groove-utilities-task-create
groove-utilities-task-create
Outcome
A task is created in the configured backend with a title, type, status, optional parent, and (for non-trivial tasks) a rich body. The task ID is returned for reference. This command is the single source of truth for how tasks are created — other skills (work compound, daily, etc.) that need to create tasks must follow this spec and call this skill rather than defining their own creation rules.
Acceptance Criteria
- Task exists in backend with all required fields populated
- Task ID is shown to user after creation
- Non-trivial tasks (feature work, bugs, plans, stage tasks) have a rich body — never create with an empty body when the task represents real work or a stage
- Parent is set when context suggests one (e.g. stage task under a daily or work epic)
Constraints
- Read
tasks.backendfrom.groove/index.mdto determine backend - If
tasks.backend: none, no-op with friendly message - If title not provided in arguments, ask user for title and type before proceeding
- Infer parent from current context (open tasks, recent work) and confirm with user if ambiguous
- Default status is
in-progress(nottodo) — tasks are created when work is being done - Do not auto-mark any task as completed during creation
- Backend mappings:
beans:beans create "<title>" -t <type> --parent <id> -s in-progress; body viabeans update <id> -d "<body>"or by editing the task file under.groove/tasks/if the backend is file-basedlinear: create issue via linear CLI or MCP with appropriate team/projectgithub:gh issue create --title "<title>" --body "<body>" --milestone <milestone>
- Body (standard): For any non-trivial task, always supply a body. Use the backend's body/description field (or task file content). Standard body sections: Context (what work or session this task belongs to), Goal (what "done" means at a high level), Acceptance Criteria (checklist of concrete conditions), Links (to CHANGELOG, specs, learned files, or other artifacts). Omit a section only if it truly does not apply.
- Type: Use the backend's types (e.g. beans:
task,bug,feature,epic,milestone). Stage and bookend tasks (daily Start/End, work stages such as "YYYY-MM-DD, Compound — topic") use typetaskwhen the backend has nochore(e.g. beans). - Hierarchy: Set parent when the task is part of a larger unit (e.g. a daily, an epic). If the caller does not specify a parent, infer from context when possible.
- Always echo the created task ID and title back to the user
More from andreadellacorte/groove
pdf-to-markdown
[Document Processing] Convert PDF files to Markdown with support for native text PDFs and scanned documents (OCR). Cross-platform.
257agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
251groove
Groove engineering workflow system. Top-level entry point. Use groove-daily-*, groove-work-*, groove-utilities-*, groove-admin-* for all workflow and admin commands.
248find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
245groove-utilities-memory-log-daily
Write the daily memory log entry. Use at end of day to record what happened.
235groove-daily-start
Start the workday: review yesterday, create today's daily memory, load tasks, prepare agenda. Use when beginning the day.
231