SKILLS & AGENTS/Skill 与 Agent·MULTI-AGENT

codexkit

manhvann/codexkit

Project-local Codex workspace kit with reusable skills, agents, hooks, plans, docs, and helper scripts for multi-repository development.

打开仓库Open repository

怎么装：Install: npm install -g @manhnv319/codexkit

02 / 现在的位置02 / Why now

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

+0.0%+0.0%

90 → 90 stars · 2 个快照90 → 90 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

它能帮你做成什么What it helps you do

04 / 安装04 / Install

怎么装How to install

NPM

$

Node 用户的安装方式。The install route for Node users.

NPM

$

Node 用户的安装方式。The install route for Node users.

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

限制与风险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

存在风险Risk found

01需要 API KeyREQUIRES API KEY: 是Yes
02需要本地环境NEEDS LOCAL RUNTIME: 是Yes
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 需要本地环境Needs a local runtime

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/manhvann/codexkit
原始数据哈希Raw data hash: 840618e794861716a814a31287c2c326
解析时间Parsed at: 2026-10-03T23:24:19.938Z
最后一次验证Last verified: 2026-10-04T08:53:33.891Z
增长测量时间Growth measured: 2026-10-03T23:24:59.911Z
发现查询Discovery queries: focus:motion:code:threejs
分类来源Category source: rules
焦点Focus: motion (3)

静态扫描STATIC SCAN

01执行远程脚本Runs a remote script.agents/skills/gkg/SKILL.md

curl -fsSL https://gitlab.com/gitlab-org/rust/knowledge-graph/-/raw/main/install.sh | bash

02控制浏览器Controls a browser.agents/skills/agent-browser/SKILL.md

Browser automation CLI designed for AI agents. Uses "snapshot + refs" paradigm for 93% less context than Playwright MCP.

03执行 Shell 命令Runs shell commands.agents/skills/ai-multimodal/SKILL.md
```
allowed-tools: Bash
```
04读写本地文件Reads and writes local files.agents/skills/ai-multimodal/SKILL.md
```
allowed-tools: Write
```
05读写本地文件Reads and writes local files.agents/skills/ai-multimodal/SKILL.md
```
allowed-tools: Edit
```
06读取 API KeyReads an API key.agents/skills/better-auth/SKILL.md
```
clientSecret: process.env.GITHUB_CLIENT_SECRET!,
```

07控制浏览器Controls a browser.agents/skills/chrome-devtools/SKILL.md

Browser automation via Puppeteer scripts with persistent sessions. All scripts output JSON.

08读取 API KeyReads an API key.agents/skills/docs-seeker/SKILL.md

Scripts load `.env`: `process.env` > `.agents/skills/docs-seeker/.env` > `.agents/skills/.env` > `.codex/.env`

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.

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "codex",
      "evidence": "tree: .codex/"
    },
    {
      "agent": "gemini-cli",
      "evidence": ".agents/skills/mcp-management/SKILL.md: …red in `.codex/.mcp.json`. **Gemini CLI Integration** (recommended):…"
    },
    {
      "agent": "opencode",
      "evidence": ".agents/skills/scout/SKILL.md: …: Scout using external Gemini/OpenCode CLI tools in parallel (`./ref…"
    }
  ],
  "apiKey": "rowser profile directory | | `BROWSERBASE_API_KEY` | Browserbase API key | | `BROWSERBASE",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 0,
      "dev-tools": 1,
      "indie-web": 0,
      "skill-agent": 1,
      "productivity": 0
    },
    "primary": "skill-agent",
    "secondary": "multi-agent"
  },
  "localRuntime": "-preview` Also: OpenAI Codex, Ollama, LiteLLM, vLLM, Model Garden ## Best P",
  "skillMdTotal": 68,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 0,
    "media": 0,
    "design": 1,
    "browser": 0,
    "devtool": 2,
    "security": 1,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "60 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    }
  ],
  "scannedSources": [
    "readme",
    ".agents/skills/agent-browser/SKILL.md",
    ".agents/skills/ai-artist/SKILL.md",
    ".agents/skills/ai-multimodal/SKILL.md",
    ".agents/skills/ask/SKILL.md",
    ".agents/skills/backend-development/SKILL.md",
    ".agents/skills/better-auth/SKILL.md",
    ".agents/skills/bootstrap/SKILL.md",
    ".agents/skills/brainstorm/SKILL.md",
    ".agents/skills/chrome-devtools/SKILL.md",
    ".agents/skills/ck-help/SKILL.md",
    ".agents/skills/code-review/SKILL.md",
    ".agents/skills/coding-level/SKILL.md",
    ".agents/skills/context-engineering/SKILL.md",
    ".agents/skills/cook/SKILL.md",
    ".agents/skills/copywriting/SKILL.md",
    ".agents/skills/databases/SKILL.md",
    ".agents/skills/debug/SKILL.md",
    ".agents/skills/devops/SKILL.md",
    ".agents/skills/docs-seeker/SKILL.md",
    ".agents/skills/docs/SKILL.md",
    ".agents/skills/docx/SKILL.md",
    ".agents/skills/find-skills/SKILL.md",
    ".agents/skills/fix/SKILL.md",
    ".agents/skills/frontend-design/SKILL.md",
    ".agents/skills/frontend-development/SKILL.md",
    ".agents/skills/git/SKILL.md",
    ".agents/skills/gkg/SKILL.md",
    ".agents/skills/google-adk-python/SKILL.md",
    ".agents/skills/journal/SKILL.md",
    ".agents/skills/kanban/SKILL.md",
    ".agents/skills/markdown-novel-viewer/SKILL.md",
    ".agents/skills/mcp-builder/SKILL.md",
    ".agents/skills/mcp-management/SKILL.md",
    ".agents/skills/media-processing/SKILL.md",
    ".agents/skills/mermaidjs-v11/SKILL.md",
    ".agents/skills/mintlify/SKILL.md",
    ".agents/skills/mobile-development/SKILL.md",
    ".agents/skills/payment-integration/SKILL.md",
    ".agents/skills/pdf/SKILL.md",
    ".agents/skills/plan/SKILL.md",
    ".agents/skills/plans-kanban/SKILL.md",
    ".agents/skills/pptx/SKILL.md",
    ".agents/skills/preview/SKILL.md",
    ".agents/skills/problem-solving/SKILL.md",
    ".agents/skills/project-management/SKILL.md",
    ".agents/skills/react-best-practices/SKILL.md",
    ".agents/skills/remotion/SKILL.md",
    ".agents/skills/repomix/SKILL.md",
    ".agents/skills/research/SKILL.md",
    ".agents/skills/scout/SKILL.md",
    ".agents/skills/sequential-thinking/SKILL.md",
    ".agents/skills/shader/SKILL.md",
    ".agents/skills/shopify/SKILL.md",
    ".agents/skills/skill-creator/SKILL.md",
    ".agents/skills/tanstack/SKILL.md",
    ".agents/skills/team/SKILL.md",
    ".agents/skills/template-skill/SKILL.md",
    ".agents/skills/test/SKILL.md",
    ".agents/skills/threejs/SKILL.md",
    ".agents/skills/ui-styling/SKILL.md"
  ],
  "skillMdFetched": 60
}