Skill 与 AgentSKILLS & AGENTS· CLAUDE-SKILL
no-session/pstack
独立开发者的AI工作流套件,把从验证想法到监控线上产品的过程变成一串命令pstack is a collection of Claude Code skills that walks solo founders through the full build-ship-monitor loop.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
快速验证产品点子值不值得做
从多角度审阅开发计划
在真实浏览器里自动检查页面
一键推送代码到生产环境
上线后持续监控网站状态
上手GET STARTED
git clone --single-branch --depth 1 https://github.com/no-session/pstack.git ~/.claude/skills/pstack选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01执行 Shell 命令Runs shell commandsSKILL.md
allowed-tools: Bash
02执行 Shell 命令Runs shell commandsbenchmark/SKILL.md
allowed-tools: Bash
03读写本地文件Reads and writes local filesbenchmark/SKILL.md
allowed-tools: Write
04读写本地文件Reads and writes local filescodex/SKILL.md
allowed-tools: Write
05控制浏览器Controls a browserconnect-chrome/SKILL.md
This launches Playwright's bundled Chromium in headed mode with:
06控制浏览器Controls a browserdesign-review/SKILL.md
**CDP mode detection:** Check if browse is connected to the user's real browser:
静态扫描命中多项中风险:技能会调用 shell 执行命令(Bash)、读写本地文件(Write),并可能通过 Playwright 启动浏览器或连接真实 Chrome;这些操作是项目功能的一部分,但意味着它会主动改动你的系统和数据。建议先浏览源码、理解每条命令再运行,尤其注意它可能自动执行升级脚本。
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+30.8%+30.8%
120 → 157 stars · 49 个快照120 → 157 stars · 49 snapshots
状态STATUS
长期未更新Not updated
质量 A-Quality A-
这个仓库创建于 2026-03-29,目前有 138 stars、9 forks 和 0 个 open issues,可以立即克隆试用。It's a fork of gstack, rebuilt specifically for bootstrappers and solo founders.
依赖:Dependencies:diff, playwright, puppeteer-core
{
"agents": [
{
"agent": "claude-code",
"evidence": "readme: …# Quick Start Requirements: [Claude Code](https://docs.anthropic.com/e…"
},
{
"agent": "codex",
"evidence": "readme: …/codex` | Second opinion from OpenAI Codex. Independent code review, adv…"
}
],
"apiKey": "at` (network exfiltration) - `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `env.`, `process.en",
"docker": null,
"taxonomy": {
"scores": {
"design": 2,
"ai-tools": 0,
"dev-tools": 4,
"indie-web": 6,
"skill-agent": 3,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "claude-skill"
},
"localRuntime": null,
"skillMdTotal": 30,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 2,
"agent": 0,
"media": 0,
"design": 2,
"browser": 0,
"devtool": 3,
"security": 1,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "30 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"SKILL.md",
"benchmark/SKILL.md",
"browse/SKILL.md",
"careful/SKILL.md",
"codex/SKILL.md",
"connect-chrome/SKILL.md",
"cso/SKILL.md",
"design-consultation/SKILL.md",
"design-review/SKILL.md",
"design-shotgun/SKILL.md",
"document-release/SKILL.md",
"freeze/SKILL.md",
"guard/SKILL.md",
"investigate/SKILL.md",
"land-and-deploy/SKILL.md",
"monitor/SKILL.md",
"plan-ceo-review/SKILL.md",
"plan-design-review/SKILL.md",
"plan-eng-review/SKILL.md",
"plan/SKILL.md",
"pstack-upgrade/SKILL.md",
"qa-only/SKILL.md",
"qa/SKILL.md",
"reflect/SKILL.md",
"review/SKILL.md",
"setup-browser-cookies/SKILL.md",
"setup-deploy/SKILL.md",
"ship/SKILL.md",
"unfreeze/SKILL.md",
"validate/SKILL.md"
],
"skillMdFetched": 30
}