Execute repo work one task at a time using a strict plan → execute → iterate loop tracked in .copilot-todo.yaml.
Use this skill to drive work through a **single authoritative YAML todo file**: `.copilot-todo.yaml`.
```bash
cp .github/skills/task-orchestration/template/plan.md.template plan.md
python3 .github/skills/task-orchestration/scripts/task_orchestrator.py \
--plan-md plan.md \
--plan-mode regen \
init
```
```bash
cp .github/skills/task-orchestration/template/copilot-todo.yaml.template .copilot-todo.yaml
python3 .github/skills/task-orchestration/scripts/task_orchestrator.py init
```
**Template locations:**
Repeat until no runnable tasks remain:
1) Sync / migrate state
```bash
python3 .github/skills/task-orchestration/scripts/task_orchestrator.py init
```
- If an item starts with an explicit ID prefix like `A1. ...` or `T-001: ...`, that ID is used.
- Otherwise a stable-ish `P-XXXXXXXX` ID is generated from the text.
```bash
python3 .github/skills/task-orchestration/scripts/task_orchestrator.py \
--plan-md plan.md \
--plan-mode regen \
init
```
2) Start next task
```bash
python3 .github/skills/task-orchestration/scripts/task_orchestrator.py next
```
3) Plan (short bullets, only for the chosen task)
4) Execute (minimal diff; run smallest relevant existing build/test)
5) Update status
```bash
python3 .github/skills/task-orchestration/scripts/task_orchestrator.py update <ID> completed --note "..."
python3 .github/skills/task-orchestration/scripts/task_orchestrator.py update <ID> blocked --note "..."
```
5b) Commit (required when using `ralph_loop.py --require-commit`)
```bash
git add -A
git commit -m "<ID>: <short summary>"
```
6) Iterate / expand
If you discover missing work, **add follow-up tasks** (don’t silently expand scope):
```bash
python3 .github/skills/task-orchestration/scripts/task_orchestrator.py add "Title" --deps <ID1,ID2> --priority Medium --goal "..."
```
To run **one fresh Copilot run per task** (uses `copilot -p`, consuming Copilot requests accordingly):
```bash
python3 .github/skills/task-orchestration/scripts/ralph_loop.py \
--non-interactive \
--max-steps 10
python3 .github/skills/task-orchestration/scripts/ralph_loop.py \
--non-interactive \
--plan-md plan.md \
--plan-mode regen \
--max-steps 10
```
Notes:
Leave a review
No reviews yet. Be the first to review this skill!
# Download SKILL.md from killerskills.ai/api/skills/task-orchestration/raw