launch-check
Skill0 starsChanged 31 days agoMITView on GitHub
Check an AI-built website or app before it goes online. Use when the user says they want to publish, launch, deploy, or share their project, or asks whether it is safe to make it public. Finds exposed secrets, broken pages, missing setup, and things that will break on a real visitor's phone, then fixes what can be fixed safely.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- ssaarthakk/dev-setuptheir own version, first seen Nov 8, 2026
- craigcossairt/trellistheir own version, first seen Nov 6, 2026
- Ces107/agent-forgetheir own version, first seen Oct 25, 2026
- matt-warchol/launch-checktheir own version, first seen Oct 20, 2026
- path-to-ai-com/ptai-ecom-toolkittheir own version, first seen Oct 15, 2026
- me2resh/apexyardtheir own version, first seen Oct 8, 2026
Used with
Projects with it also use setup.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
VercelSkillsetup
Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".
Also in 3 projects that use this
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- me2resh/apexyard★ 542same name
- craigcossairt/trellis★ 5same name
- ssaarthakk/dev-setup★ 2same name
- matt-warchol/launch-check★ 1same name
- 20030419zhanghongyi/AI-Software-Engineering-Workflow-Template★ 0same name
- Ces107/agent-forge★ 0same name
- path-to-ai-com/ptai-ecom-toolkit★ 0same name
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 repository11 other files it gives its agents.
- brand-paletteSkill
- clear-deckSkill
- data-storySkill
- event-posterSkill
- icon-familySkill
- idea-deckSkill
- kinetic-typeSkill
- landing-storySkill
- portfolio-pageSkill
- product-posterSkill
- sketch-notesSkill
The file
Files
上线前检查
用户不懂代码。你负责检查、解释和修复,用户只需要回答问题和确认结果。
目标
在项目公开之前,找出会真正影响用户的问题:密钥泄露、打不开的页面、没配好的环境、 手机上显示错乱、缺少必要配置。能安全修的直接修,不能修的用大白话说清楚。
语言
用用户使用的语言回复。用户说中文就用中文,说英文就用英文。报告里不出现 "环境变量""构建产物""依赖树"这类词,除非用户先用了并且你解释过一次。
步骤
1. 先确认项目位置和结构
- 找到项目根目录,识别它是哪种项目(页面网站、带后端的应用、小程序、桌面应用)。
- 找到它的启动方式、构建方式,以及线上部署的目标(如果用户已经部署过)。
- 如果项目里已有 README 或部署说明,读一下,不要凭猜测行动。
输出一句话给用户,例如:"这是一个网站项目,用 Vite 构建,目前还没看到部署配置。"
2. 只读检查
按 references/checks.md 逐项检查。这一阶段不修改任何文件,只记录结果。
每一组检查完成后,如果发现问题,先用一句话告诉用户发现了什么、严重程度如何, 再继续下一组。不要在最后一次性抛出所有问题。
3. 生成大白话报告
按下面的顺序输出,最严重的问题放最前面。每条都要有:是什么、为什么有影响、 用户会看到什么现象、建议怎么处理。
# 上线前检查报告
结论:<可以直接上线 / 修完这几项再上线 / 暂时不要公开>
## 必须修(会影响真实用户)
1. <问题> — <用户会看到什么> — 建议:<处理方式>
## 建议修(不影响能用,但容易被看出来)
1. ...
## 已经没问题的部分
- ...
## 需要你自己操作的步骤
1. <去哪里、点什么、复制什么、粘贴到哪>如果某一项无法检查(缺少工具、缺少账号、需要联网但没有网络),明确写"没检查到", 不要写成"通过"。
4. 修复
- 修之前,先说明要改哪些文件、改什么,等用户同意。一次只改一类问题。
- 涉及删除文件、改动数据库、覆盖已有配置的操作,必须先问。
- 密钥、密码、令牌:写进本地配置文件或部署平台的设置项,不要写进代码。 如果发现密钥已经提交进版本历史,告诉用户这个密钥需要作废重发,并说明这不是 改代码能解决的问题。
- 报告和对话里不要出现密钥的任何内容,包括开头几位、结尾几位、长度或哈希。 只说它出现在哪个文件、哪一类密钥、为什么危险。写出一部分同样会让密钥更容易被 使用。确需指认时,用文件路径加行号代替。
- 每修完一类问题,让用户看一眼结果,再继续下一类。
5. 复测并确认上线
- 重新跑一遍受影响的检查,确认修好了。
- 告诉用户现在能不能上线;如果可以,给出上线所需的下一步(部署、绑定域名等)。
- 提醒用户:这次检查覆盖的是常见问题,不能代替真实用户的使用测试。
边界
- 不代替用户注册账号、开通服务、填付款信息。
- 不做未经确认的重构、不升级依赖大版本、不改动业务逻辑。
- 用户明确要求跳过某一项时,记录为"用户选择跳过",不再检查该项。
- 如果项目里有明显的违法内容或用于欺骗用户的功能,停止检查并直接说明原因。
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.

