agentsclimarketplace

Autonomous setup

Skill BechsteinDigital/claude-shiploop/autonomous-setup

Autonomous delivery skills for Claude Code — pitch an idea, get an MVP. CEO/PO/DEV/Reviewer agent team with contracts, gates, and evidence rules.

Install
npx -y skills add BechsteinDigital/claude-shiploop --skill autonomous-setup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 22 days oldThe repository was created 22 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when an approved product brief (project/BRIEF.md, status APPROVED) exists and the project should be set up without further user input — research, tech decisions, scaffold, backlog. Do not use while the brief is missing or DRAFT (→ project-onboarding).

SKILL.md

3.2 KB, as published. Nobody here has run it

Autonomous Setup

Principle

From here on, no questions to the user. Every open decision is made autonomously and logged in project/DECISIONS.md as an ADR. Only exceptions: the escalation criteria from the autonomy contract in project/BRIEF.md.

No AskUserQuestion tool (enforced): a reversible open decision → decide and log an ADR; an escalation criterion hit → stop with a decision memo. Never an interactive prompt.

Precondition

project/BRIEF.md exists with status APPROVED. Otherwise abort and request project-onboarding.

Phases

1. Research (timeboxed, parallel)

First read the global knowledge base (resolve: $SKILLS_KNOWLEDGE_DIR if set, otherwise the path in <skills-dir>/_shared/knowledge.path — written by install.sh; if neither resolves → skip) — documented learnings from earlier projects replace research and prevent repeat mistakes.

Then parallel read-only subagents in one invocation block, one per question:

  • Alternatives: What already exists? What does it not do well enough? (confirms/sharpens the core contract)
  • Tech options: 2–3 stack candidates fitting the must-have outcomes, target environment, and cost frame — with trade-offs, not with a winner
  • Risks: legal, technical, and cost traps of the domain

Results go to project/log/<date>-research-<topic>.md. Research findings that suggest new features go into project/IDEAS.mdnever directly into scope.

2. Decide

Determine stack, architecture cut, and project structure: one ADR each in project/DECISIONS.md (decision, alternatives, rationale, reversal cost). On a tie, the decider is: least complexity for the must-have outcomes — not the most interesting technology.

3. Scaffold

  • Initialize the repo (if not present), skeleton per the ADRs, .gitignore, minimal README.
  • Create project/PROFILE.md from _shared/templates/PROFILE.template.md. Enter each command (build, test, lint, run) only after it ran successfully once.
  • A walking skeleton is enough: buildable, testable, startable. No feature implementation during setup.

4. Backlog

  • At least one WORK card per must-have outcome from the brief (project/backlog/, follow the template): P0 = critical path to MVP.
  • Cut cards small and with disjoint claim zones where possible — that enables the loop to parallelize.
  • Initialize project/STATE.md and project/IDEAS.md from the templates.

5. Finish

First commit (scaffold + project/ artifacts). Short setup report in project/log/. Then start autonomous-loop directly — don't wait for confirmation.

Red flags

  • "I'll quickly ask the user which language they prefer" → violation: decide, log, continue.
  • Research takes longer than the scaffold → timebox violated; decide with available knowledge.
  • Commands in the profile that never ran → the profile lies, the loop breaks later.
  • Setup already implements features → belongs in WORK cards and the loop.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.