Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Launch non-blocking interactive Claude Code tasks for slash-only plugins like ralph-loop. Use when a task needs interactive slash commands and completion cal...
Launch non-blocking interactive Claude Code tasks for slash-only plugins like ralph-loop. Use when a task needs interactive slash commands and completion cal...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Format: /dispatchi <project> <task-name> <prompt...> Workdir mapping: ${REPOS_ROOT:-/home/miniade/repos}/<project> Defaults: max-iterations=20, completion-promise=COMPLETE Auto-exit: when completion promise appears on its own line, wrapper requests /exit and closes tmux session.
optional env file: ${OPENCLAW_DISPATCH_ENV:-<workspace>/skills/dispatch.env.local} supports OpenClaw skills.entries.dispatchi.env injection script is self-contained (bundled claude_code_run.py)
Reads only allowlisted env keys from dispatch.env.local using key=value parsing (no source). Launches local tmux session and local Claude process; writes output to configured result paths. Network callback is disabled by default; enable only with ENABLE_CALLBACK=1 and explicit group settings. No runtime download of external code.
Validate args and return usage if incomplete. Start interactive dispatch in background (non-blocking). Verify tmux session exists before returning started. Use /cancel <run-id> to stop a running loop.
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.