groove-utilities-task-archive — Claude Code skill: archive tasks
Archives completed and scrapped tasks in the configured backend. Use it when you want to close a batch of finished work with a confirmation step.
npx skills add andreadellacorte/groove --skill groove-utilities-task-archive -a claude-codeWhat groove-utilities-task-archive does
The skill reads tasks.backend from .groove/index.md, identifies the configured service, and displays the tasks in scope. It asks for confirmation before changing anything, then reports how many tasks were archived.
For beans, it runs beans archive, which handles all completed or scrapped tasks rather than one selected task. With linear, filtered issues are archived through the CLI or MCP. With github, resolved issues are closed using gh issue close. A tasks.backend: none setting leaves the project unchanged.
The skill runs only after an explicit request. It does not start as part of the daily end routine, so unattended archiving is avoided.
What it helps with
- archive completed tasks
- remove scrapped tasks from the active queue
- close resolved GitHub issues
- review the archive scope before execution
- report the number of archived tasks
Example prompts for the agent
- Archive all completed and scrapped tasks.
- Show me the archive scope, then run it after I confirm.
- Read
.groove/index.mdand archive the tasks through the configured backend.
How to install groove-utilities-task-archive
1Skills CLI (Vercel)
npx skills add andreadellacorte/groove --skill groove-utilities-task-archive -a claude-code2Manually: put the files in place
~/.claude/skills/groove-utilities-task-archive/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/groove-utilities-task-archive/
1Skills CLI (Vercel)
npx skills add andreadellacorte/groove --skill groove-utilities-task-archive -a codex2Manually: put the files in place
.agents/skills/groove-utilities-task-archive/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add andreadellacorte/groove --skill groove-utilities-task-archive -a cursor2Manually: put the files in place
.cursor/skills/groove-utilities-task-archive/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install andreadellacorte/groove groove-utilities-task-archive2Manually: put the files in place
.github/skills/groove-utilities-task-archive/SKILL.md1Skills CLI (Vercel)
npx skills add andreadellacorte/groove --skill groove-utilities-task-archive -a gemini-cli2Platform CLI
gemini skills install https://github.com/andreadellacorte/groove --path skills/groove-utilities-task-archiveManually: put the files in place
.devin/skills/groove-utilities-task-archive/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add andreadellacorte/groove --skill groove-utilities-task-archive -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about groove-utilities-task-archive
How do I install groove-utilities-task-archive in Claude Code?
Run npx skills add andreadellacorte/groove --skill groove-utilities-task-archive -a claude-code, then check ~/.claude/skills/groove-utilities-task-archive/SKILL.md.
What does groove-utilities-task-archive do?
It finds completed and scrapped tasks in the configured backend, shows the planned scope, waits for approval, and reports the archive count when finished.
Which backends can the skill use?
It uses beans archive for beans, the CLI or MCP for linear, and gh issue close for resolved github issues. With tasks.backend: none, it exits without changes.
Source text
SKILL.md · MIT
--- name: groove-utilities-task-archive description: "Archive a completed task in the configured backend." license: MIT allowed-tools: Read Write Edit Glob Grep Bash(git:*) Bash(beans:*) Bash(gh:*) Bash(linear:*) Bash(npx:*) AskUserQuestion metadata: author: andreadellacorte --- # groove-utilities-task-archive ## Outcome All completed and scrapped tasks are archived in the configured backend. The count of archived tasks is reported to the user. ## Acceptance Criteria - All completed/scrapped tasks are moved to archived state in backend - User is shown the scope of what will be archived and confirms before running - Count of archived tasks is reported after completion ## Constraints - Read `tasks.backend` from `.groove/index.md` to determine backend - If `tasks.backend: none`, no-op with friendly message - Always show user what will be archived and ask for confirmation before proceeding - Never run automatically during daily end — only when user explicitly requests - Backend mappings: - `beans`: `beans archive` (archives all completed/scrapped — no single-task option) - `linear`: mark filtered issues as archived via linear CLI or MCP - `github`: close resolved issues via `gh issue close` - Report count of archived tasks after completion
© andreadellacorte · MIT · andreadellacorte/groove