Writing plans skill for AI agents

writing-plans is a skill from the Summer skill library: a guide your AI agent reads when the task matches, so it builds the good version on the first try. Turn a spec or requirements for a multi-step task into a written implementation plan before touching code.


Status	Stable
Domains	Agent workflow, Meta
Version	`1.0.3`
Engine version	`>=4.6`
Recommended set	No, installed by `--all` or by name

When your agent uses it

You have a spec or requirements for a multi-step task, before touching code
A task spans several files or steps and needs an ordered, reviewable plan before implementation starts

Install

summer setup installs every skill for your agent. To add only this one:

npx -y summer-engine@latest skills install writing-plans --agent claude-code

Swap claude-code for your agent, such as codex or cursor. See Skills for every option.

The skill

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: If the work needs isolation from the current checkout, create a git worktree for it before execution starts. Save plans to: .summer/plans/YYYY-MM-DD-<feature-name>.md in the game project

(User preferences for plan location override this default)

Scope Check

If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn’t, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.

File Structure

Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.

Design units with clear boundaries and well-defined interfaces. Each file should have one clear responsibility.
You reason best about code you can hold in context at once, and your edits are more reliable when files are focused. Prefer smaller, focused files over large ones that do too much.
Files that change together should live together. Split by responsibility, not by technical layer.
In existing codebases, follow established patterns. If the codebase uses large files, don’t unilaterally restructure - but if a file you’re modifying has grown unwieldy, including a split in the plan is reasonable.

This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.

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 agentic workers:** implement this plan task-by-task, in order, checking off each step as it lands. Steps use checkbox (`- [ ]`) syntax for tracking. Dispatch a fresh subagent per task where the tasks are independent (see dispatching-parallel-agents), otherwise execute inline with a review checkpoint after each 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.gd`
- Modify: `exact/path/to/existing.gd:123-145`
- Test: `tests/exact/path/to/test_file.gd`

- [ ] **Step 1: Write the failing test**

```gdscript
# tests/unit/test_health.gd (GUT or gdUnit4 style)
func test_damage_reduces_health():
    var health := Health.new()
    health.apply_damage(30)
    assert_eq(health.current, 70)
```

- [ ] **Step 2: Run test to verify it fails**

Run: the project's test command (for GUT: `<engine> --headless -s addons/gut/gut_cmdln.gd -gtest=res://tests/unit/test_health.gd`)
Expected: FAIL because `apply_damage` does not exist yet

- [ ] **Step 3: Write minimal implementation**

```gdscript
# scripts/health.gd
class_name Health
var current := 100
func apply_damage(amount: int) -> void:
    current -= amount
```

- [ ] **Step 4: Run test to verify it passes**

Run: the same test command
Expected: PASS

- [ ] **Step 5: Commit**

```bash
git add tests/unit/test_health.gd scripts/health.gd
git commit -m "feat: add specific feature"
```

No Placeholders

Every step must contain the actual content an engineer needs. These are plan failures — never write them:

“TBD”, “TODO”, “implement later”, “fill in details”
“Add appropriate error handling” / “add validation” / “handle edge cases”
“Write tests for the above” (without actual test code)
“Similar to Task N” (repeat the code — the engineer may be reading tasks out of order)
Steps that describe what to do without showing how (code blocks required for code steps)
References to types, functions, or methods not defined in any task

Remember

Exact file paths always
Complete code in every step — if a step changes code, show the code
Exact commands with expected output
DRY, YAGNI, TDD, frequent commits

Self-Review

After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch. 1. Spec coverage: Skim each section/requirement in the spec. Can you point to a task that implements it? List any gaps. 2. Placeholder scan: Search your plan for red flags — any of the patterns from the “No Placeholders” section above. Fix them. 3. Type consistency: Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called clearLayers() in Task 3 but clearFullLayers() in Task 7 is a bug. If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.

Execution Handoff

After saving the plan, offer execution choice: “Plan complete and saved to .summer/plans/<filename>.md. Two execution options: 1. Subagent-Driven (recommended) - I dispatch a fresh subagent per task, review between tasks, fast iteration 2. Inline Execution - Execute tasks in this session, batched with checkpoints Which approach?” If Subagent-Driven chosen:

One fresh subagent per task, each given the task’s full text and nothing else from this session’s history. See dispatching-parallel-agents for prompt structure and when parallelism is safe.
Two-stage review: read the subagent’s summary, then verify the diff yourself before starting the next task.

If Inline Execution chosen:

Execute tasks in order in this session, stopping at a checkpoint after each task for review.
Never batch past a failing step. Fix it, verify it, then continue.

Files in this skill

plan-document-reviewer-prompt.md

Source: library/skills/writing-plans/SKILL.md, rendered from summer-engine@4.3.0 on npm.

​When your agent uses it

​Install

​The skill

​Overview

​Scope Check

​File Structure

​Bite-Sized Task Granularity

​Plan Document Header

​Task Structure

​No Placeholders

​Remember

​Self-Review

​Execution Handoff

​Files in this skill