Best use case
openhook-cli is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Teams using openhook-cli 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/openhook-cli/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How openhook-cli Compares
| Feature / Agent | openhook-cli | 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?
This skill provides specific capabilities for your AI agent. See the About section for full details.
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.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# openhook CLI
Use the openhook CLI to receive real-time events from external platforms and communicate with other agents through channels.
## When to use
- Receiving webhook events from GitHub, Stripe, Linear, Vercel, Slack
- Listening for external platform events in real-time
- Sending messages to other agents through channels
- Coordinating multi-agent workflows
## Installation
```bash
brew tap openhook-dev/openhook && brew install openhook
```
## Authentication
Requires an API key from openhook. The user must:
1. Sign up at https://openhook.dev/signup
2. Go to Settings > API Keys
3. Create a new API key (starts with `oh_live_` or `oh_test_`)
Then authenticate:
```bash
openhook auth login --key oh_live_xxxxxxxx
# Verify authentication worked
openhook whoami
```
## Receiving Events
### Subscribe to platform events
```bash
# GitHub
openhook subscribe github --repo owner/repo --events push,pull_request,issues
# Stripe
openhook subscribe stripe --events payment_intent.succeeded,customer.created
# Linear
openhook subscribe linear --events issue.created,issue.updated
```
### Listen for events
```bash
# Interactive output
openhook listen
# JSON output (for parsing)
openhook listen --json
# Pipe to your processing script
openhook listen --json | jq '.payload'
```
### Background daemon
```bash
openhook daemon start
openhook daemon status
openhook daemon logs -f
openhook daemon stop
```
## Channels (Agent-to-Agent Communication)
Channels let agents send messages to each other. Each agent subscribes to a channel with a unique name, then messages can be sent to specific agents or broadcast to all.
### Create a channel
```bash
openhook channel create <name> [--description "..."]
# Example
openhook channel create deploy-team --description "Deployment coordination"
```
### Subscribe to a channel
Each subscription needs:
- `--endpoint`: The HTTP endpoint ID that will receive messages
- `--name`: A unique alias for this agent in the channel
```bash
openhook channel subscribe <channel-id> --endpoint <endpoint-id> --name <alias>
# Example: Subscribe the "deployer" agent
openhook channel subscribe ch_abc123 --endpoint ep_xyz789 --name deployer
```
### List channel members
```bash
openhook channel members <channel-id>
openhook channel members <channel-id> --json
```
### Send messages
```bash
# Send to specific agent
openhook channel send <channel-id> "<message>" --to <agent-name>
# Broadcast to all agents
openhook channel send <channel-id> "<message>" --to all
# Include sender info
openhook channel send <channel-id> "<message>" --to <agent-name> --from <your-name>
```
### Channel workflow example
```bash
# 1. Create coordination channel
openhook channel create release-v2 --description "v2.0 release coordination"
# 2. Agents join with their endpoints
openhook channel subscribe ch_xxx --endpoint ep_builder --name builder
openhook channel subscribe ch_xxx --endpoint ep_tester --name tester
openhook channel subscribe ch_xxx --endpoint ep_deployer --name deployer
# 3. Coordinate the release
openhook channel send ch_xxx "build v2.0.0" --to builder --from coordinator
openhook channel send ch_xxx "run integration tests" --to tester --from builder
openhook channel send ch_xxx "deploy to staging" --to deployer --from tester
openhook channel send ch_xxx "v2.0.0 deployed successfully" --to all --from deployer
```
## Managing subscriptions
```bash
# List all subscriptions
openhook list
# View event history
openhook events
# Remove subscription
openhook unsubscribe <subscription-id>
```
## Common patterns
### Wait for specific event
```bash
# Listen until you get the event you need
openhook listen --json | while read -r event; do
type=$(echo "$event" | jq -r '.event_type')
if [ "$type" = "push" ]; then
echo "$event" | jq '.payload'
break
fi
done
```
### React to GitHub push
```bash
openhook subscribe github --repo myorg/myrepo --events push
openhook listen --json | jq -c 'select(.event_type == "push") | .payload.commits'
```
## Reference
| Command | Description |
|---------|-------------|
| `openhook whoami` | Show authenticated user |
| `openhook subscribe <platform>` | Subscribe to platform events |
| `openhook list` | List subscriptions |
| `openhook unsubscribe <id>` | Remove subscription |
| `openhook listen [--json]` | Listen for events |
| `openhook events` | View event history |
| `openhook channel create <name>` | Create channel |
| `openhook channel list` | List channels |
| `openhook channel subscribe <ch> --endpoint <ep> --name <alias>` | Join channel |
| `openhook channel members <ch>` | List members |
| `openhook channel send <ch> <msg> --to <name\|all>` | Send message |
## Links
- Website: https://openhook.dev
- Dashboard: https://openhook.dev/dashboard
- GitHub: https://github.com/openhook-dev/openhook-cliRelated Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述