figure-it-out

Designs an auditable multi-phase workflow for large migrations and ambiguous engineering tasks.

4|1|Updated Dec 16, 2023
One-click install
npx skills add https://github.com/Shtian/AuthentiClash --skill figure-it-out-shtian
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: figure-it-out
Source: https://github.com/Shtian/AuthentiClash/tree/main/.claude/skills/figure-it-out
Command: npx skills add https://github.com/Shtian/AuthentiClash --skill figure-it-out-shtian

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When a task matches no existing playbook—such as a large migration, an ambitious multi-part change, or work a human reviews after stepping away—this Skill designs a rigorous, auditable workflow before any code is written, preventing wasted effort on the wrong approach. ## Core Features & Use Cases - Workflow Design: Frames the task with a falsifiable definition of done, quantified scope, and a rigor level scaled to risk, then decomposes work into atomic, independently-landable units sequenced riskiest-first. - Hypothesis Loop: Runs each unit as an experiment—state a hypothesis, make the smallest change, verify 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 alongside the diff. - Use Case: You need to migrate a large codebase to a new framework with no existing playbook. Use this Skill to frame the migration, build a verification harness from the pre-change baseline, execute units under the loop discipline, and hand back a committed decision trail. ## Quick Start Ask the AI to figure out a plan for your large migration or ambiguous multi-part change using the figure-it-out playbook.

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 no existing playbook?▼

Frame the migration with a falsifiable definition of done and quantified scope, then decompose it into atomic, independently-landable units sequenced riskiest-first. Build a verification harness from the pre-change baseline before starting feature work.

What is a hypothesis loop for coding tasks?▼

A hypothesis loop treats each work unit as an experiment: state the hypothesis, make the smallest change, measure against the predicate on the real artifact, and keep or revert based on the result. Verdicts are VERIFIED, NOT VERIFIED, or INCONCLUSIVE.

When should I use figure-it-out instead of a narrower skill?▼

Use it only when no narrower playbook applies, such as large migrations or ambiguous multi-part changes. For mechanical work with a concrete shape, a settled design does not need another architecture pass.

How do I make autonomous AI work auditable for human review?▼

Log the run in a canonical TSV with one row per decision and per unit, with evidence as links, and commit the trail alongside the diff. The trail plus the diff lets a reviewer trust the work after stepping away.

What are the limitations of a hypothesis-loop workflow?▼

The loop adds rigor overhead that is wasteful for reversible, low-stakes tasks. It also depends on a sound verification gate; if the gate itself is wrong, results are misleading until the gate is fixed in its own change.