figure-it-out
Design and run an auditable playbook when no narrower mestack playbook fits.
Skill by kevherro
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.
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.
About
Use cases: design
Reviews
Write a reviewNo 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
- Repository
- github.com/kevherro/mestack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kevherro
- 0.567score
mestack
kevherro
Kevin's harness-agnostic engineering dispatcher.
SkillAFreshness: AClaude Code +9 - 0.567score
create-verification-skill
kevherro
Generate a project-local verify-<app> skill that drives this repo's real app the way a user does.
SkillAFreshness: AClaude Code +9 - 0.565score
create-formal-verification-skill
kevherro
Write a repo-local formal-<area> skill that machine-checks one high-stakes promise tests rarely exercise, using the verifier that fits the question.
SkillAFreshness: AClaude Code +9 - 0.565score
maintain-formal-verification-skill
kevherro
Re-sync a repo's formal-* checks with code that moved since their last confirmation: read those commits, update the model from the code, rerun, and classify…
SkillAFreshness: AClaude Code +9 - 0.563score
interrogate
kevherro
Adversarial review of a change by one child per configured reviewer.
SkillAFreshness: AClaude Code +9 - 0.561score
correct
kevherro
Turn the mistakes agents repeat in this repo into ones they cannot make, preferring the strongest enforcement that fits.
SkillAFreshness: AClaude Code +9
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.
Cite this page
figure-it-out skill. Agent Mart. https://agentmart.dev/skills/kevherro-figure-it-out (last updated 2026-10-24)