Skip to content
Agentmart
Submit a tool

figure-it-out

Design and run an auditable playbook when no narrower mestack playbook fits.

Skill by kevherro

IndexedMIT
Write a review

Chalk Labs

Need help deploying figure-it-out?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/kevherro-figure-it-out

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Design and run an auditable playbook when no narrower mestack playbook fits. Use for /figure-it-out, a large migration, or work a human will review after stepping away.

Use cases: design

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/figure-it-out

What's inside

Skill name
figure-it-out
Description
Design and run an auditable playbook when no narrower mestack playbook fits. Use for /figure-it-out, a large migration, or work a human will review after stepping away.
License
MIT
Instructions
38 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Figure it out

When investigate, fix, build, reshape, and leave-running do not fit,
design the playbook first. The deliverable before code is a sequence
of units that each end in a check.

A focused bug, feature, or refactor still belongs on those playbooks.
This skill is for the large or cross-cutting case, or for work the
user will audit after stepping away.

If they are leaving, run **leave-running** with this playbook as the
work. Do not invent a second overnight contract.

## Steps

1. Read the Principles index in the **mestack** skill. Name each
   principle that changes a decision.
2. Frame, then stop long enough to say it:
   - Done as a falsifiable predicate (**prove-on-the-artifact**).
   - Scope in rough units, plus blockers already visible.
   - Rigor as gates and artifacts, biased high for one-way doors.
     Reversible steps stay small (**smallest-change**).
3. Decompose into independently landable units. Riskiest unknown
   first. Harness and baseline before features. Fan-out only on real
   seams, unique worktrees, parent-owned
   (**parent-owns-fan-out**). Write the unit list into the todo list.
4. For each unit: state the hypothesis, make the smallest change,
   **prove** it on the real artifact. Keep it if the predicate moved.
   Revert it if it did not. Inconclusive is not a pass.
5. Log every decision and unit through **show-me-your-work**. Do not
   invent a second trail format.
6. Prove the whole against the step-2 predicate. Encode a recurring
   miss as a check (**encode-the-rule**).

**Reply:** the playbook, the rigor level and why, the trail path,
what the predicate showed, what is still open.

From kevherro/mestack, MIT.

Signals

Stars
0
Forks
2
Open issues
0
Last commit (this folder)
Sep 1, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from kevherro

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get figure-it-out running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying figure-it-out?

CallGet help
Cite this page

figure-it-out skill. Agent Mart. https://agentmart.dev/skills/kevherro-figure-it-out (last updated 2026-10-24)