// Use when you have a spec or requirements for a multi-step task, before touching code
Use when adding new dependencies, deciding whether to update packages, running security audits on dependencies, evaluating library alternatives, or encountering outdated or vulnerable packages
Use when starting any conversation — establishes how to find and use skills, requiring skill check before ANY response including clarifying questions
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when a task requires interacting with a web browser — testing UI flows, verifying web app behavior, clicking through screens, reading live web content, or automating browser workflows in Google Antigravity
Use when executing implementation plans with independent tasks in the current session
| name | writing-plans |
| description | Use when you have a spec or requirements for a multi-step task, before touching code |
Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Context: This should be run in a dedicated worktree (created by brainstorming skill).
Save plans to: docs/plans/YYYY-MM-DD-<feature-name>.md
Each step produces exactly one artifact: a written test, a passing test run output, a code file, a commit. If a step produces two artifacts, split it.
Examples:
For files that don't exist yet, use paths based on the project's existing naming convention. If no convention exists, document the path convention you're using at the top of the plan.
Every plan MUST start with this header:
# [Feature Name] Implementation Plan
> **For Antigravity:** REQUIRED SUB-SKILL: Load 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 N: [Component Name]
**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
```
**Step 2: Run test to verify it fails**
Run: `pytest tests/path/test.py::test_name -v`
Expected: FAIL with "function not defined"
**Step 3: Write minimal implementation**
```python
def function(input):
return expected
```
**Step 4: Run test to verify it passes**
Run: `pytest tests/path/test.py::test_name -v`
Expected: PASS
**Step 5: Commit**
```bash
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
```
Before handing the plan to execution: read it from the perspective of an engineer who has never seen this codebase. Does every task have enough context to start without asking questions? If not, add it.
Checklist:
After saving the plan, offer execution choice:
"Plan complete and 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. REQUIRED: Switch Antigravity to Fast Mode for this implementation phase.
2. Parallel Session (separate) - Open new session with executing-plans, batch execution with checkpoints
Which approach?"
If Subagent-Driven chosen:
If Parallel Session chosen: