Claude-skill-registry batch-notification

Send IM messages to users in batch. Used for notifying specific user groups, sending after table filtering, all-staff notifications, etc. Use this Skill when administrators request batch notifications, mass messaging, or notifications after table filtering. Trigger words: notify/send/mass + users/batch/table.

install

source · Clone the upstream repo

git clone https://github.com/majiayu000/claude-skill-registry

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/batch-notification" ~/.claude/skills/majiayu000-claude-skill-registry-batch-notification && rm -rf "$T"

manifest: skills/data/batch-notification/SKILL.md

Batch User Notification

Support administrators to send IM notification messages to users in batch.

Typical Scenarios

Upload table + filter conditions: Notify all users with benefits points greater than 0
Upload target list: Notify specified user list
All-staff notification: Notify everyone

Quick Start

All-staff Notification

mcp__{channel}__send_markdown_message(
    touser="@all",
    content="## Notification Title\n\nNotification content..."
)

Filtered Notification

python3 -c "
import pandas as pd
mapping = pd.read_excel('knowledge_base/企业管理/人力资源/user_mapping.xlsx')
business = pd.read_excel('/tmp/data.xlsx')
filtered = business[business['积分'] > 0]
result = pd.merge(filtered, mapping, on='工号', how='inner')
print('|'.join(result['企业微信用户ID'].tolist()))
"

Detailed Workflow

Complete 5-stage workflow, see WORKFLOW.md

pandas Query Patterns

Common filtering, JOIN, date processing patterns, see PANDAS_PATTERNS.md

Example Scenarios

Complete end-to-end examples, see EXAMPLES.md

Core Principles

Privacy protection: Notifications are one-on-one private chats, messages must not contain other people's information
Must confirm: Must wait for administrator reply "confirm send" after constructing message
Python first: All table processing uses pandas
Result transparency: Clearly report sending results (success/failure counts)

Available Tools

Bash: Execute pandas scripts
mcp__{channel}__send_markdown_message: Send Markdown messages
mcp__{channel}__send_text_message: Send plain text messages