writing-plans – skill Viết lách & Nội dung cho agent AI

Writing Plans

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: Use the project's existing planning location and workflow. A dedicated worktree is useful when code isolation is needed, but planning does not require an unavailable brainstorming skill or authorize implementation.

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

> **Execution:** Follow this plan task-by-task within the user-authorized scope. If the installed environment provides an executing-plans skill, read it before use; this catalog entry does not bundle that dependency.

**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**

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"

The outer Task Structure template should be copied as Markdown with its inner code blocks intact. Commands and expected outputs are planned checks, not evidence that those checks ran; verify file paths and tool availability against the actual repository. Scale tests and commits to meaningful behavior and the repository policy rather than adding a test or commit mechanically for every edit.

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:

• Use an installed subagent-driven-development procedure if available; otherwise describe the available execution workflow without claiming this dependency is bundled.
• Stay in this session
• Fresh subagent per task + code review

If Parallel Session chosen:

• Guide them to open new session in worktree
• Use an installed executing-plans procedure if available; otherwise carry the saved plan and project instructions into the new session.

When to Use

This skill is applicable to execute the workflow or actions described in the overview.

Limitations

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.