From openclaw-cc
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly. Run: node scripts/gen-skill-docs.mjs -->
How this skill is triggered — by the user, by Claude, or both
Slash command
/openclaw-cc:daily-routineThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly. Run: node scripts/gen-skill-docs.mjs -->
Before executing this skill:
Load context from memory:
memory_search(query: "{skill-relevant-query}", associative: true, limit: 5)
memory_search(tag: "{skill-name}", limit: 3)
Review returned memories for relevant past context, decisions, and patterns.
Check OMC state for active work:
state_get_status()
If conflicting active tasks exist, warn the user before proceeding.
Detect current branch (for git-related skills):
git rev-parse --abbrev-ref HEAD 2>/dev/null || echo "not-a-git-repo"
Check proactive mode:
state_read("occ-proactive")
If "false": do NOT proactively suggest other OpenClaw-CC skills during this session.
Only run skills the user explicitly invokes.
Log skill activation:
memory_daily_log(type: "note", entry: "Skill activated: /{skill-name}")
Automate the 4 routines that structure the user's day (morning briefing, task management, evening review, weekly retrospective) using the memory-manager and messenger-bot MCP tools. Registering as a cron job in task-scheduler enables fully autonomous execution.
Trigger: Automatic execution on weekdays at 09:00, or on "morning briefing", "today's briefing" request
memory_search:
category: "daily-logs"
limit: 1
→ Retrieve daily log from yesterday
→ Summarize main activities in 3 lines
memory_search:
tag: "todo"
limit: 20
→ Sort results descending by importance
→ Group in order: priority-high > priority-mid > priority-low
memory_search:
tag: "{today's date, e.g. 2026-03-21}"
limit: 10
→ Sort meetings, deadlines, events chronologically
web_search:
query: "{user's areas of interest} latest news"
→ Web3 security, AI agents, startup-related
→ Top 3 results only, summarized in one line each
→ This step is optional; skip if network request fails
Fill in the morning briefing template from references/routine-templates.md with the collected data.
Send notifications for significant events via messenger:
| Event | Platform | Priority |
|---|---|---|
| Task/pipeline completed | telegram | Normal |
| Verification failed | telegram | High |
| Long-running task done (10+ min) | telegram | Normal |
| Critical error or blocker | telegram | High |
| PR created / release shipped | all | Normal |
| Importance ≥ 8 memory created | telegram | Normal |
messenger_send(
platform: "telegram",
message: "[{skill-name}] {status_emoji} {brief description}\n\n{details if relevant}"
)
Status Emojis:
messenger_send:
platform: "telegram"
message: "{generated briefing markdown}"
Also record the briefing in the daily log:
memory_daily_log:
entry: "Morning briefing generated and sent"
type: "note"
When the user mentions a task, store it as follows:
memory_store:
category: "tasks"
title: "{task title}"
content: "{detailed description (if any)}"
tags: ["todo", "priority-{high|mid|low}", "{project name}"]
importance: {high=9, mid=7, low=6}
Record confirmation after saving:
memory_daily_log:
entry: "Task added: {task title}"
type: "todo"
memory_update:
id: {relevant memory ID}
mode: "metadata"
tags: ["done", ...existing tags with "todo" removed]
memory_daily_log:
entry: "{task title} completed"
type: "done"
Run on "organize tasks", "today's tasks" request:
memory_search:
tag: "todo"
limit: 30
→ Sort descending by importance
→ Visualize with icons: priority-high (🔴), priority-mid (🟡), priority-low (🟢)
→ Mark overdue items with ⚠️
Trigger: Automatic execution daily at 21:00, or on "wrap up the day", "evening review" request
memory_search:
category: "daily-logs"
limit: 1
→ Retrieve full log for today's date
memory_search:
tag: "done"
category: "tasks"
limit: 20
→ Collect items completed today
memory_search:
tag: "todo"
limit: 20
→ Collect items still incomplete
Among incomplete items:
importance >= 7 → Automatically carry over (keep as tomorrow's task)importance < 7 → Suggest to user whether to carry overFill in the evening review template from references/routine-templates.md with the data.
Record the review in the daily log:
memory_daily_log:
entry: "Daily review complete — Completed {N}, Incomplete {M}, Carried over {K}"
type: "note"
Trigger: Automatic execution on Sundays at 20:00, or on "weekly summary", "weekly review" request
memory_search:
category: "daily-logs"
limit: 7
→ Collect Monday–Sunday logs in chronological order
memory_search:
category: "projects"
limit: 20
→ Filter by updated_at within this week
→ Group by project and summarize progress
Extract type: "decision" entries from daily logs and compile them.
Based on incomplete tasks and project progress, propose the Top 3 priorities for next week.
Fill in the weekly retrospective template from references/routine-templates.md with the data.
messenger_send:
platform: "telegram"
message: "{generated weekly retrospective markdown}"
After completing the workflow, persist results to the 3-layer memory system:
Log completion to daily log:
memory_daily_log(type: "done", entry: "{skill-name}: {brief result summary}")
Store significant findings (importance ≥ 6):
memory_store(
category: "{appropriate category}",
title: "{descriptive title}",
content: "{structured result content}",
tags: ["{skill-name}", "{project}", "{relevant-tags}"],
importance: {6-10 based on significance}
)
Link to related memories (if applicable):
memory_link(source: "{new_memory_id}", target: "{related_id}", relation: "{related|derived|refines}")
| Content Type | Category | Subcategory |
|---|---|---|
| Bug fix / debugging | knowledge | debugging |
| Code review results | projects | {project-name} |
| Design decisions | projects | {project-name} |
| Research findings | knowledge | {topic} |
| Release / deploy | projects | {project-name} |
| Person-related info | people | — |
| Task / action item | tasks | — |
memory_store:
category: "daily-logs"
title: "Weekly Retrospective — Week {N}"
content: "{retrospective markdown}"
tags: ["weekly-review", "{year-month}"]
importance: 6
Call task_create on the task-scheduler MCP to register automated execution:
task_create:
name: "Morning Briefing"
prompt: "Generate morning briefing and send via Telegram"
cron: "0 9 * * 1-5"
allowedTools: ["memory-manager", "messenger-bot"]
tags: ["routine", "morning"]
enabled: true
task_create:
name: "Evening Review"
prompt: "Write end-of-day review"
cron: "0 21 * * *"
allowedTools: ["memory-manager"]
tags: ["routine", "evening"]
enabled: true
task_create:
name: "Weekly Retrospective"
prompt: "Generate weekly retrospective and send via Telegram"
cron: "0 20 * * 0"
allowedTools: ["memory-manager", "messenger-bot"]
tags: ["routine", "weekly"]
enabled: true
| Task | MCP Tool | Notes |
|---|---|---|
| Retrieve daily log | memory_search | category:"daily-logs" |
| Retrieve tasks | memory_search | tag:"todo" |
| Retrieve schedule | memory_search | tag:date |
| Save task | memory_store | category:"tasks" |
| Mark task complete | memory_update | mode:"metadata" |
| Record log | memory_daily_log | Emoji auto-added by type |
| Memory status | memory_stats | For weekly retrospective stats |
| Send message | messenger_send | platform:"telegram" |
| Register auto-run | task_create | cron expression |
references/routine-templates.mdscripts/generate-briefing.pyEvery skill must end with one of these status codes:
| Code | Meaning | When to Use |
|---|---|---|
| DONE | All steps completed, evidence provided | Root cause found + fix verified, PR created, review finished |
| DONE_WITH_CONCERNS | Completed with warnings or caveats | Tests pass but coverage dropped, fix applied but can't fully verify |
| BLOCKED | Cannot proceed, requires user intervention | 3 failed attempts, missing permissions, external dependency down |
| NEEDS_CONTEXT | Missing information to continue | Unclear requirements, need user clarification |
3-strike rule: After 3 failed attempts at any step, STOP and escalate to user. Do not continue guessing. Present what was tried and ask for direction.
Scope escalation: If fix/change touches 5+ files unexpectedly, pause and confirm with the user before proceeding.
Security uncertainty: If you are unsure about a security implication, STOP and escalate. Never guess on security.
Verification requirement: Never claim DONE without evidence.
═══════════════════════════════════════
Status: {DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT}
Summary: {one-line description of outcome}
Evidence: {test output, verification results, or blocking reason}
═══════════════════════════════════════
npx claudepluginhub kit4some/oh-my-claudeclaw --plugin openclaw-ccConducts a structured weekly review to clear inboxes, review projects, and set priorities, reducing cognitive load and improving focus for the coming week.
Provides a structured morning briefing with AI-powered insights, news, and task prioritization to start the day efficiently.