Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/clawcap/manobrowser/api-skill-buildernpx skills add ClawCap/ManoBrowser --skill api-skill-buildergit clone --depth 1 https://github.com/ClawCap/ManoBrowserWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00099 | $0.05837 |
| Opus 5 | $0.00049 | $0.02919 |
| Sonnet 5 | $0.00020 | $0.01167 |
| Haiku 4.5 | $0.00010 | $0.00584 |
Grade A, and why
api-skill-builder scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **本地验证**:`document.cookie` 仅用于本地 `curl` 命令测试 API 鉴权机制,不会上传至任何外部服务 How it starts
The opening of the file, as written. The whole thing — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API 取数 Skill 生成器
安全声明
本模块的 Cookie 提取和 API 测试功能遵循以下安全原则:
- 本地验证:
document.cookie仅用于本地curl命令测试 API 鉴权机制,不会上传至任何外部服务 - 用户授权:所有操作仅作用于用户已登录的平台,需用户明确触发
- 合法用途:适用于开发调试、数据导出、自动化测试等场景,用户需确保符合目标平台的使用条款
概述
这是一个元技能(Meta-skill),将"逆向网页API并生成可复用取数Skill"的方法论封装为标准流程。
核心思路:页面上能看到的数据,一定来自某个 API 请求。找到 API → 逆向参数 → 生成可复用 Skill。
输入:用户描述要从某个网页/平台获取什么数据 输出:一个完整的、可复用的 API 取数 Skill(SKILL.md + Python 脚本 + api_mapping.json)
前置条件
- 浏览器已登录目标平台,登录态有效
- DataSaver Chrome 扩展已安装并连接(提供
fetch_api等工具) - MCP 端点已配置
设计原则
- 逻辑尽量收敛到 Python 脚本:脚本可独立测试、可维护,SKILL.md 保持精简
- SKILL.md 控制在 500 行以内:超过后 Claude 执行步骤时遗漏/出错概率显著上升
- Claude 只做调度员:参数收集 + 执行脚本 + 转述输出,不参与数据处理
- 所有数据处理由脚本完成:避免 LLM 截断数据或产生幻觉
执行流程(5个阶段)
阶段0: 鉴权探测(确定 Cookie 是否够用)
↓
阶段1: 侦察(找到 API endpoint)
↓
阶段2: 逆向(破解请求参数)
↓
阶段3: 验证(确认数据完整性 + 发现转换规则)
↓
阶段4: 生成(产出 Skill 三件套)
阶段0: 鉴权探测 — 确定 Cookie 可用性
目标:确认 document.cookie 能否独立完成 API 鉴权,这决定了脚本是否能直接调用 API。
Step 0.1: 提取 document.cookie
// chrome_execute_script, world: MAIN, tabId: <目标页面>
() => document.cookie
记录 Cookie 内容,识别可能的鉴权 token(如 sso.token、access-token、User、sessionid 等)。
Step 0.2: 找到一个数据 API endpoint
通过 Performance API 快速找一个数据 API(详见阶段1 Step 1.2),用于鉴权测试。
Step 0.3: curl 鉴权测试
MCP 工具走 Chrome 网络栈,会在底层自动附加 httpOnly cookie,即使设置 includeCookies: false 或传入假 Cookie 也无效,导致鉴权测试结果永远成功,产生误判。
curl 是完全独立于浏览器的 HTTP 客户端,只发送你显式传入的 Cookie,是唯一可靠的验证方式。
curl -s -X <METHOD> \
-H "Cookie: <Step 0.1 提取的 document.cookie>" \
-H "Content-Type: application/json" \
-H "User-Agent: Mozilla/5.0" \
"<API_URL>" [-d '<request_body>'] \
| python3 -c "import json,sys; d=json.load(sys.stdin); print(json.dumps({
'status': d.get('status', d.get('code', d.get('Code'))),
'msg': d.get('msg', d.get('Msg', ''))
}, ensure_ascii=False))"
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 497 lines · 99 tokens per session scan A 6c52733b6ee7
api-skill-builder is a skill published in the GitHub repository ClawCap/ManoBrowser (9 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 5,837 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
xiaohongshu-ops
把 Hermes Agent 变成你的小红书运营助手 — 首页分析、账号诊断、选题灵感、内容创作、自动发布、评论回复、爆款复刻、知识库沉淀。全链路 SOP 覆盖,基于浏览器自动化(CDP)。.
wcag22-a11y-audit
WCAG 2.2 Accessibility Audit skill that systematically evaluates web pages against 8 core Success Criteria (1.1.1, 1.4.3, 1.4.11, 2.1.1, 2.1.2, 2.4.3, 2.4.7, 4.1.2) using accessibility tree inspection and visual analysis. Use this skill when you need to perform accessibility testing/auditing on a live webpage.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends AIPex's capabilities with specialized knowledge, workflows, or tool integrations.
ux-audit-walkthrough
Minimalist UX/Interaction Audit Expert that deconstructs complex interactions through cognitive load and operational efficiency lenses. Use this skill when you need to perform a UX walkthrough audit on a Figma prototype or web interface, evaluating usability based on principles like fewer clicks, less UI elements, no…
aipex-browser
AI-powered browser automation using the AIPex Chrome Extension via MCP bridge. Use this skill when the agent needs to control a Chrome browser — navigating pages, clicking elements, filling forms, capturing screenshots, managing tabs, or downloading content — by connecting to the AIPex MCP bridge.
build-plugin
Complete plugin development workflow: build, test, icon, troubleshoot, and setup. Use when the user wants to build a plugin, create a plugin, troubleshoot issues, add icons, or install/configure plugins. Triggers on: build plugin, create plugin, develop plugin, new plugin, plugin icon, troubleshoot, debug, setup…