figure-it-out

Designs an auditable multi-phase playbook for large migrations and ambitious changes.

3|2|Updated Aug 28, 2026
One-click install
npx skills add https://github.com/adjohn/pstack --skill figure-it-out-adjohn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: figure-it-out
Source: https://github.com/adjohn/pstack/tree/main/skills/figure-it-out
Command: npx skills add https://github.com/adjohn/pstack --skill figure-it-out-adjohn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When a task matches no existing playbook—a large migration across many call sites, an ambitious multi-part change, or work a human reviews after stepping away—ad-hoc execution produces unverifiable results and no decision trail. This Skill designs a rigorous, auditable workflow before any code is written. ## Core Features & Use Cases - Playbook Design: Frames the task with a falsifiable definition of done, quantified scope, and a rigor level scaled to blast radius, then decomposes work into atomic, independently-landable units. - Hypothesis Loop: Runs each unit as an experiment—state a hypothesis, make the smallest change, measure against the predicate on the real artifact, and keep or revert based on evidence. - Audit Trail: Logs every decision and unit in a canonical TSV via the show-me-your-work skill so a reviewer can audit the run after stepping away. - Use Case: You need to migrate an API pattern across hundreds of call sites. The Skill sequences riskiest-unknown-first units, builds a verification harness from the pre-change baseline, and produces a decision log you can review in the PR. ## Quick Start Ask the agent to figure out a plan for migrating the legacy authentication module across all services with a verifiable audit trail.

Frequently Asked Questions about figure-it-out

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I plan a large code migration with an AI agent?▼

Use a playbook-design workflow that frames a falsifiable definition of done, quantifies scope, and decomposes the migration into atomic, independently-landable units. Sequence riskiest-unknown-first and verify each unit before starting the next.

When should I use figure-it-out instead of a feature or bug-fix playbook?▼

Use it when the task matches no narrower playbook: a migration across many call sites, an ambitious multi-part change, or work a human reviews after stepping away. Focused single-unit tasks route to the Bug fix, Perf, or Feature playbooks instead.

How does the hypothesis loop verify each change?▼

Each unit states a hypothesis, makes the smallest change, and measures against the predicate on the real artifact. Verdicts are VERIFIED, NOT VERIFIED, or INCONCLUSIVE, and inconclusive results never count as passes.

What is the decision audit trail and where is it stored?▼

The audit trail is a canonical TSV logged via the show-me-your-work skill, with one row per decision and per unit plus evidence links. For ambitious work it is committed so reviewers can read it in the PR and re-run evidence scripts.

When is the architect skill invoked during playbook design?▼

The architect skill runs for one-way-door design decisions, using diverse isolated candidates and a read-only judge on a different model family. It is skipped for mechanical work whose shape is already concrete to avoid over-engineering.