Best use case
daily-briefing is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Morning briefing: tasks + email + follow-ups
Teams using daily-briefing should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/daily-briefing/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How daily-briefing Compares
| Feature / Agent | daily-briefing | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Morning briefing: tasks + email + follow-ups
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Daily Briefing
> Morning summary: tasks, emails, follow-ups, priorities
## When to use
- "good morning" / "morning"
- "what's today?"
- "daily briefing"
- "start of day"
- At the beginning of work day
## Paths
| What | Path |
|------|------|
| Tasks | `$PM_PATH/pm_tasks_master.csv` |
| Leads | `$CRM_PATH/relationships/leads.csv` |
| People (CRM) | `$CRM_PATH/contacts/people.csv` |
| Email script | `$GOOGLE_TOOLS_PATH/read_emails.py` |
## How to execute
### Step 1: Read tasks
```python
import pandas as pd
from datetime import date
today = str(date.today())
tasks = pd.read_csv('$PM_PATH/pm_tasks_master.csv')
# Deadline today
deadline_today = tasks[tasks['deadline'] == today]
# In progress
in_progress = tasks[tasks['status'] == 'in_progress']
# Hot tasks (not done)
hot_tasks = tasks[(tasks['priority'] == 'hot') & (tasks['status'] != 'done')]
# Top by priority score
tasks_sorted = tasks[tasks['status'].isin(['todo', 'in_progress'])].sort_values(
'priority_score', ascending=False
)
```
### Step 2: Check leads follow-ups (source of truth for sales)
```python
leads = pd.read_csv('$CRM_PATH/relationships/leads.csv')
leads_today = leads[leads['next_action_date'] == today]
```
### Step 3: Check CRM follow-ups
```python
try:
people = pd.read_csv('$CRM_PATH/contacts/people.csv')
followups = people[people['next_followup_date'] == today]
except:
followups = pd.DataFrame()
```
### Step 4: Check inbox
```bash
cd $GOOGLE_TOOLS_PATH
python3 read_emails.py 10
```
### Step 5: Output format
```markdown
## Good Morning! Daily Briefing for [DATE]
### Inbox ([N] unread)
| From | Subject | Preview |
|------|---------|---------|
| ... | ... | ... |
### Deadline TODAY
| Task | Project | Description |
|------|---------|-------------|
| ... | ... | ... |
### In Progress
| Task | Project | Description |
|------|---------|-------------|
| ... | ... | ... |
### Hot Tasks (Top 5)
| Score | Task | Description | Note |
|-------|------|-------------|------|
| ... | ... | ... | ... |
### Leads Follow-ups TODAY (source of truth)
| Lead | Next Action | Stage |
|------|-------------|-------|
| ... | ... | ... |
### CRM Follow-ups TODAY
| Person | Company | Note |
|--------|---------|------|
| ... | ... | ... |
### Recommended to Start
**[Task name]**
- Project: [project_id]
- Description: [description]
- Why: highest priority_score / blocking others / deadline approaching
```
## Priority logic
1. **Deadline today** - must do
2. **Blocking others** - unblocks team
3. **Highest priority_score** - calculated importance
4. **In progress** - finish what started
## Quick command
For Claude to run daily briefing:
1. Read this skill
2. Execute all steps
3. Format output
4. Ask: "Ready to start with [top task]?"
## Task completion rule
**IMPORTANT:** If during briefing user says a task is already done, or you discover from email/context that a task was completed:
1. **Mark it done immediately** (status=done, last_updated=today, update notes)
2. **Suggest follow-up** if applicable (invoice -> check payment, email -> check reply)
3. **Re-show** updated briefing without the completed task
See `pm-done` skill for full logic and auto-follow-up rules.
## Related skills
- `pm-done` - Mark task done + follow-up
- `show-today` - Tasks only (no email/crm)
- `email-read` - Email only
- `query-leads` - CRM details
- `weekly-review` - Weekly reviewRelated Skills
team-daily-report
自动汇总团队内 agent、cron、skill 进展与关键事件,生成并推送结构化日报。
daily-xhs-content — 小红书每日内容生产
> Cron: `daily-xhs-content` | 每日 21:00 | agentId: content
daily-trending
获取今日热榜,从tophub.today抓取各平台热搜榜单。当用户询问"今天有什么热搜"、"热榜"、"微博热搜"时触发。
daily-reflection
Evening reflection — full P&L review and strategy adjustment at end of day
daily-portfolio
Morning portfolio review — full position snapshot and daily P&L report
daily-gzh-content — 公众号每日内容生产
> Cron: `daily-gzh-content` | 每日 21:30 | agentId: content
daily-douyin-content — 抖音每日内容生产
> Cron: `daily-douyin-content` | 每日 22:00 | agentId: content
wemp-operator
> 微信公众号全功能运营——草稿/发布/评论/用户/素材/群发/统计/菜单/二维码 API 封装
zsxq-smart-publish
Publish and manage content on 知识星球 (zsxq.com). Supports talk posts, Q&A, long articles, file sharing, digest/bookmark, homework tasks, and tag management. Use when publishing content to 知识星球, creating/editing posts, uploading files/images/audio, managing digests, batch publishing, or formatting content for 知识星球.
zoom-automation
Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.
zoho-crm-automation
Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.
ziliu-publisher
字流(Ziliu) - AI驱动的多平台内容分发工具。用于一次创作、智能适配排版、一键分发到16+平台(公众号/知乎/小红书/B站/抖音/微博/X等)。当用户需要多平台发布、内容排版、格式适配时使用。触发词:字流、ziliu、多平台发布、一键分发、内容分发、排版发布。