persistent-memory-hygiene
Keeps OpenClaw's memory store clean, structured, and useful. Use at session end and during periodic maintenance.
git clone --depth 1 https://github.com/ArchieIndian/openclaw-superpowers /tmp/persistent-memory-hygiene && cp -r /tmp/persistent-memory-hygiene/skills/openclaw-native/persistent-memory-hygiene ~/.claude/skills/persistent-memory-hygieneSKILL.md
# Persistent Memory Hygiene State file: `~/.openclaw/skill-state/persistent-memory-hygiene/state.yaml` ## Memory Structure ``` memory/ YYYY-MM-DD.md # Daily notes - raw, comprehensive MEMORY.md # Long-term - curated, distilled ``` ## When to Write Write to memory/YYYY-MM-DD.md when: - Completing a significant task - Making a decision with reasoning - Encountering a notable error and its fix - At checkpoints on long tasks Write to MEMORY.md when: - Something is worth remembering across months - A user preference has been established - A pattern has been confirmed ## Session Closing Routine ``` ## [HH:MM] Session End - Completed: [what was finished] - In progress: [what was started] - Next: [what to do next session] - Decisions: [choices made and why] ``` After writing, update state: `last_cleaned_at`, `memory_line_count`, `daily_file_count`, `last_daily_file`, `status: done`. ## Hygiene Rules - Daily files: write raw, append-only, never edit old entries - MEMORY.md: review periodically, remove stale entries, keep under 500 lines ## Cron Wakeup Behavior On 11pm wakeup: - Read state file - If `last_cleaned_at` is today's date: skip (already ran) - Otherwise: run Session Closing Routine, update state
Syncs agent daily memory and MEMORY.md to an Obsidian vault so notes are human-browsable. Use nightly or on demand.
Structured ideation before any implementation. Use when starting any non-trivial task.
Scaffolds and validates new superpowers skills. Use when creating a new skill for this repository.
Executes plans task-by-task with verification. Use when implementing a plan.
Triggers a secondary verification pass for any agent output containing factual claims, numbers, dates, or named entities before the output is acted on
Crawls a new codebase to infer stack, conventions, and key invariants, then generates a PROJECT.md context file for the agent
Handles PR review feedback by fetching comments, grouping issues, fixing one group at a time, and verifying before replies.
Detects skill name shadowing and description-overlap conflicts that cause OpenClaw to trigger the wrong skill or silently ignore one when two skills compete for the same intent.