memory-review
Review daily memory logs and consolidate durable knowledge into the existing memory hierarchy. Use for scheduled or manual knowledge review, especially when deciding whether to upd…
AxelHu
@axelhu
Install
$ openclaw skills install @axelhu/memory-reviewMemory Review
Turn daily logs into a small, current knowledge base. Treat daily logs as evidence, not as the authority.
Required workflow
-
Read references/spec.md before any write.
-
Read the workspace
AGENTS.mdandMEMORY.mdfor current hierarchy and owner rules. -
Build the deterministic scan plan:
python3 skills/memory-review/scripts/memory_review.py scan \ --root . \ --output /tmp/memory-review-scan.json -
Read every file in
changed_sources. Ignore*-memory-review.md; the scanner excludes them. -
Extract only durable signals. Exclude transient status, unverified ideas, routine execution logs, and secrets.
-
Resolve every signal against existing memory before writing. Use exact references,
memory_search,rg, and the helper when useful:python3 skills/memory-review/scripts/memory_review.py candidates \ --root . --query "主题或结论" -
Create a decision plan using the schema in the spec. Validate it before editing:
python3 skills/memory-review/scripts/memory_review.py validate-plan \ --root . --plan /tmp/memory-review-decisions.json -
Apply decisions in this order:
update_existingskip_duplicatereview_mergecreate_newdefer
-
Verify the diff, references, and current conclusion. A second run over unchanged inputs must not change canonical memory.
-
Write the report and execution log, then commit scan state only after all writes and checks succeed:
python3 skills/memory-review/scripts/memory_review.py commit-state \
--root . --scan /tmp/memory-review-scan.json
Hard rules
- Update-first: prefer the best existing canonical document over creating a near-synonym.
- Never create a third document when two candidates already overlap; emit
review_mergeinstead. - Resolve conflicts; do not append mutually contradictory conclusions as if both were current.
- Knowledge and hot memory outrank daily logs unless newer verified evidence explicitly supersedes them.
- Do not automatically edit
AGENTS.md,MEMORY.md,TOOLS.md,USER.md,SOUL.md, orENVIRONMENT.md. Record a proposal unless the current request explicitly authorizes that edit. - Do not put dates in new
memory/knowledge/filenames. Git history tracks time. - Do not advance state after partial failure.
- Do not send reports unless the caller or cron prompt specifies a destination.
Outputs
- Report:
memory/daily/YYYY-MM/YYYY-MM-DD-memory-review.md - Execution log:
data/exec-logs/memory-review/YYYY-MM-DD.md - State:
data/exec-logs/memory-review/state.json - Canonical targets:
memory/knowledge/,memory/glossary.md,memory/projects/,memory/post-mortems.md
Top skills in this category
Apple Notes
@steipeteManage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks Clawdbot to add a note, list notes, search notes, or manage note folders.
Writer
@ivangdavilaFix AI writing patterns that create repetitive and robotic content
Win Mouse Native (Windows)
@lurklightNative Windows mouse control (move, click, drag) via user32.dll. Use when the user asks you to move the mouse, click, drag, or automate pointer actions on Windows.
Self-Evolving
@ivangdavilaImprove reusable agent workflows with reflective experiments, value checks, and local pattern memory.
TotalReclaw
@p-diogoEnd-to-end encrypted, decentralized memory for OpenClaw. A native kind:memory provider — recall is automatic via memory_search/memory_get, and facts are captured in the background. Trigger on 'install TotalReclaw', 'set up TotalReclaw', 'restore my recovery phrase', any recall request ('what do you remember about me', 'what's my X'), AND any explicit remember request ('remember X', 'save X').