start-task
SkillProductivityResume execution of an approved plan from the next unchecked subtask, following the gated Task Execution Workflow in AGENTS.md.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the start-task skill
What this skill tells your AI
The instructions your AI receives, as published by maotoumao/cebian in .agents/skills/start-task/SKILL.md and read by ahel’s review.
Resume work on an in-progress plan. Follow the Task Execution Workflow defined in AGENTS.md strictly — one subtask, code review, test instructions, then stop.
Steps
-
Locate the plan
- If the user provided a path, use that file.
- Otherwise list docs/plans/ and pick the most recently modified
*.mdplan that is not markedPROPOSAL. Confirm the choice with the user in one short line before proceeding.
-
Find the next subtask
- Read the plan and locate the first
## Task N:section that still contains unchecked- [ ]steps. - If every task is fully checked, report "All tasks complete" and stop. Do not invent new work.
- Read the plan and locate the first
-
Sync the TODO list
- Use your harness's todo/task list to mirror the plan's tasks. Mark already-completed tasks as
completed, the located next task asin-progress, and remaining tasks asnot-started.
- Use your harness's todo/task list to mirror the plan's tasks. Mark already-completed tasks as
-
Execute exactly that one subtask
- Implement only the steps inside that single
## Task N:section. - Do not touch files belonging to later tasks. Do not look ahead.
- When the implementation is done, update the plan file to check off (
- [x]) the steps you completed.
- Implement only the steps inside that single
-
Code review
- Run the repository's
code-reviewworkflow in the current harness's dedicated read-only reviewer. Pass it the files changed in this task and the plan section as context, then address any actionable issues before continuing.
- Run the repository's
-
Hand off to the user
- Provide concrete manual testing instructions: what to run (
pnpm devis usually already running in thedevterminal), what to open, what to click, expected console output, expected UI state. - Then stop. Do not start the next task. Do not mark the TODO
completedyet.
- Provide concrete manual testing instructions: what to run (
-
Wait for explicit approval
- Only after the user replies with explicit approval (e.g., "approved", "next", "looks good", "passed") should the TODO be marked
completed. Acknowledgements and silence are not approval.
- Only after the user replies with explicit approval (e.g., "approved", "next", "looks good", "passed") should the TODO be marked
If the plan turns out to be wrong or incomplete during step 4, stop and trigger the Plan-First re-approval flow instead of pushing forward.
Signals
- GitHub stars
- 146
- Forks
- 27
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
start-task-maotoumao- Source
- github.com/maotoumao/cebian