Back to Details

figure-it-out

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Figure it out

Figure it out

A skill named in bold or in backticks, or run as 
/<name>
, is the file 
../<name>/SKILL.md
beside this skill's directory, and a principle named without its prefix is 
../principle-<name>/SKILL.md
. Read the file and follow it. Most pstack skills are user-only, so your skill tool cannot load them.
When the task matches no playbook, design one. The deliverable before any code is the workflow itself: a sequence of phases that scales rigor to the task, runs the scientific method, and leaves a decision trail a human can audit after stepping away.
凡是名称以粗体或反引号标出的 skill，或以 
/<name>
形式运行的 skill，都是指本 skill 目录旁的文件 
../<name>/SKILL.md
；名称不带此前缀的 principle 则指 
../principle-<name>/SKILL.md
。读取该文件并遵循其中的说明。大多数 pstack skill 仅供用户使用，因此你的 skill 工具无法加载它们。
当任务不匹配任何 playbook 时，请自行设计一个。在编写任何代码之前，首要交付物应当是工作流本身：一组按照任务规模调整严谨程度、运用科学方法，并留下可供人在离开后回来审计的决策轨迹的阶段。

Start

开始

Open a task list (your harness's task tool, or a checklist file at 
~/.local/state/pstack/checklists/<repo>-<branch>.md
when it has none) whose first item is to read the Principles section of the poteto-mode skill. Then add the phases below as todos.
打开一个任务列表（使用 harness 的任务工具；如果没有，则使用 
~/.local/state/pstack/checklists/<repo>-<branch>.md
形式的 checklist 文件），并将第一项设为读取 poteto-mode skill 的 Principles 部分。然后将下列阶段添加为 todos。

Phase A: Frame

Phase A：界定框架

Ground first, then commit. Don't start the run until you can state:
  • The definition of done as a falsifiable predicate (the prove-it-works principle skill).
  • Scope, quantified: rough units and effort, plus the blockers grounding surfaced.
  • The rigor level, biased high. One-way doors and high blast radius get more. Reversible low-stakes steps get less. Rigor is gates and artifacts, not "try harder".
Present the framing and tradeoffs before committing to a long run. Reversible work proceeds (the never-block-on-the-human principle skill), but a multi-hour run earns one checkpoint.
先基于事实确定方案，再正式开始。在能够明确陈述以下内容之前，不要启动本次 run：
  • 以可证伪的 predicate 表述完成定义（prove-it-works principle skill）。
  • 量化范围：大致工作单元和投入量，以及 grounding 揭示的 blockers。
  • 严谨等级，默认偏向较高水平。不可逆决策（one-way door）和高 blast radius 应获得更高严谨度；可逆且风险较低的步骤则可降低严谨度。严谨度体现为 gates 和 artifacts，而不是“再努力一点”。
在承诺进行长时间 run 之前，先展示问题界定和 tradeoffs。可逆工作应继续推进（never-block-on-the-human principle skill），但持续数小时的 run 至少应设置一个 checkpoint。

Phase B: Design the workflow

Phase B：设计工作流

Decompose into atomic, independently-landable units. Sequence riskiest-unknown-first. Scaffold and verification come before features (the foundational-thinking principle skill).
  • Build the verification harness before the work, with the baseline captured from the pre-change state, so the check reads as "old value vs new value".
  • For one-way-door design decisions, run the architect skill (it runs arena). Skip it for mechanical work whose shape is already concrete. A second arena over a settled design is over-engineering (the laziness-protocol principle skill).
  • Decide what fans out. Parallelize only across seams, and give each worker its own worktree or branch through a 
    t3_thread_launch
    thread with a worktree 
    workspaceStrategy
    (the separate-before-serializing-shared-state principle skill). Commit the harness and any preparation first and use that commit as 
    baseRef
    . Don't over-fan. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the poteto-mode skill.
  • Write the designed phase list down. That list is what the human reviews.
Then execute the design. Add its steps to the task list as concrete items between the Phase C and Phase D entries. Run each under the Phase C loop discipline, and weave the Phase D log through them, a row as each step lands, rather than saving the whole trail for the end.
将任务拆分为原子化且可独立落地的单元。排序时先处理风险最高且未知最多的部分。先搭建 scaffold 和 verification，再实现 features（foundational-thinking principle skill）。
  • 在工作开始前构建 verification harness，并从变更前状态捕获 baseline，让 check 呈现为“old value vs new value”。
  • 对于 one-way-door 设计决策，运行 architect skill（它会运行 arena）。如果机械性工作的形态已经明确，则可以跳过。对已经定案的设计再运行一次 arena 属于过度工程化（laziness-protocol principle skill）。
  • 决定哪些工作可以 fan out。只在 seams 之间并行，并通过使用 worktree 
    workspaceStrategy
    的 
    t3_thread_launch
    thread，为每个 worker 提供独立的 worktree 或 branch（separate-before-serializing-shared-state principle skill）。先 commit harness 和所有准备工作，并将该 commit 用作 
    baseRef
    。不要过度 fan out。根据 poteto-mode skill 的 Subagents 部分，为每个 subagent 选择适合任务的 reasoning level，以及 fast 或 standard speed。
  • 将设计出的阶段列表写下来。这份列表就是供人审阅的对象。
接着执行设计。将这些步骤作为具体事项添加到任务列表中 Phase C 与 Phase D 两个条目之间。每个步骤都遵循 Phase C 的循环纪律执行，并在过程中贯穿 Phase D 日志；每一步落地就新增一行，而不是直到最后才保存完整轨迹。

Phase C: Run the loop

Phase C：运行循环

Each unit is an experiment. State the hypothesis, make the smallest change, measure against the predicate on the real artifact, keep it if it advanced, revert it if it didn't. Apply the sequence-verifiable-units principle skill, verifying each unit before starting the next instead of batching checks at the end.
  • Verify by inspecting the artifact, never a self-report. When something passes too easily, suspect the observation method before the system.
  • Pair delegated work with a judge. If a worker games the gate, reset and harden the contract. If the gate itself is wrong, fix the gate in its own change rather than routing around it.
  • A verdict is VERIFIED, NOT VERIFIED, or INCONCLUSIVE. Inconclusive is not a pass. Don't hide a negative.
每个单元都是一次 experiment。先陈述 hypothesis，再做最小改动，在真实 artifact 上依据 predicate 进行测量；如果有进展就保留，否则回退。应用 sequence-verifiable-units principle skill，在开始下一个单元前验证当前单元，而不是将检查批量留到最后。
  • 通过检查 artifact 进行验证，绝不能依赖自我报告。如果某项内容过于轻易地通过，应先怀疑 observation method，而不是 system。
  • 为每项 delegated work 配备一个 judge。如果 worker 在钻 gate 的空子，应重置并强化 contract。如果 gate 本身有问题，则通过自身的变更修复 gate，而不是绕过它。
  • verdict 只能是 VERIFIED、NOT VERIFIED 或 INCONCLUSIVE。INCONCLUSIVE 不算通过。不要隐瞒负面结果。

Phase D: Keep the audit trail

Phase D：保留审计轨迹

Log the run via the show-me-your-work skill. figure-it-out's work is usually ambitious enough to commit the trail so the reviewer can read it in the PR. The trail plus the diff is what lets the human come back and trust the work.
通过 show-me-your-work skill 记录本次 run。figure-it-out 的工作通常足够复杂，值得将 trail commit 到版本库中，让 reviewer 能在 PR 中阅读。trail 与 diff 结合起来，才能让人回来后信任工作成果。

Phase E: Verify and hand back

Phase E：验证并交付

Check the whole against the Phase A predicate on the real product, not just the harness. Encode any recurring correction as a gate, a lint rule, a check, or a script (the encode-lessons-in-structure principle skill).
Reply: the playbook you designed, the rigor level and why, the decision-trail path, what's verified against the predicate, and what's still open.
在真实产品上依据 Phase A 的 predicate 检查整体结果，而不只是检查 harness。将任何反复出现的纠正措施编码为 gate、lint rule、check 或 script（encode-lessons-in-structure principle skill）。
**回复：**你设计的 playbook、严谨等级及其理由、decision trail 的路径、已依据 predicate 验证的内容，以及仍未解决的事项。