Loom task start
Skill DanielC000/loom/packages/daemon/assets/skills/loom-task-start
Use when starting a new task, feature, bugfix, or refactor in a Loom project — "let's start", "new task", "working on", "implement", "begin". Ensures a board task exists with a clear scope and a sharp definition of done, then loads context before any code changes.From its SKILL.md
npx -y skills add DanielC000/loom --skill loom-task-startAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 5 commands, including `git log --oneline -15` and 4 more.
SKILL.md
1.8 KB, 409 tokens by cl100k_base, as published. Nobody here has run it
Task Start (Loom)
Make the work trackable on the board before diving in. The board is the source of truth — one task = one focused, independently-mergeable change.
Steps
- Find or create the task —
tasks_list(theloom-tasksMCP); if none matches,tasks_createwith a clear, specific title in Conventional-Commits form (type(scope): summary— lowercase type likefeat/fix/refactor, imperative summary), drawing the scope from the project'sCLAUDE.md"Commit scopes". - Scope it. Put the scope and a sharp definition of done in the task body (
tasks_updatebody). The DoD states what proves it works — a command that exits clean, a manual repro, a regression check. A task without a DoD isn't ready to work. If an open decision blocks pinning the DoD, ask the human viaquestion_ask(the Requests inbox) rather than guessing. Keep it to one logical change; if it's really several, split it. - Move it — set the task to the
activecolumn (the in-progress ROLE) viatasks_updatecolumnKey. First, skip any card flaggedheld(an owner brake) ordeferred(the manager hasn't sequenced it) — don't begin work on those. - Load context before changing anything —
git log --oneline -15, readCLAUDE.md, and read the relevant code/notes so your change matches what's there. Reuse existing shapes over inventing new ones.
Then implement: keep the change small and matched to the surrounding code, meet the DoD, and build/ verify before reporting it done.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.