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