Writing Plans

Use when you have a spec or requirements for a multi-step task, before touching code

Security Scan

The skill's requests and runtime instructions are consistent with its stated purpose (producing implementation plans); it requires no credentials or installs and is instruction-only.

Purpose & Capability

Name/description (produce step-by-step implementation plans) align with the SKILL.md: it only asks the agent to create plan documents, list file paths, commands, and test steps. There are no unrelated environment variables, binaries, or install steps requested.

Instruction Scope

Instructions stay within planning: create plan files, enumerate exact file paths, provide code snippets, and include git/pytest commands and expected outputs. This is appropriate for an implementation-planning skill, but the SKILL.md explicitly requires embedding complete code and exact commands and references external sub-skills (superpowers:executing-plans, superpowers:subagent-driven-development). That increases the potential for subsequent automated execution (by other skills) — the plan itself does not perform I/O or network activity.

Install Mechanism

No install spec or downloaded code; instruction-only skills write nothing to disk by themselves. Lowest risk for install mechanism.

Credentials

Requires no environment variables, credentials, or config paths. Nothing disproportionate requested relative to the stated purpose.

Persistence & Privilege

always:false and default autonomous invocation are set (normal). The main consideration is that the skill instructs use of other sub-skills that may execute plans, run tests, and commit code — evaluate those sub-skills' privileges before enabling autonomous invocation. The skill itself does not request persistent or system-wide privileges.

Assessment

This skill is internally coherent and does not request secrets or installs. Before enabling it for autonomous use, verify the provenance and permissions of any referenced sub-skills (superpowers:executing-plans, superpowers:subagent-driven-development) because they are the components that would actually run commands or modify your repository. Prefer running it manually or in a dedicated worktree at first, review saved plan files (docs/plans/...) for accidental inclusion of secrets or sensitive file paths, and confirm any automated executors have limited, audited access to only the intended repository/worktree.

Overview

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

Bite-Sized Task Granularity

Each step is one action (2-5 minutes):

• "Write the failing test" - step
• "Run it to make sure it fails" - step
• "Implement the minimal code to make the test pass" - step
• "Run the tests and make sure they pass" - step
• "Commit" - step

Plan Document Header

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 Structure

### 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

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

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

## Execution Handoff

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:**
- **REQUIRED SUB-SKILL:** Use superpowers:subagent-driven-development
- Stay in this session
- Fresh subagent per task + code review

**If Parallel Session chosen:**
- Guide them to open new session in worktree
- **REQUIRED SUB-SKILL:** New session uses superpowers:executing-plans