<task_skill_guides>
You are executing a task within the LobeHub task system. Use the lh task CLI via runCommand to manage your task and related resources.
Read the reference file for detailed command options: readReference('references/commands')
Run commands via runCommand — the lh prefix is automatically handled
Use --json flag on any command for structured output
Use lh task <subcommand> --help for full command-line help
Task Execution Guidelines
Check your task first: Use lh task view to understand the full instruction and context
Use workspace documents: Store outputs and deliverables as task documents
Report progress: Use lh task comment to log key milestones
Respect dependencies: Check lh task tree to understand task ordering
Complete when done: Use lh task complete when all deliverables are ready
Automation tasks are the exception — NEVER complete them: a task with automation (heartbeat or schedule — shown as an Automation: line in the task context) is a recurring loop, and this run is one tick of it. NEVER run lh task complete (or set a terminal status via lh task edit --status) on that task: a terminal status cancels the in-flight run and permanently disarms the loop — no future tick will fire and nothing recovers it. A tick with nothing to do is still a successful run; just finish your turn and the next tick is armed automatically. Only the user retires a recurring task.
</task_skill_guides>
1---2name: task-23description: \<task\_skill\_guides>4---5\<task\_skill\_guides>6You are executing a task within the LobeHub task system. Use the `lh task` CLI via `runCommand` to manage your task and related resources.78# Task Lifecycle910| Command | Description |11| ------------------------------- | ----------------------------------------------------- |12| `lh task view <id>` | View task details, instruction, workspace, activities |13| `lh task edit <id>` | Update task name, instruction, status, priority |14| `lh task complete <id>` | Mark task as completed |15| `lh task comment <id> -m "..."` | Add a progress comment |16| `lh task tree <id>` | View subtask tree with dependencies |1718# Working with Subtasks1920| Command | Description |21| ----------------------------------------- | ----------------- |22| `lh task create -i "..." --parent <id>` | Create a subtask |23| `lh task list --parent <id>` | List subtasks |24| `lh task sort <parentId> <id1> <id2> ...` | Reorder subtasks |25| `lh task dep add <id> <dependsOnId>` | Add dependency |26| `lh task dep rm <id> <dependsOnId>` | Remove dependency |2728# Task Workspace (Documents)2930| Command | Description |31| ------------------------------------------------- | ------------------------- |32| `lh task doc create <id> -t "title" -b "content"` | Create and pin a document |33| `lh task doc pin <id> <docId>` | Pin existing document |34| `lh task doc unpin <id> <docId>` | Unpin document |3536# Task Topics (Conversations)3738| Command | Description |39| ----------------------------------- | ------------------------ |40| `lh task topic list <id>` | List conversation topics |41| `lh task topic view <id> <topicId>` | View topic messages |4243# Usage Pattern44451. Read the reference file for detailed command options: `readReference('references/commands')`462. Run commands via `runCommand` — the `lh` prefix is automatically handled473. Use `--json` flag on any command for structured output484. Use `lh task <subcommand> --help` for full command-line help4950# Task Execution Guidelines5152- **Check your task first**: Use `lh task view` to understand the full instruction and context53- **Use workspace documents**: Store outputs and deliverables as task documents54- **Report progress**: Use `lh task comment` to log key milestones55- **Respect dependencies**: Check `lh task tree` to understand task ordering56- **Complete when done**: Use `lh task complete` when all deliverables are ready57- **Automation tasks are the exception — NEVER complete them**: a task with automation (heartbeat or schedule — shown as an `Automation:` line in the task context) is a recurring loop, and this run is one tick of it. NEVER run `lh task complete` (or set a terminal status via `lh task edit --status`) on that task: a terminal status cancels the in-flight run and permanently disarms the loop — no future tick will fire and nothing recovers it. A tick with nothing to do is still a successful run; just finish your turn and the next tick is armed automatically. Only the user retires a recurring task.58 \</task\_skill\_guides>
Run npx skillmds@latest add gabrielmoreira/task-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
\<task\_skill\_guides> It is listed under Productivity on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.
gabrielmoreira