ship-gate
Skill0 starsChanged 3 months agoMITView on GitHub
Use when work is headed for a real audience, deploying a website, publishing, releasing, pushing to production, or any change someone other than the builder will see. Triggers on deploy, publish, release, go-live, production, "put it online". Enforces the ladder, run it locally, test it deliberately, explicit go / no-go, then verify live.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- kazemcodes/skill-treetheir own version, first seen Nov 8, 2026
- hamidettefagh/two-gatestheir own version, first seen Oct 28, 2026
- tderoussel/agent-skillstheir own version, first seen Oct 20, 2026
- edenbuilds/agentlooptheir own version, first seen Oct 13, 2026
- Hassaan146/claude-skillstheir own version, first seen Jul 25, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- unlearndev/skills★ 101same name
- Hassaan146/claude-skills★ 18same name
- csiddhant796-blip/claude-skills-collection★ 2same name
- Hussain-Elfalah/Agentic-Skills★ 2same name
- kazemcodes/skill-tree★ 1same name
- mahiunfiltered/claude-code-skills★ 1same name
- orkait/hyperstack★ 1same name
- tderoussel/agent-skills★ 1same name
- darkweb19/skills★ 0same name
- edenbuilds/agentloop★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llm-actionsSkill
- product-onboardingSkill
- product-specSkill
- research-swarmSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
2
Distinctive
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
- Distinctive: line 8
WHEN shipping to anyone beyond this machine, climb the ladder in order.
- Distinctive: line 17
Test the states real users hit: empty, loading, error, slow network, wrong input, mobile.
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ship-gate
WHEN shipping to anyone beyond this machine, climb the ladder in order; a skipped rung is how demos break in public:
- Local first. Run the real thing on this machine (localhost for a site, the actual app for an app) and use it the way the end user will: click through it at the actual screen size, not just compile it. Nothing goes live that was never run.
- Green must prove work. A gate that cannot fail is not a gate: trip each check once on purpose (bad input, missing env var, broken link) and watch it catch the failure. Read exit codes and output; do not trust the shape of the logs.
- Test the states real users hit: empty, loading, error, slow network, wrong input, mobile. The happy path is the best case, not the common case.
- Explicit go / no-go before shipping: say what this deploy changes, what it cannot undo, and how to roll back. For money, compliance, or customer data, a read-only audit (the auditor agent) makes the call; the builder never grades their own audit. NO-GO is a normal, cheap outcome.
- Ship, then verify live: use the shipped thing as a stranger would (the real URL in a fresh browser, the installed build on a real device) and watch it work. The release is done when it is seen working where users see it, not when the command exits.
Skill updated: 2026-08-15
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
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.