SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL

my-skills

akitaonrails/my-skills

akitaonrails' personal skills (not tailored for general usage)

打开仓库Open repository

怎么装：Install: npm i -g agent-browser@latest

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

+1.5%+1.5%

201 → 204 stars · 2 个快照201 → 204 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

需检查Needs review

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

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

来源 URLSource URL: https://github.com/akitaonrails/my-skills
原始数据哈希Raw data hash: 99ee3849795296b35a7ec0a3af84fdb6
解析时间Parsed at: 2026-10-03T23:19:31.683Z
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:design:code:ui-ux
分类来源Category source: rules
焦点Focus: design (4)

静态扫描STATIC SCAN

01控制浏览器Controls a browseragent-browser/SKILL.md

Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with accessibility-tree snapshots and compact `@eN` element refs.

02执行 Shell 命令Runs shell commandsagent-browser/SKILL.md
```
allowed-tools: Bash(agent-browser:*)
```
03控制浏览器Controls a browseragent-browser/SKILL.md
```
allowed-tools: Bash(agent-browser:*)
```
04执行 Shell 命令Runs shell commandsagent-browser/SKILL.md
```
allowed-tools: Bash(npx
```

05读写本地文件Reads and writes local filespr-audit/SKILL.md

- network calls, telemetry, credential access, environment reads, filesystem

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": "readme: …links | | --- | --- | --- | | Claude Code | `~/.claude/skills` | per-sk…"
    },
    {
      "agent": "claude-ai",
      "evidence": "readme: …kill-creator, docs, pdf, …) | claude.ai cloud sync | `~/.claude/skill…"
    },
    {
      "agent": "codex",
      "evidence": "readme: …restart opencode | | opencode-openai-codex-auth | npm | opencode plugin…"
    },
    {
      "agent": "opencode",
      "evidence": "readme: …lls` | per-skill symlinks | | opencode | `~/.config/opencode/skills`…"
    },
    {
      "agent": "windsurf",
      "evidence": "agent-browser/SKILL.md: …Claude Code, Codex, Continue, Windsurf, etc.) - Chrome/Chromium via…"
    },
    {
      "agent": "vscode",
      "evidence": "agent-browser/SKILL.md: …# Electron desktop apps (VS Code, Slack, Discord, Figma, ...)…"
    }
  ],
  "apiKey": "ither. Read them with `env -u GITHUB_TOKEN gh api ...` — a limited session token l",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 2,
      "dev-tools": 2,
      "indie-web": 1,
      "skill-agent": 2,
      "productivity": 0
    },
    "primary": "skill-agent",
    "secondary": "claude-skill"
  },
  "localRuntime": null,
  "skillMdTotal": 23,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 0,
    "media": 0,
    "design": 2,
    "browser": 0,
    "devtool": 2,
    "security": 0,
    "marketing": 0,
    "productivity": 1
  },
  "classification": [
    {
      "signal": "23 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    },
    {
      "signal": "name contains 'skill'",
      "weight": 0.4
    }
  ],
  "scannedSources": [
    "readme",
    "agent-browser/SKILL.md",
    "blog-cost-charts/SKILL.md",
    "clonedeps/SKILL.md",
    "codemap/SKILL.md",
    "deepwork/SKILL.md",
    "effect/SKILL.md",
    "fact-check/SKILL.md",
    "github-resolution/SKILL.md",
    "humanizer/SKILL.md",
    "improve-codebase-architecture/SKILL.md",
    "iss-audit/SKILL.md",
    "loop-engineering/SKILL.md",
    "post-refactor/SKILL.md",
    "pr-audit/SKILL.md",
    "pr-bump/SKILL.md",
    "pr-post-audit/SKILL.md",
    "reflect/SKILL.md",
    "release-smoke-test/SKILL.md",
    "release/SKILL.md",
    "security-audit/SKILL.md",
    "simplify/SKILL.md",
    "verification-planning/SKILL.md",
    "worktrees/SKILL.md"
  ],
  "skillMdFetched": 23
}