SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL

spellbook

majiayu000/spellbook

Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

怎么装：Install: npx skills add majiayu000/spellbook --skill frontend-design --skill app-ui-design --skill ui-design-system --skill figma-to-react

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%

287 → 287 stars · 2 个快照287 → 287 stars · 2 snapshots

状态STATUS

持续活跃Active

质量 B+Quality B+

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

SKILLS-CLI

$

README 里给出的安装方式。The installation method given in the README.

CURL-PIPE

$

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

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/majiayu000/spellbook
原始数据哈希Raw data hash: 4e479804c515b71b76eae599f00bf2e3
解析时间Parsed at: 2026-10-03T23:17:39.618Z
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:token:code:token-usage
分类来源Category source: rules
焦点Focus: design · web · token (5)

静态扫描STATIC SCAN

01执行远程脚本Runs a remote scriptreadme

curl -fsSL https://raw.githubusercontent.com/majiayu000/spellbook/main/install.sh | bash -s -- --target all

02控制浏览器Controls a browserreadme

| [`playwright-automation`](./skills/playwright-automation/) | Browser automation and testing with Playwright |

03执行 Shell 命令Runs shell commandsskills/clash-doctor/SKILL.md
```
allowed-tools: Bash
```
04读写本地文件Reads and writes local filesskills/clash-doctor/SKILL.md
```
allowed-tools: Write
```
05读写本地文件Reads and writes local filesskills/clash-doctor/SKILL.md
```
allowed-tools: Edit
```
06执行 Shell 命令Runs shell commandsskills/clash-routes/SKILL.md
```
allowed-tools: Bash
```
07控制浏览器Controls a browserskills/css-debug/SKILL.md
```
在浏览器控制台运行：
```

08读取 API KeyReads an API keyskills/devops-excellence/SKILL.md

**Never use long-lived static credentials. Always use OIDC or short-lived tokens.**

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": "claude-code",
      "evidence": "tree: .claude-plugin/"
    },
    {
      "agent": "claude-ai",
      "evidence": "readme: …lls/web-artifacts-builder/) | Claude.ai HTML artifacts | | [`react-be…"
    },
    {
      "agent": "codex",
      "evidence": "readme: …Spellbook versions installed Codex skills under `~/.codex/skills`; rein…"
    },
    {
      "agent": "vscode",
      "evidence": "readme: …tDesk connection issues | | [`vscode-doctor`](./skills/vscode-doct…"
    },
    {
      "agent": "gemini-cli",
      "evidence": "skills/ask-opencli/SKILL.md: …*: - User wants to use native Gemini CLI (`gemini -p`) → use `ask-gemi…"
    }
  ],
  "apiKey": "w AuthError('Invalid token', 'INVALID_TOKEN'); } } ``` --- ## Token Storage ##",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 2,
      "ai-tools": 0,
      "dev-tools": 5,
      "indie-web": 1,
      "skill-agent": 10,
      "productivity": 6
    },
    "primary": "skill-agent",
    "secondary": "claude-skill"
  },
  "localRuntime": "ally on Mac/Apple Silicon via llama.cpp or Ollama | | [`gpu-use`](./skills/gpu-",
  "skillMdTotal": 114,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 6,
    "media": 0,
    "design": 3,
    "browser": 0,
    "devtool": 5,
    "security": 0,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "60 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "skills/ directory with 321 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",
    "plugins/idea-coach/skills/idea-analogist/SKILL.md",
    "plugins/idea-coach/skills/idea-devils-advocate/SKILL.md",
    "plugins/idea-coach/skills/idea-research/SKILL.md",
    "plugins/idea-coach/skills/idea-team/SKILL.md",
    "plugins/idea-coach/skills/idea-to-product/SKILL.md",
    "plugins/spellbook-ui/skills/app-ui-design/SKILL.md",
    "plugins/spellbook-ui/skills/figma-to-react/SKILL.md",
    "plugins/spellbook-ui/skills/frontend-design/SKILL.md",
    "plugins/spellbook-ui/skills/ui-design-system/SKILL.md",
    "skills/agentsmd-optimize/SKILL.md",
    "skills/agentsmd-scaffold/SKILL.md",
    "skills/api-design/SKILL.md",
    "skills/app-ui-design/SKILL.md",
    "skills/app-user-story-qa/SKILL.md",
    "skills/architecture-foundation/SKILL.md",
    "skills/architecture-research/SKILL.md",
    "skills/ask-opencli/SKILL.md",
    "skills/auth-security/SKILL.md",
    "skills/blender-editable-3d/SKILL.md",
    "skills/blender-reference-to-3d/SKILL.md",
    "skills/build-product-demo/SKILL.md",
    "skills/capability-distill/SKILL.md",
    "skills/clash-doctor/SKILL.md",
    "skills/clash-routes/SKILL.md",
    "skills/claude-code-reverse/SKILL.md",
    "skills/cliproxy-newapi-stack/SKILL.md",
    "skills/codebase-audit/SKILL.md",
    "skills/codex-agent/SKILL.md",
    "skills/codex-fluent/SKILL.md",
    "skills/codex-log-guard/SKILL.md",
    "skills/codex-retrospective/SKILL.md",
    "skills/codex/SKILL.md",
    "skills/comprehensive-testing/SKILL.md",
    "skills/config-secrets-environments/SKILL.md",
    "skills/contribution-architect/SKILL.md",
    "skills/contributor/SKILL.md",
    "skills/css-debug/SKILL.md",
    "skills/data-contract-migrations/SKILL.md",
    "skills/database-patterns/SKILL.md",
    "skills/dev-architecture-playbook/SKILL.md",
    "skills/devops-excellence/SKILL.md",
    "skills/disk-cleaner/SKILL.md",
    "skills/elegant-architecture/SKILL.md",
    "skills/figma-to-code/SKILL.md",
    "skills/figma-to-react/SKILL.md",
    "skills/flowguard/SKILL.md",
    "skills/frontend-design/SKILL.md",
    "skills/gemma4-local-deploy/SKILL.md",
    "skills/git-commit-smart/SKILL.md",
    "skills/github-trending/SKILL.md",
    "skills/golang-web/SKILL.md",
    "skills/gpu-use/SKILL.md",
    "skills/harmonyos-app/SKILL.md",
    "skills/humanizer/SKILL.md",
    "skills/idea-analogist/SKILL.md",
    "skills/idea-devils-advocate/SKILL.md",
    "skills/idea-research/SKILL.md",
    "skills/idea-team/SKILL.md",
    "skills/idea-to-product/SKILL.md",
    "skills/illustrated-gallery/SKILL.md"
  ],
  "skillMdFetched": 60
}