用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Vibe-Marketer/brain --skill gsd-health命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
End-to-end battle-tested playbook for taking a SaaS product from "works on my machine" to production. Generates CI/CD pipelines (GitHub Actions), runs load tests (k6 + Locust), audits security against OWASP Top 10:2025, verifies Supabase RLS, runs Lighthouse Core Web Vitals checks, and produces a launch-day runbook. Use this skill whenever the user is preparing for a SaaS launch, asks about pre-launch reviews, mentions launch readiness, OWASP audit, load testing, k6, Locust, GitHub Actions for SaaS, Lighthouse audit, RLS verification, post-deploy smoke tests, go-live checklist, or production launch — even if they don't explicitly say "launch readiness." If the user is in pre-launch territory and asks about CI/CD, monitoring, security, or testing for a SaaS product, fire this skill rather than generic dev tooling skills.
Run all remaining phases autonomously — discuss→plan→execute per phase
Review source files changed during a phase for bugs, security issues, and code quality problems
基于 SOC 职业分类
正在显示 SKILL.md
| name | gsd-health |
| description | Diagnose planning directory health and optionally repair issues |
--context runs an orthogonal check: the running session's context utilization. The workflow asks for the model's tokensUsed + contextWindow, calls gsd-sdk query validate.context, and renders one of three states:
| Utilization | State | Action |
|---|---|---|
| < 60% | healthy | no action — context is comfortable |
| 60% – 70% | warning | recommend /gsd-thread to start fresh |
| ≥ 70% | critical | reasoning quality may degrade past the fracture point |
<execution_context> @~/.gemini/antigravity/get-shit-done/workflows/health.md </execution_context>
Execute end-to-end. Parse `--repair` and `--context` flags from arguments and pass to workflow.