skills/curated/writing-plans/SKILL.md
Use when you have a spec or requirements for a multi-step task, before touching code
npx skillsauth add jwa91/agentskills writing-plansInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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 is one action (2-5 minutes):
Every plan MUST start with this header:
# [Feature Name] Implementation Plan
> **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 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"
```
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
2. Parallel Session (separate) - Open new session with executing-plans, batch execution with checkpoints
Which approach?"
If Subagent-Driven chosen:
If Parallel Session chosen:
data-ai
Release the current project to the personal Homebrew tap from repo-local release config. Use when the user says "release", "ship", "cut a version", "publish", "make a new tag", or asks how to make a new version available via jwa91/tap.
tools
Use the `jwa-harden` CLI for secret-safe command execution, env-template discovery, and signing/notarization preflight checks. Trigger when a command needs secrets, when `.env.template` or 1Password references are involved, or before signed release flows.
documentation
Modify or extend the `jwa-tobrew` scaffolding system — the templates that `init` writes into target projects. Trigger when the user says "add a new scaffold kind", "change what init writes", "update the templates", or asks how the embedded templates are wired.
development
Detect and fix drift between a project and the conventions encoded in `jwa-tobrew`, prek, and the tap ADRs. Trigger when the user says "align", "any drift", "verify conventions", or asks why a particular file/symlink/script is required.