Skills for Real Engineers. Straight from my .agents directory.
figure-it-out
Agent skill frommichael-denyer/pstack-claude
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. Use for /figure-it-out or 'figure it out'.
How to install figure-it-out
npx skills add michael-denyer/pstack-claude# or add only this skill to Claude Code: copy the folder
plugins/pstack/skills/figure-it-out/
# into
~/.claude/skills/figure-it-out/ (all projects)
.claude/skills/figure-it-out/ (one project)
1# Figure it out23When 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.45## Start67Open a todolist whose first item is to read the Principles section of the **poteto-mode** skill. Then add the phases below as todos.89## Phase A: Frame1011Ground first, then commit. Don't start the run until you can state:1213- The definition of done as a falsifiable predicate (the **prove-it-works** principle skill).14- Scope, quantified: rough units and effort, plus the blockers grounding surfaced.15- 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".1617Present 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.1819## Phase B: Design the workflow2021Decompose into atomic, independently-landable units. Sequence riskiest-unknown-first. Scaffold and verification come before features (the **foundational-thinking** principle skill).2223- 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".24…
Excerpt shown under the repository's MIT license.
More skills in pstack-claude
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
