daily-review
End-of-day structured summary and next-session prep. Use at the end of each working day or significant work block.
git clone --depth 1 https://github.com/ArchieIndian/openclaw-superpowers /tmp/daily-review && cp -r /tmp/daily-review/skills/openclaw-native/daily-review ~/.claude/skills/daily-reviewSKILL.md
# Daily Review State file: `~/.openclaw/skill-state/daily-review/state.yaml` ## The Review ### 1. What Was Accomplished List everything completed. Be specific. ### 2. What's In Progress For each: current status, next concrete step, blockers. ### 3. What Was Decided Capture decisions and reasoning. ### 4. What Was Learned Technical discoveries, user preferences, gotchas. ### 5. Tomorrow's Priorities Top 3 things to do next session, in order. ## Format ``` ## Daily Review - YYYY-MM-DD ### Accomplished - [item] ### In Progress - [item]: status / next step / blockers ### Decisions - [decision]: reason ### Learned - [learning] ### Tomorrow 1. [priority 1] 2. [priority 2] 3. [priority 3] ``` ## After the Review - Update memory/YYYY-MM-DD.md with full review - Update MEMORY.md with any durable learnings - Update open task files with current progress - Update state: `last_review_date` (today's date), `priorities` (Tomorrow list), `status: done`, `last_review_at` ## Cron Wakeup Behavior On 6pm weekday wakeup: - Read state file - If `last_review_date` is today: skip (already ran) - Otherwise: run the review and 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.