# Source the helper functions
source skills/lib/beads-helper.sh

# 1. Create the implementation plan epic
epic_id=$(beads_create_plan_epic \
    "Feature Name" \
    "One sentence describing what this builds" \
    "2-3 sentences about approach" \
    "Key technologies/libraries" \
    1)  # priority: 1=high

echo "Created epic: $epic_id"

# 2. Create each task under the epic
task1_id=$(beads_create_task "$epic_id" \
    "Task 1: Component Name" \
    "$(cat <<'EOF'
**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py`

**Step 1: Write the failing test**

```python
def test_specific_behavior():
    result = function(input)
    assert result == expected

### Method 2: Scripted (For Complex Plans with Many Tasks)

Use the helper script for plans with many tasks:

```bash
# 1. Create a tasks.json file describing all tasks
cat > tasks.json <<'EOF'
{
  "tasks": [
    {
      "title": "Task 1: Component Name",
      "description": "Full task description with files and steps...",
      "priority": 1,
      "dependencies": []
    },
    {
      "title": "Task 2: Another Component",
      "description": "Full task description...",
      "priority": 2,
      "dependencies": ["Task 1: Component Name"]
    }
  ]
}
EOF

# 2. Run the script
skills/writing-plans/scripts/create-plan-in-beads.sh \
    "Feature Name" \
    "One sentence goal" \
    "2-3 sentences architecture" \
    "Tech stack" \
    tasks.json

# Output will show epic ID and all task IDs

# [Feature Name] Implementation Plan

**Beads Epic:** bd-abc123  
**View:** `bd show bd-abc123`  
**List Tasks:** `bd list --parent bd-abc123`

> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.

**Goal:** [One sentence describing what this builds]

**Architecture:** [2-3 sentences about approach]

**Tech Stack:** [Key technologies/libraries]

---

### Task 1: Component Name

**Beads ID:** bd-xyz456

**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`

[... full task details ...]

### Task N: [Component Name]

**Beads ID:** bd-xyz123

**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py`

**Step 1: Write the failing test**

```python
def test_specific_behavior():
    result = function(input)
    assert result == expected

def function(input):
    return expected

git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"

## Remember
- Exact file paths always
- Complete code in plan (not "add validation")
- Exact commands with expected output
- Reference relevant skills with @ syntax
- DRY, YAGNI, TDD, frequent commits
- Each task has a beads ID for tracking
- Markdown is for documentation, beads is for execution

## Beads Integration

This skill creates implementation plan epics in beads with child tasks, plus markdown reference files.

**Workflow:**
1. Plan the task breakdown and dependencies
2. Create beads epic with tasks (interactive or scripted method)
3. Create markdown reference file linking to epic and tasks
4. Commit both to git (beads auto-saves in `.beads/`, markdown in `docs/plans/`)

**Beads Commands:**
- View plan: `bd show <epic-id>`
- List tasks: `bd list --parent <epic-id>`
- List ready tasks: `bd ready --parent <epic-id>` (no dependencies blocking)
- Update task: `bd update <task-id> --status in_progress`
- Show task: `bd show <task-id>`

**Markdown Reference:**
- Stored in `docs/plans/YYYY-MM-DD-<topic>.md`
- Contains epic and task links at top
- Includes full task descriptions for easy reading
- Human-readable, searchable, diff-friendly
- Auto-updated by executing-plans skill as work progresses

## Execution Handoff

After creating the plan in beads and saving the markdown reference, offer execution choice:

**"Plan complete! Created epic `<epic-id>` with N tasks. Markdown saved to `docs/plans/<filename>.md`. Two execution options:**

**1. Subagent-Driven (this session)** - I dispatch fresh subagent per task, review between tasks, fast iteration

**2. Parallel Session (separate)** - Open new session with executing-plans, batch execution with checkpoints

**Which approach?"**

**If Subagent-Driven chosen:**
- **REQUIRED SUB-SKILL:** Use superpowers:subagent-driven-development
- Stay in this session
- Fresh subagent per task + code review
- Pass epic ID to subagent system

**If Parallel Session chosen:**
- Guide them to open new session in worktree
- **REQUIRED SUB-SKILL:** New session uses superpowers:executing-plans
- Pass epic ID for task loading