async-taskRun and manage long tasks exceeding HTTP timeouts by starting, updating, and completing them asynchronously with immediate responses.
Install via ClawdBot CLI:
clawdbot install Enderfga/async-taskExecute long-running tasks without HTTP timeouts. Use when you need to:
IMPORTANT: When a task might timeout, you MUST use this skill to avoid empty response from server errors.
Triggers: "async task", "long running", "timeout", "background task", "push result"
# Clone and link globally
git clone https://github.com/Enderfga/openclaw-async-task.git
cd openclaw-async-task
npm link
# Or just copy async-task.js to your PATH
chmod +x async-task.js
cp async-task.js /usr/local/bin/async-task
async-task start "<description>" # Start task, returns immediately
async-task done "<result>" # Complete task, push result to user
async-task fail "<error>" # Task failed, push error message
async-task push "<message>" # Push message directly (no start needed)
async-task status # Show current task status
async-task start "Scanning files..."async-task done "Found 42 files"User asks: "Count all TypeScript files in this project"
# Step 1: Acknowledge immediately
async-task start "Counting TypeScript files..."
# Step 2: Do the actual work
count=$(find . -name "*.ts" | wc -l)
# Step 3: Push the result
async-task done "Found $count TypeScript files"
start saves task state and returns confirmation immediatelydone/fail uses OpenClaw/Clawdbot CLI to push result to the active sessionZero configuration required - automatically detects active session via openclaw sessions or clawdbot sessions.
For custom webchat or notification systems:
export ASYNC_TASK_PUSH_URL="https://your-server.com/api/push"
export ASYNC_TASK_AUTH_TOKEN="your-token"
The endpoint receives:
{
"sessionId": "session-id",
"content": "message",
"role": "assistant"
}
| Variable | Required | Description |
|----------|----------|-------------|
| OPENCLAW_SESSION | No | Target session (auto-detected) |
| ASYNC_TASK_PUSH_URL | No | Custom HTTP push endpoint |
| ASYNC_TASK_AUTH_TOKEN | No | Auth token for custom endpoint |
start with done or failGenerated Mar 1, 2026
Developers can use this skill to analyze extensive code repositories for security vulnerabilities or code quality metrics without encountering HTTP timeouts. It allows for scanning thousands of files, generating detailed reports, and pushing results once the analysis is complete, ensuring reliable long-running operations.
Data engineers can leverage this skill to execute ETL (Extract, Transform, Load) jobs that process large datasets from external APIs or databases. It handles unpredictable latency and multi-step operations, pushing processed data summaries or error notifications upon completion to maintain workflow efficiency.
QA teams can run comprehensive automated test suites on web applications or APIs that may take several minutes. The skill prevents timeout errors by starting the task, executing tests in the background, and pushing pass/fail results with detailed logs, improving testing reliability in CI/CD pipelines.
Content creators and marketers can use this skill to generate or summarize large documents, such as reports or articles, using AI models with high latency. It starts the task, processes the content asynchronously, and pushes the final output, avoiding interruptions during lengthy generation processes.
Offer this skill as part of a subscription-based platform that integrates with existing developer tools like IDEs or CI/CD systems. Provide premium features such as advanced analytics, custom push endpoints, and priority support, generating revenue through monthly or annual licenses.
Provide consulting services to businesses needing tailored async task solutions for specific workflows, such as data processing or automation. Develop custom integrations, offer training, and charge on a project basis or hourly rates, leveraging the skill's flexibility for diverse client needs.
Distribute the skill as a free, open-source tool for individual developers, with paid enterprise versions offering enhanced capabilities like team collaboration, audit logs, and SLA guarantees. Monetize through upselling to larger organizations requiring scalability and compliance features.
💬 Integration Tip
Ensure Node.js and OpenClaw/Clawdbot CLI are installed, and follow the strict usage flow of start, execute, and push to avoid errors in async operations.
Terminal Spotify playback/search via spogo (preferred) or spotify_player.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.
Download videos from YouTube, Bilibili, Twitter, and thousands of other sites using yt-dlp. Use when the user provides a video URL and wants to download it, extract audio (MP3), download subtitles, or select video quality. Triggers on phrases like "下载视频", "download video", "yt-dlp", "YouTube", "B站", "抖音", "提取音频", "extract audio".
Search and add movies to Radarr. Supports collections, search-on-add option.
Control Spotify playback on macOS. Play/pause, skip tracks, control volume, play artists/albums/playlists. Use when a user asks to play music, control Spotify, change songs, or adjust Spotify volume.
Search and add TV shows to Sonarr. Supports monitor options, search-on-add.