curate scan, review, apply, verify, and rollback verbs.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Operate graph readiness, topology lookup, synthesis-aware routing, and symbolic evidence canvases. Use for project ownership, impact, dependency, or idea-to-project questions.
Govern embedding refresh, episodic evidence synchronization, metadata writeback, and engine dataset snapshots. Use before or after bounded sync, reindex, migration, or writeback operations.
Govern source-linked temporal facts in openclaw-mem. Use for current truth, timelines, stale detection, fact packs, and review-only fact extraction.
Operate experimental Dream Lite planning, governed refresh canaries, rollback, and Director rehearsals. Use only for explicitly reviewed derived card maintenance.
Operate the experimental GBrain lookup, restricted helper-job, and governed refresh-canary lanes. Use only when GBrain integration is explicitly enabled.
Operate the experimental read-only goal primitive and surface validation. Use for normalized goal status, compact goal packs, and receipt validation, not continuation or autonomous mutation.
| name | openclaw-mem-curate |
| description | Govern memory, episode, skill, and fact lifecycle maintenance through the unified curate scan, review, apply, verify, and rollback verbs. |
| metadata | {"ring":1,"surface":["cli"],"version":"2.0.0","requires":["openclaw-mem-memory"]} |
Use scan → review → apply → verify → rollback as the explicit governed loop. Every wrapper preserves the complete engine receipt in inner.
openclaw-mem curate scan --target memory --json
openclaw-mem curate scan --target episodes --json
openclaw-mem curate scan --target skills --skill-root <workspace>/skills --json
openclaw-mem curate scan --target facts --source-root <workspace> --json
openclaw-mem curate review --target memory --from-file <recommendation.json> --json
openclaw-mem curate apply --target memory --from-file <governor.json> --json
openclaw-mem curate verify --target memory --run-dir <receipt-dir> --json
openclaw-mem curate rollback --target memory --receipt <rollback.json> --json
Skill mutation remains checkpointed and whitelist-only: pass an explicit self-curator plan to curate apply --target skills --plan <plan.json>. Unsupported verb-target pairs return stable zero-write receipts.
See legacy commands when maintaining older automation. Aliases remain callable and emit deprecation guidance; do not remove them during migration.
openclaw-mem curate scan --target skills --skill-root <workspace>/skills --json
python -m pytest tests/test_self_curator.py -q
git diff --check