← Back to Skills Marketplace
djy77733

Auto-Report

by DJY77733 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
108
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install auto-report
Description
Automated daily/weekly/monthly report generation with scheduled delivery. Use when: generating reports, creating cron-based report tasks, pushing structured...
README (SKILL.md)

📊 Auto-Report — Automated Report Generation

Generate structured reports on schedule and deliver them to any chat channel.

How It Works

Data Collection → Structured Summary → Template Rendering → Channel Delivery

Report Types

Type Frequency Best For
Daily Report Every day Work summaries, market recaps, health tracking
Weekly Report Once a week Sprint reviews, trend analysis, planning
Monthly Report Once a month KPI reviews, budget tracking
Ad-hoc Report On demand Incident analysis, deep research
Standup Report Daily/Weekly Team check-ins, progress updates

Report Templates

Daily Report

## [Date] Daily Report

### Key Metrics
- Metric 1: value
- Metric 2: value

### Highlights
1. ...
2. ...

### Analysis
- ...

### Tomorrow's Focus
- ...

Weekly Report

## Week X Report (MM.DD - MM.DD)

### This Week
- Mon: ...
- Tue: ...

### Metrics Summary
| Metric | This Week | Last Week | Change |
|--------|-----------|-----------|--------|

### Lessons Learned
1. ...
2. ...

### Next Week Plan
- ...

Scheduling with Cron

Create automated report tasks using OpenClaw cron:

# Daily report at 20:00 on workdays
openclaw cron add \
  --name "Daily Report" \
  --cron "0 20 * * 1-5" \
  --tz "Asia/Shanghai" \
  --session isolated \
  --agent-turn "Generate the daily report. Read the relevant data sources, structure the findings, and deliver to the target channel."

# Weekly report every Friday at 16:00
openclaw cron add \
  --name "Weekly Report" \
  --cron "0 16 * * 5" \
  --tz "Asia/Shanghai" \
  --session isolated \
  --agent-turn "Generate the weekly report covering this week's activity."

Cron Best Practices

  1. Use isolated sessions — prevents message duplication
  2. Use agentTurn — not systemEvent (avoids triple-delivery bugs)
  3. Set delivery.mode: "none" — let the agent handle messaging itself
  4. Keep prompts self-contained — isolated sessions have no context
  5. Set reasonable timeouts — 90-180s for simple reports, 300s for complex ones

Channel Delivery

Feishu (Lark) Interactive Card

{
  "config": {"wide_screen_mode": true},
  "header": {
    "title": {"tag": "plain_text", "content": "📊 Daily Report — 2026-04-06"},
    "template": "blue"
  },
  "elements": [
    {"tag": "markdown", "content": "**Key Metrics**\
▸ Revenue: +12%\
▸ Users: 1.2k active"},
    {"tag": "hr"},
    {"tag": "markdown", "content": "**Highlights**\
1. Launched new feature\
2. Fixed critical bug"},
    {"tag": "hr"},
    {"tag": "markdown", "content": "**Tomorrow**\
▸ Ship v2.1\
▸ Team standup at 10am"}
  ]
}

Use the message tool: action=send, channel=feishu, target=chat:\x3Cchat_id>, card=\x3Cjson>

Plain Text (any channel)

Use the message tool with a message parameter for simple text delivery.

Document Export

  • Use feishu_create_doc to create persistent documents (for archives)
  • Use feishu_update_doc to update existing documents

Report Quality Standards

  1. Data first — Collect real data before writing analysis
  2. Concise — Daily: 300-500 words, Weekly: 800-1200 words
  3. Actionable — Conclusions should drive decisions, not just describe
  4. Consistent format — Same structure every time for scannability
  5. No fluff — Skip filler phrases, lead with the most important info

Common Cron Schedules

# After market close (workdays)
0 15 * * 1-5   Asia/Shanghai   # A-share close
0 16 * * 1-5   Asia/Shanghai   # Buffer for data collection

# Evening summaries
0 20 * * 1-5   Asia/Shanghai   # Workday evening
0 22 * * *     Asia/Shanghai   # Before sleep

# Weekly reports
0 16 * * 5     Asia/Shanghai   # Friday afternoon
0 8 * * 1      Asia/Shanghai   # Monday morning

# Monthly reports
0 9 1 * *      Asia/Shanghai   # 1st of month

Advanced: Report Chains

For complex workflows, chain multiple cron jobs:

  1. Data collector (15:00) — Fetch raw data, save to file
  2. Analyzer (15:10) — Read data file, generate insights
  3. Publisher (15:15) — Format and deliver to channels

This prevents timeout issues with complex reports.

Examples

Health Tracking Report

# Daily health summary at 22:00
openclaw cron add --name "Health Daily" \
  --cron "0 22 * * *" --tz "Asia/Shanghai" \
  --session isolated \
  --agent-turn "Read health/LOG.md and health/PROFILE.md. Generate a health summary covering: water intake, meals, exercise, sleep, weight trend. Deliver to user via message tool."

Market Intelligence Report

# Market briefing at 07:00
openclaw cron add --name "Market Intel" \
  --cron "0 7 * * 1-5" --tz "Asia/Shanghai" \
  --session isolated \
  --agent-turn "Search for overnight US market data, commodity prices, and key news. Format as a structured briefing card and deliver to chat:oc_xxxxxx via message tool."

Compatibility

  • Works with any OpenClaw channel (Feishu, Telegram, Discord, Slack, etc.)
  • No external dependencies required
  • Works in both main and isolated session targets
Usage Guidance
This skill appears coherent for scheduled report generation, but it relies on the agent having permission to read data sources and to send messages to channels. Before installing: (1) review and narrow any agent-turn cron prompts so they only reference explicit files/data sources you want the agent to access; (2) prefer isolated sessions for scheduled runs to limit context exposure; (3) confirm which channel integrations (Feishu, Slack, etc.) are connected and what those connectors can send; (4) test cron jobs in a sandbox or staging channel to avoid accidental leakage of sensitive files; and (5) if you need market data from a paid API, consider adding explicit data-source instructions and credentials rather than relying on open web searches.
Capability Analysis
Type: OpenClaw Skill Name: auto-report Version: 1.0.0 The 'auto-report' skill bundle is a legitimate tool designed to automate report generation and delivery via OpenClaw's cron and messaging systems. The SKILL.md file provides clear instructions, templates, and examples for scheduling tasks (e.g., health tracking, market briefings) and delivering them to channels like Feishu. No evidence of malicious intent, data exfiltration, or unauthorized execution was found.
Capability Assessment
Purpose & Capability
Name/description match the behavior in SKILL.md: scheduling, collecting data, template rendering, and channel delivery. The examples (cron commands, Feishu card JSON, message tool usage) are coherent for a reporting automation skill and no unrelated environment variables or installers are requested.
Instruction Scope
Instructions legitimately require the agent to "read relevant data sources" and give examples that reference files (e.g., health/LOG.md). That is expected for reports, but the language is broad and could lead an agent to access arbitrary workspace files or external sources unless prompts are narrowly scoped. Also suggests web searches for market data (no API specified), which is consistent but open-ended.
Install Mechanism
No install spec and no code files are present (instruction-only). This is low-risk: nothing is written to disk or downloaded by the skill itself.
Credentials
The skill declares no environment variables or credentials. It expects the platform's existing message/document tools and channel connections to be available; that is proportionate. There are no unexpected credential requests.
Persistence & Privilege
always is false and the skill does not request persistent elevation or to modify other skills. Autonomous invocation is allowed (platform default) and is not combined with other red flags.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install auto-report
  3. After installation, invoke the skill by name or use /auto-report
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of auto-report: automated generation and scheduled delivery of daily, weekly, and monthly reports. - Supports cron-based scheduling for reports with customizable templates and structured summaries. - Delivers reports to any OpenClaw channel, including Feishu (Lark), with both card and plain text output. - Provides guidance for cron setup, quality standards, and advanced report chaining. - Compatible with all OpenClaw channels and requires no external dependencies.
Metadata
Slug auto-report
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Auto-Report?

Automated daily/weekly/monthly report generation with scheduled delivery. Use when: generating reports, creating cron-based report tasks, pushing structured... It is an AI Agent Skill for Claude Code / OpenClaw, with 108 downloads so far.

How do I install Auto-Report?

Run "/install auto-report" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Auto-Report free?

Yes, Auto-Report is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Auto-Report support?

Auto-Report is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Auto-Report?

It is built and maintained by DJY77733 (@djy77733); the current version is v1.0.0.

💬 Comments