Executing Plans
Overview
Load plan, review critically, execute tasks in batches, report for review between batches.
Core principle: Batch execution with checkpoints for architect review.
Announce at start: "I'm using the executing-plans skill to implement this plan."
The Process
Step 1: Load and Review Plan
- 1. Read plan file
- Review critically - identify any questions or concerns about the plan
- If concerns: Raise them with your human partner before starting
- If no concerns: Create TodoWrite and proceed
Step 2: Execute Batch
Default: First 3 tasks
For each task:
- 1. Mark as in_progress
- Follow each step exactly (plan has bite-sized steps)
- Run verifications as specified
- Mark as completed
Step 3: Report
When batch complete:
- - Show what was implemented
- Show verification output
- Say: "Ready for feedback."
Step 4: Continue
Based on feedback:
- - Apply changes if needed
- Execute next batch
- Repeat until complete
Step 5: Complete Development
After all tasks complete and verified:
- - Announce: "I'm using the finishing-a-development-branch skill to complete this work."
- REQUIRED SUB-SKILL: Use superpowers:finishing-a-development-branch
- Follow that skill to verify tests, present options, execute choice
When to Stop and Ask for Help
STOP executing immediately when:
- - Hit a blocker mid-batch (missing dependency, test fails, instruction unclear)
- Plan has critical gaps preventing starting
- You don't understand an instruction
- Verification fails repeatedly
Ask for clarification rather than guessing.
When to Revisit Earlier Steps
Return to Review (Step 1) when:
- - Partner updates the plan based on your feedback
- Fundamental approach needs rethinking
Don't force through blockers - stop and ask.
Remember
- - Review plan critically first
- Follow plan steps exactly
- Don't skip verifications
- Reference skills when plan says to
- Between batches: just report and wait
- Stop when blocked, don't guess
- Never start implementation on main/master branch without explicit user consent
Integration
Required workflow skills:
- - superpowers:using-git-worktrees - REQUIRED: Set up isolated workspace before starting
- superpowers:writing-plans - Creates the plan this skill executes
- superpowers:finishing-a-development-branch - Complete development after all tasks
Superplanner Memory Integration (Unified Extension)
CRITICAL THEMATIC RULE: You are working inside the
superpower-with-files unified framework.
Workflow Standardization
- 1. Skill Announcement: Every time you start using this skill, you MUST first announce:
🚀 **SUPERPOWER ACTIVE:** spf-exec-plan
- 2. Context Independence: Work in any project root as requested by the user. No dedicated worktree required.
STRICT EXECUTION ONLY
- 1. Execution Only: Your sole responsibility is to carry out the steps defined in the
active_tdd_plan.md. - No Plan Modification: You MUST NOT modify the plan itself.
- Optional Steps: You MAY skip any step marked as
(optional) if the state is clear.
PARALLEL EXECUTION PROTOCOL
- 4. Parallel Spawning: If Task A and Task B are marked as
Parallel with each other:
- You MUST attempt to spawn a
sub-agent (if the platform provides a
subagent or
browser_subagent tool) to handle one of the tasks.
- If no sub-agent tool is available, you MUST execute them sequentially but acknowledge the parallel potential in
progress.md.
- Before spawning, ensure common dependencies (Tasks they both depend on) are 100% complete.
Pre-Flight Context Checklist
Before you execute any code, you MUST load your context.
- 1. Read Core Files: Read
task_plan.md, findings.md, and active_tdd_plan.md. - Guide-Aware Loading: Before starting Task N, check if
.superpower-with-files/guides/task-N.md exists. If it does, YOU MUST READ IT. It contains the detailed "how-to" for the task. - Sync Progress: Check
progress.md to resume correctly.
Execution Checkpoint Rule
When you finish a batch of 3 tasks,
before you pause to say "Ready for feedback", you MUST:
- 1. Context Hygiene:
- Summarize the batch into a single concise paragraph in
progress.md.
- Clear any temporary discovery findings from
findings.md that are no longer relevant.
- For your next prompt, keep only the relevant
task_plan.md phase and the next 3 tasks from
active_tdd_plan.md in your immediate thought block.
- 2. Session Handoff:
- If you are stopping or pausing for more than a few minutes, CREATE or UPDATE:
.superpower-with-files/handoff.md
- Include: Latest timestamp, Completed tasks, Current task status, Any blockers, and "Next Action" details.
- 3. Implicit Stop: Stop and prompt the user:
> "Batch complete. Progress saved and context compacted. Session handoff updated at
handoff.md. Ready to continue?"
Automated Timestamping
- - Every time you modify a memory file (
task_plan.md, active_tdd_plan.md, findings.md, progress.md), you MUST append a horizontal rule and a timestamp at the very bottom:
---
INLINECODE24
执行计划
概述
加载计划,严格审查,分批执行任务,批次间提交审查报告。
核心原则: 分批执行,设置检查点供架构师审查。
开始时声明: 我正在使用执行计划技能来实现此计划。
流程
第一步:加载并审查计划
- 1. 读取计划文件
- 严格审查——识别计划中存在的任何问题或疑虑
- 如有疑虑:在开始前向人类搭档提出
- 如无疑虑:创建待办事项清单并继续
第二步:执行批次
默认:前3个任务
针对每个任务:
- 1. 标记为进行中
- 精确遵循每个步骤(计划已拆分为小步骤)
- 按指定方式运行验证
- 标记为已完成
第三步:报告
批次完成后:
- - 展示已实现的内容
- 展示验证输出
- 说明:准备接收反馈。
第四步:继续
根据反馈:
第五步:完成开发
所有任务完成并验证后:
- - 声明:我正在使用完成开发分支技能来完成此工作。
- 必需子技能: 使用 superpowers:finishing-a-development-branch
- 遵循该技能验证测试、呈现选项、执行选择
何时停止并寻求帮助
遇到以下情况立即停止执行:
- - 批次中途遇到阻塞(缺少依赖、测试失败、指令不清晰)
- 计划存在严重缺口导致无法启动
- 不理解某个指令
- 验证反复失败
寻求澄清而非猜测。
何时重新审视前期步骤
遇到以下情况返回审查(第一步):
- - 搭档根据你的反馈更新了计划
- 基本方法需要重新思考
不要强行突破阻塞——停下来询问。
记住
- - 首先严格审查计划
- 精确遵循计划步骤
- 不要跳过验证
- 计划要求时引用技能
- 批次之间:只需报告并等待
- 遇到阻塞时停止,不要猜测
- 未经用户明确同意,切勿在主分支上开始实施
集成
必需的工作流技能:
- - superpowers:using-git-worktrees - 必需:开始前设置隔离工作空间
- superpowers:writing-plans - 创建本技能执行的计划
- superpowers:finishing-a-development-branch - 完成所有任务后的开发收尾
超级规划器内存集成(统一扩展)
关键主题规则: 你在 superpower-with-files 统一框架内工作。
工作流标准化
- 1. 技能声明: 每次开始使用此技能时,必须首先声明:
🚀
超级能力激活: spf-exec-plan
- 2. 上下文独立性: 根据用户要求在任意项目根目录下工作。无需专用工作树。
严格仅执行
- 1. 仅执行: 你的唯一职责是执行 activetddplan.md 中定义的步骤。
- 不得修改计划: 你不得修改计划本身。
- 可选步骤: 如果状态明确,你可以跳过任何标记为 (可选) 的步骤。
并行执行协议
- 4. 并行派生: 如果任务A和任务B标记为彼此与...并行:
- 你必须尝试派生一个
子代理(如果平台提供 subagent 或 browser_subagent 工具)来处理其中一个任务。
- 如果没有可用的子代理工具,你必须顺序执行它们,但在 progress.md 中确认并行潜力。
- 在派生之前,确保公共依赖项(它们都依赖的任务)100%完成。
飞行前上下文检查清单
在执行任何代码之前,你必须加载上下文。
- 1. 读取核心文件: 读取 taskplan.md、findings.md 和 activetdd_plan.md。
- 指南感知加载: 在开始任务N之前,检查 .superpower-with-files/guides/task-N.md 是否存在。如果存在,你必须读取它。它包含该任务的详细操作方法。
- 同步进度: 检查 progress.md 以正确恢复。
执行检查点规则
当你完成3个任务的批次后,在暂停并说准备接收反馈之前,你必须:
- 1. 上下文清理:
- 将批次总结为一个简洁段落写入 progress.md。
- 从 findings.md 中清除不再相关的临时发现结果。
- 对于你的下一个提示,在即时思考块中仅保留相关的 task
plan.md 阶段和来自 activetdd_plan.md 的下3个任务。
- 2. 会话交接:
- 如果你要停止或暂停超过几分钟,创建或更新:
.superpower-with-files/handoff.md
- 包括:最新时间戳、已完成任务、当前任务状态、任何阻塞项以及下一步行动详情。
- 3. 隐式停止: 停止并提示用户:
> 批次完成。进度已保存,上下文已压缩。会话交接已在 handoff.md 更新。准备继续?
自动时间戳
- - 每次修改内存文件(taskplan.md、activetdd_plan.md、findings.md、progress.md)时,必须在最底部追加一条水平线和时间戳:
最后更新:YYYY-MM-DD HH:MM UTC