maotoumao/Cebian / .agents/skills/start-task
start-task
UnverifiedResume execution of an approved plan from the next unchecked subtask, following the gated Task Execution Workflow in AGENTS.md.
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.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |