Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Generator for file-based task state machines (registry + task folders + lifecycle state + queue files + cron specs/jobs) for long-running work.
Generator for file-based task state machines (registry + task folders + lifecycle state + queue files + cron specs/jobs) for long-running work.
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.
Create and manage durable, file-based task state machines under the OpenClaw workspace. Target filesystem shape: TASK_REGISTRY.md (global index) tasks/<task_slug>/ TASK.md (front matter + purpose/decisions/blockers/changelog + capabilities) TODOS.md (checklist) scripts/ crons/ artifacts/ optional queue-state files (queue.jsonl, done.jsonl, failed.jsonl, lock.json)
Run on host where OpenClaw is running: python3 --version openclaw status openclaw cron --help
Skill-local config files: Example (shareable): config.env.example Real machine config: config.env Keys: WORKSPACE_DIR (default: /home/miles/.openclaw/workspace) TASKS_DIR (default: tasks) REGISTRY_FILE (default: TASK_REGISTRY.md) DEFAULT_AGENT_ID (default: main) DEFAULT_CRON_TZ (default: America/Indianapolis)
Answer in chat: task slug (filesystem-safe) task title task purpose optional skills/plugins/tools expected for this task whether queue files are needed whether a cron job should be created now Then run: python3 scripts/task_father.py init <slug> --title "..." --purpose "..." --skills "a,b" --plugins "x,y" --tools "read,write,exec" optional queue mode: python3 scripts/task_father.py enable-queue <slug> optional cron setup: python3 scripts/task_father.py cron-add <slug> --cron "*/10 * * * *" --message "<worker prompt>" --name "task-<slug>"
cp config.env.example config.env Edit config.env Initialize task: python3 scripts/task_father.py init <slug> --title "..."
Set task status (updates state.json + changelog): python3 scripts/task_father.py set-state <slug> active Append changelog entry: python3 scripts/task_father.py log <slug> "blocked by API quota" Enable queue files: python3 scripts/task_father.py enable-queue <slug> Add cron: python3 scripts/task_father.py cron-add <slug> --cron "*/5 * * * *" --message "..." --name "task-<slug>" Remove cron: python3 scripts/task_father.py cron-rm <slug> --name "task-<slug>"
Each task must contain: TASK.md with front matter and sections: Purpose Important Decisions Blockers Capabilities (skills/plugins/tools) Change Log (timestamp + short description) TODOS.md with checklist items. If queue-style long processing is used: queue.jsonl, done.jsonl, failed.jsonl, lock.json. Scripts under: <task_folder>/scripts/ Cron files under: <task_folder>/crons/
Keep machine-specific values in config.env, not in SKILL.md. Keep logs append-only where possible. Use small resumable batches for long work.
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.