hummbl-io/agent-skills/auto-ship
Claude Code and agent skill by hummbl-io/agent-skills
- community
Checking that the SKILL.md file is still in the repository.
Alias for the lfg skill (compound-engineering plugin). Full autonomous shipping pipeline: plan, implement, review, commit, push, open PR, watch CI to green — hands-off with no check-ins. Use this when you want the autonomous ship pipeline but need a self-documenting skill name.
Install
npx vskill@latest install hummbl-io/agent-skills/auto-shipSKILL.md
The same SKILL.md was published earlier as hummbl-io/agent-skills/auto-ship.
auto-ship
This is an alias for the `lfg` skill. Invoke lfg with the same arguments.
The lfg skill (compound-engineering plugin) runs the full autonomous shipping pipeline end-to-end, hands-off with no check-ins: plan, implement, review and fix, commit, push a branch, open a PR, and watch CI to green.
Why this alias exists
lfg is an opaque name (internet slang for "let's fucking go"). Agents scanning the skill catalog see lfg and don't know what it does without loading its SKILL.md. auto-ship is a self-documenting name that appears alongside lfg in the catalog, making the autonomous shipping pipeline discoverable by name.
Usage
All arguments pass through to lfg unchanged.
When to use
- Operator explicitly wants hands-off autonomous shipping to an open PR
- The full plan → implement → review → commit → push → PR → CI pipeline is wanted
- The operator says "ship it", "auto-ship", "autonomous ship", or "lfg"
When NOT to use
- In-the-loop work where the operator reviews each step — use
ce-plan,ce-work,ce-debug, orce-commit-push-prinstead - Operator-visible step-by-step shipping — use the native
shipskill instead
Relationship to ship (native)
ship(native): test → scan → PR → merge → tag with operator-visible stepsauto-ship/lfg(plugin): same pipeline but fully autonomous — pushes and opens a PR without stopping
Skill Chains
Mandatory
- None — this skill is self-contained.
Authority
- T1 (TRUSTED): May run without restriction
- T2 (Active/High): May run without restriction
- T3 (Medium): MUST get operator approval before execution
- T4 (Probationary): BLOCKED — cannot invoke this skill
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/auto-ship/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/hummbl-io/agent-skills/auto-ship)