SKILLS & AGENTS/Skill 与 Agent·MULTI-AGENT
nagisanzenin/production-grade
Claude Code Plugin: Fully autonomous production-grade SaaS pipeline — 14 bundled skills, CEO/CTO command-driven, single install
怎么装:Install: /plugin marketplace add nagisanzenin/claude-code-plugins
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+0.0%+0.0%
181 → 181 stars · 2 个快照181 → 181 stars · 2 snapshots
状态STATUS
持续活跃Active
03 / 它能帮你做什么03 / What it helps you do
04 / 安装04 / Install
$ README 里给出的安装方式。The installation method given in the README.
$ README 里给出的安装方式。The installation method given in the README.
两种装法选一个即可 —— 上面那条给命令行用户,下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.
05 / 限制与风险05 / Limits and risk
风险不是警告,是可信度的一部分。以下结论只基于文档静态扫描,我们不会执行项目里的任何代码。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读写本地文件Reads and writes local filesskills/devops/SKILL.md
- **Container security** — No root, read-only filesystem, no capabilities
02控制浏览器Controls a browserskills/frontend-engineer/SKILL.md
| Config | `frontend/` root | package.json, tsconfig, tailwind, eslint, playwright, lighthouse |
03控制浏览器Controls a browserskills/qa-engineer/SKILL.md
│ │ └── <user-flow>.spec.ts # Playwright / Cypress user flow specs
这里只做静态扫描:读 README、SKILL.md 和依赖清单,不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude-plugin/"
},
{
"agent": "codex",
"evidence": "readme: …ll natively on **Claude Code, OpenAI Codex, OpenCode, and Pi** — one sha…"
},
{
"agent": "opencode",
"evidence": "readme: …**Claude Code, OpenAI Codex, OpenCode, and Pi** — one shared core,…"
}
],
"apiKey": "deploy one binary, paste your API key, and control your server through chat.",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 2,
"dev-tools": 1,
"indie-web": 1,
"skill-agent": 1,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "multi-agent"
},
"localRuntime": null,
"skillMdTotal": 14,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 3,
"media": 0,
"design": 2,
"browser": 0,
"devtool": 1,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "14 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 67 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skills/code-reviewer/SKILL.md",
"skills/data-scientist/SKILL.md",
"skills/devops/SKILL.md",
"skills/frontend-engineer/SKILL.md",
"skills/polymath/SKILL.md",
"skills/product-manager/SKILL.md",
"skills/production-grade/SKILL.md",
"skills/qa-engineer/SKILL.md",
"skills/security-engineer/SKILL.md",
"skills/skill-maker/SKILL.md",
"skills/software-engineer/SKILL.md",
"skills/solution-architect/SKILL.md",
"skills/sre/SKILL.md",
"skills/technical-writer/SKILL.md"
],
"skillMdFetched": 14
}