pstack-figure-it-out
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- pstack-figure-it-out
- description
- Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions.
02 资源文件 1
- 许可证LICENSE1.0 KB
03 SKILL.md 正文
Figure it out
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.
Start
Apply Poteto mode, then track the phases that the actual work needs.
Phase A: Frame
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 guide).
- 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".
Share the scope and important tradeoffs briefly, then proceed within existing authorization. Ask only for a material unresolved choice or an unauthorized irreversible action.
Phase B: Design the workflow
Decompose into atomic, independently-landable units. Sequence riskiest-unknown-first. Scaffold and verification come before features (the foundational-thinking guide).
- 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 guide (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 guide).
- Decide what fans out. Parallelize only across seams, and give each worker its own worktree or branch (the separate-before-serializing-shared-state guide). Don't over-fan. Use the current harness's configured model and effort. Keep independent work isolated.
- Write the designed phase list down. That list is what the human reviews.
Then execute the design. Add its steps to the todolist 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.
Phase C: Run the loop
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 guide, 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.
Phase D: Keep the audit trail
Log the run via the show-me-your-work guide. 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.
Phase E: Verify and hand back
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 guide).
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.
04 同仓库更多 Skills
teach
Teach the user a new skill or concept, within this workspace.
stop-overthinking
Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explicitly invokes stop-overthinking.
remind
Rewrite the last response simpler and shorter in plain English, prefixed with a 3-5 sentence TLDR of the conversation so far. Manual-only, invoked as /remind.
read-all-adrs
Read every ADR markdown file in the project's docs/adr/ folder so you have full context on past decisions. Use only when the user explicitly calls it.
pstack-why
Find evidence for design choices and historical constraints through relevant authorized read-only sources; distinguish facts, inferences, and gaps.
pstack-unslop
Cut AI tells from any writing.