diff options
| author | Paul Buetow <paul@buetow.org> | 2026-03-19 21:38:35 +0200 |
|---|---|---|
| committer | Paul Buetow <paul@buetow.org> | 2026-03-19 21:38:35 +0200 |
| commit | 5f91fb7d257046e3ca641fbb29a3423afdc83a15 (patch) | |
| tree | 28fadf100a5e752697f683014332059b563d9747 /prompts/skills/taskwarrior-task-management/SKILL.md | |
| parent | ccd3c4ce1125cdc0e15e09bdfe28704b5ca6f44c (diff) | |
ask ...
Diffstat (limited to 'prompts/skills/taskwarrior-task-management/SKILL.md')
| -rw-r--r-- | prompts/skills/taskwarrior-task-management/SKILL.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/prompts/skills/taskwarrior-task-management/SKILL.md b/prompts/skills/taskwarrior-task-management/SKILL.md index 6d88e7f..b706ff8 100644 --- a/prompts/skills/taskwarrior-task-management/SKILL.md +++ b/prompts/skills/taskwarrior-task-management/SKILL.md @@ -7,7 +7,7 @@ description: "Manage Taskwarrior tasks scoped to the current git project. Use wh Taskwarrior tasks are scoped to the current git repository. **Load only the files you need** for the current action so the whole skill does not need to be in context. -Prefer `ask ...` for agent-managed project tasks. `ask` is Taskwarrior-compatible because it pre-sets `project:<name> +agent` while preserving normal Taskwarrior commands, reports, filters, and UUID workflows. `hexai task ...` is a compatibility alias with the same behavior. +Always use `ask ...` for all task operations. `ask` is a tiny wrapper that pre-sets `project:<name> +agent`, scoping every command to the current project's agent-managed tasks while preserving normal Taskwarrior commands, reports, filters, and UUID workflows. `hexai task ...` is a compatibility alias with the same behavior. Never use the raw `task` command directly. Taskwarrior numeric IDs are **ephemeral working-set indices** and may be renumbered; this skill treats **UUIDs as the stable identifiers** for tasks. Use numeric IDs only within a single “report → immediate command” flow, and use UUIDs for anything that must survive across sessions, agents, or reports. |
