morning-briefing
Compiles a daily morning briefing from active tasks, priorities, and pending items. Use at the start of each working day.
git clone --depth 1 https://github.com/ArchieIndian/openclaw-superpowers /tmp/morning-briefing && cp -r /tmp/morning-briefing/skills/openclaw-native/morning-briefing ~/.claude/skills/morning-briefingSKILL.md
# Morning Briefing State file: `~/.openclaw/skill-state/morning-briefing/state.yaml` Start every working day knowing exactly what matters — one message, no tab-switching. ## When to Use - On 7am weekday cron wakeup - When the user asks for a morning update or daily kickoff ## The Briefing Compile from these sources, in order: 1. **Today's priorities** — read `priorities` from `daily-review` state file (`~/.openclaw/skill-state/daily-review/state.yaml`) 2. **Active tasks** — read any task with `status: in_progress` from `long-running-task-management` state file 3. **Pending handoffs** — check `task-handoff` state; if `status: written`, flag it 4. **Date and day** — include today's date and day of week at the top ## Output Format ``` Good morning. Here's your [Day], [Date] briefing. PRIORITIES 1. [priority from daily-review] 2. ... IN PROGRESS - [task_id]: [checkpoint] → next: [next_action] NEEDS ATTENTION - [handoff task_name] waiting to be picked up ``` Send via the user's active messaging channel (Telegram, Slack, etc.). ## After Delivery Update state: `last_briefing_date` (today), `delivered_at`, `items_count` (total items in briefing). ## Cron Wakeup Behavior On 7am weekday wakeup: - Read state; if `last_briefing_date` is today, skip (already delivered) - Otherwise compile and deliver briefing, then 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.