Writing Plans

与 bensz-collect-bugs 的协作约定

• 因本 skill 设计缺陷导致的 bug，先用 bensz-collect-bugs 规范记录到 ~/.bensz-skills/bugs/，不要直接修改用户本地已安装的 skill 源码；若有 workaround，先记 bug，再继续完成任务。
• 只有用户明确要求“report bensz skills bugs”等公开上报时，才用本地 gh 上传新增 bug 到 huangwb8/bensz-bugs；不要 pull / clone 整个仓库。

Overview

Write implementation plans sized to the task risk. Small, localized work should get a short closed-loop plan; complex or high-risk work should get the full task tree with explicit tests, affected files, dependencies, and rollback/verification notes. 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

Risk-Scaled Plan Depth

• Low risk / single-file / docs-only: produce a compact plan with goal, minimal change scope, success criteria, verification command, and 2-4 execution steps.
• Medium risk / one specialty: include affected files, one focused test path, implementation steps, and review checklist.
• High risk / cross-module / security / data changes: include assumptions, non-goals, dependency order, rollback notes, required agents, success criteria, and a verification matrix.

Do not inflate a small task into a large plan just because the planning skill is active.

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]

**Minimal Change Scope:** [Allowed paths and explicit avoid list]

**Success Criteria:** [Observable checks that prove completion]

**Verification Plan:** [Exact commands or manual checks]

---

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"

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