Skip to content
Back to skills

Setup

ASecurity

Configure this repository for the Skrrt ship workflows and select a branching strategy. Run once before commit, pr, and release.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 22, 2026
ai-agentsbashgit

Security analysis

A100/100

Pro scans all 9 files and shows the line behind each finding

Scanned October 22, 2026

npx -y skills add skrrt-sh/skills --skill setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Setup?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Setup
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/skrrt-sh-setup/badge)](https://www.skillsdirectory.com/skills/skrrt-sh-setup)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: setup
description: Configure this repository for the Skrrt ship workflows and select a branching strategy. Run once before commit, pr, and release.
disable-model-invocation: true
allowed-tools: Bash(${CLAUDE_SKILL_DIR}/scripts/configure-ship.sh:*)
---

# Configure Ship Workflows

Create a short agent-instruction pointer and a detailed `.agents/ship.md` policy for this
repository.

## Process

1. Confirm the current directory is a Git repository.
2. Select the first existing instruction file from `CLAUDE.md`, `AGENTS.md`,
   `.claude/CLAUDE.md`, and `.github/AGENTS.md`. If none exists, ask the user whether to create
   `CLAUDE.md` or `AGENTS.md`.
3. Read [references/branching-strategies.md](references/branching-strategies.md). Inspect the
   repository signals it names, then present GitHub Flow, Trunk-Based Development, and Gitflow with
   one evidence-based recommendation. The user makes the final choice: wait for it before writing
   anything, even where other skills say not to ask. If they already named a
   strategy, treat that as their choice after reporting any material mismatch.
4. If `.agents/ship.md` already exists, report its configured strategy before replacing it. Only
   the `skrrt:policy` block is replaced; anything the repository added outside it is kept.
5. From the target repository, run:

   ```text
   ${CLAUDE_SKILL_DIR}/scripts/configure-ship.sh \
     --instruction-file <path> \
     --strategy <github-flow|trunk-based|gitflow>
   ```

6. Report the instruction file, selected strategy, and whether each file changed.

The script may modify only the selected instruction file and `.agents/ship.md`. It preserves
content outside Skrrt markers, removes the legacy `skrrt:branching` block during migration, and is
safe to run repeatedly.

Files in this skill

  • SKILL.md1.7 KB
  • agents/openai.yaml233 B
  • assets/gitflow.md811 B
  • assets/github-flow.md697 B
  • assets/instruction-pointer.md431 B
  • assets/trunk-based.md935 B
  • evals/evals.json4.8 KB
  • references/branching-strategies.md1.6 KB
  • scripts/configure-ship.sh5.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.