agentleFS
joaoajmatosjoaoajmatos/ze/.claude/skills/ze-land-floor/SKILL.md

ze-land-floor

Skill2 starsChanged 48 days agoUnlicenseView on GitHub

Lands a reviewed floor into main behind code checks and pushes it. Use when the Maestro is asked to land a floor, or a floor in review has a reviewer APPROVE and a QA pass.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Run these steps exactly, in order.

    line 9
  2. Distinctive:

    Never force-push, and never push main from any role but the Maestro.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Land a floor (Maestro only)

Run these steps exactly, in order. Stop at the first failure and report it. Do not work around a failed check.

  1. Preflight, from the floor's checkout: make process-land-preflight FLOOR=<floor path> It checks history and merge conflicts, untracked files in the floor and Ground, phase status sync, new files under specs/arch/, the gate receipt for the floor HEAD, and the APPROVE review chain. Fix what it names; never edit receipts or review records by hand.
  2. Land: maestri floor land "<floor>" --into main.
  3. In Ground, run the full gates and record the receipt with this one command: make process-gates PROFILE=land It must exit 0. Run no raw make test-py, test-web or other gate first: the push accepts only this receipt, and each full gate would run twice.
  4. Post-land, in Ground: scripts/process/land_post.sh It refreshes the graph and pushes main. It skips any step already done, so re-running is safe. The push hook refuses without a green receipt for HEAD.
  5. By hand, because they need judgment: the score line and roadmap line, then dismiss the floor's agents, delete the floor, remove lane worktrees and archive state files.

Preview without side effects: python3 scripts/process/land_preflight.py --dry-run and scripts/process/land_post.sh --dry-run.

Never force-push, and never push main from any role but the Maestro.

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.