Skip to content
Agentmart
Submit a tool

build

Clarify a project with the user and compile it into an advisory queue of goal-sized milestones.

Skill by qwerty-sapien

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying build?

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/qwerty-sapien-build

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

Clarify a project with the user and compile it into an advisory queue of goal-sized milestones. Build plans; queue runs execute.

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/build

What's inside

Skill name
build
Description
Clarify a project with the user and compile it into an advisory queue of goal-sized milestones. Build plans; queue runs execute.
License
MIT
Instructions
17 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Cruise Build

Build is the bowling setup for a whole project: clarify the vision once, inspect the repository, and decompose the work into a sequence of independently verifiable Goal runs. Do not implement the milestones in this conversation. Execution belongs to `cruise queue run` or an explicit Goal invocation.

Inspect the repository before asking questions. Ask only material questions whose answers change the decomposition: product intent, hard constraints, compatibility obligations, required migrations, and what must never break. Resolve ordinary implementation details from repository evidence. Do not demand approval phrases, plan digests, or ceremonial checkpoints.

Compile the result into goal-sized milestones. Every milestone must have a one-line falsifiable outcome, its own verification commands, explicit likely touchpoints, explicit non-goals, protected invariants, a risk level, relevant quality profiles, and only real dependencies. Always select `core`; add `web`, `backend-data`, or `cxx-hpc` when the milestone surface warrants it. Use `high` or `critical` for security, persistence, concurrency, public contracts, migrations, costly computation, or unusually costly failure. A milestone should be independently completable; split work that cannot be verified without an unrelated later phase. Use non-goals to stop later concerns from bleeding into the current milestone.

State cross-milestone reconciliation obligations once in the queue body. Include backward and forward compatibility, migration reversibility, coexistence windows, and cleanup conditions when they matter. Every generated flight plan inherits this body, so write obligations as constraints that remain meaningful throughout the queue.

Write the compiled plan to `.cruise/QUEUE.md` using version 2: `milestones` with `id`, `status`, `outcome`, `verify`, `depends`, `touchpoints`, `non_goals`, `invariants`, `risk`, and `profiles`, followed by a concise Markdown body explaining the vision, milestone rationale, compatibility obligations, and sequencing. New milestones start `pending`. Queue v1 remains readable, but new Build work uses v2 so queue execution can seed the appropriate Flight quality dimensions and high-risk independent review.

Present the queue plainly in the conversation so the user can reorder, split, combine, or edit it before execution. The queue is advisory and user-editable between runs. It grants nothing, gates nothing, and never replaces the selected host's permissions. It is not a contract, ledger, digest, archive, approval record, or per-milestone run directory.

Treat worker-level and communication-manner preferences as natural-language instructions for this request only. Never persist or globally enforce them. Override the ordinary worker level only when the user explicitly asks for a higher, lower, or numbered level; an explicit terminal `cruise worker --level <1-7>` selection has highest priority for that invocation.

From qwerty-sapien/cruise, MIT.

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Jul 25, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from qwerty-sapien

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 build 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 build?

CallGet help
Cite this page

build skill. Agent Mart. https://agentmart.dev/skills/qwerty-sapien-build (last updated 2026-10-24)