skills/ship/SKILL.md
Commit and push changes with a pre-launch gate (validate-code + safe-repo) by default. Use when user asks to "ship", "commit and push", or requests committing and pushing changes. Don't use for creating pull requests or reviewing changes before committing.
npx skillsauth add helderberto/skills shipInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Ship runs a pre-launch gate before committing. By default: validate-code + safe-repo. The gate ensures nothing broken or unsafe leaves the working tree.
git statusgit diff HEADgit log --oneline -10--fast — skip the pre-launch gate. Use only for hotfixes or commits to disposable branches. State the reason in the commit message body.--fast)validate-code returns FAIL → report errors, STOP. Do not commit or push.git add -A or git add .)git push (current branch)git status after to verify--fast with a stated reasongit add -A or git add .-f or --force)validate-code fails → report all errors, stop; do not commit or pushsafe-repo flags sensitive data → report findings, stop; do not commit or pushgit push is rejected (non-fast-forward) → run git pull --rebase then retry push once--amend)--fast is used → log "Pre-launch gate skipped via --fast" in agent output for traceability--fastAcceptable cases:
Not acceptable:
tools
Teach the user a new skill or concept, within this workspace.
documentation
Compact the current conversation into a handoff document for another agent to pick up.
testing
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
development
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill, or asks "make a skill for X".