agentleFS
Sign inStart free
HarambeeAIHarambeeAI/bayes-ship/skills/ship-new/SKILL.md

ship-new

Skill1 starsChanged 7 months agoMITView on GitHub

Initialize a new Bayes Ship product project. Creates state directory, captures project basics, detects relevant skills. Run this first before any other ship command.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create the project scaffold for a Bayes Ship product delivery pipeline.

    line 8
  2. Very specific:

    Create .claude/state/ directory if it does not exist.

    line 12
  3. Distinctive:

    Ask the user for:

    line 13
  4. Very specific:

    Write .claude/state/PROJECT.md with all captured information.

    line 19
  5. Distinctive:

    Do NOT start any implementation, brainstorming, or research.

    line 36
  6. Distinctive:

    Keep it fast. This should take under 1 minute.

    line 37
  7. Very specific:

    If the project directory already has a .claude/state/PROJECT.md, warn the user and ask if they want to overwrite.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Initialize new product

Create the project scaffold for a Bayes Ship product delivery pipeline.

Process

  1. Create .claude/state/ directory if it does not exist.
  2. Ask the user for:
    • Project name (short, lowercase, kebab-case, used for git branches and directories)
    • One-line description (what does this product do, in plain language)
    • Target users: A. Businesses (B2B) / B. Consumers (B2C) / C. Internal team tool / D. Other
    • Primary platform: A. Web app / B. Mobile app / C. API/backend service / D. Desktop app
  3. Scan installed skills and flag which are relevant to this project based on the description and platform.
  4. Write .claude/state/PROJECT.md with all captured information.
  5. Initialize .claude/state/progress.json:
{
  "project": "<project-name>",
  "current_phase": "setup",
  "phases": {},
  "last_checkpoint": "<timestamp>",
  "git_commits": 0
}
  1. Output: "Ready. Run /bayes-ship:ship-discover to start requirements gathering."

Rules

  • Do NOT start any implementation, brainstorming, or research. Only capture project basics.
  • Keep it fast. This should take under 1 minute.
  • If the project directory already has a .claude/state/PROJECT.md, warn the user and ask if they want to overwrite.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free