Skip to content
Agentmart
Submit a tool

cheese-board-loop

Runs the cheese-board workflow and asks the user each question it raises.

Skill by paulnsorensen

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying cheese-board-loop?

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/paulnsorensen-cheese-board-loop

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

Runs the cheese-board workflow and asks the user each question it raises. Use when the user says "cheese-board", "plan the backlog", "strategy from triage and ideas", or invokes /cheese-board-loop. Do NOT use for one spec (/mold), for building a spec (/cheese-factory), or for an unattended run (pass auto:true to the workflow directly).

Use cases: productivity

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 and code. Checked Nov 1, 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/cheese-board-loop

What's inside

Skill name
cheese-board-loop
Description
Runs the cheese-board workflow and asks the user each question it raises. Use when the user says "cheese-board", "plan the backlog", "strategy from triage and ideas", or invokes /cheese-board-loop. Do NOT use for one spec (/mold), for building a spec (/cheese-factory), or for an unattended run (pass auto:true to the workflow directly).
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# cheese-board-loop

Run the cheese-board workflow. Ask the user each question the workflow raises. Rerun it with the answers.

## Loop

1. Run the Workflow tool with `cheese-board` and args `{ stamp: "<today, YYYY-MM-DD>" }`. Add `repo`, `limit`, `ideas`, `maxSpecs`, or `focus` only when the user gave them.
2. Read `status` in the result.
3. If `status` is `needs-input`, ask the user every entry in `questions` with AskUserQuestion.
   - Put the `recommended` option first. Add the other `options`.
   - Show `evidence` as the question context.
   - AskUserQuestion takes 1 to 4 questions per call and 2 to 4 options per question. Batch the questions in groups of up to 4, with one call per group.
   - If a question has 0 or 1 options, pad the options, or let the user type a free answer in the built-in "Other" field. Keep the `recommended` option first.
   - At the `strategy` checkpoint, ask whether any initiative changes lane. Pass the moves as `lanes: { "IN-n": "spec|mold|defer" }`.
4. Rerun the Workflow tool with `{ stamp, state, digest, answers }`.
   - Reuse the original `stamp` without change on every rerun.
   - Copy `state` and `digest` from the `needs-input` result without change.
   - Key each answer by the question `id`. The exact question text or its 1-based number also works.
5. Repeat from step 2.
6. Stop on any other `status` (`ok`, `partial`, `needs-review`, `stopped`, `blocked`, `empty`). Report the factory queue, the `/mold` list, the report path, and the gaps.

## Rules

- Never edit `state`. The digest detects an edit, and the run returns `blocked`.
- Never combine `auto: true` with `state`, `digest`, `answers`, or `lanes`. An auto run does not pause.
- Answer closed questions (those with `options` and a `closed` flag) with exactly one option.
- At the `done` checkpoint, the answer `approve` records the strategy. Any other answer is a fix that the workflow applies to the report once.
- Do not chain into `/cheese-factory`. Print the queue commands and stop.

From paulnsorensen/dotfiles, MIT.

More from paulnsorensen/dotfiles

Signals

Stars
2
Forks
0
Open issues
69
Last commit (this folder)
Oct 15, 2026 (18 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from paulnsorensen

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 cheese-board-loop 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 cheese-board-loop?

CallGet help
Cite this page

cheese-board-loop skill. Agent Mart. https://agentmart.dev/skills/paulnsorensen-cheese-board-loop (last updated 2026-10-24)