技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 0 · 369 · 1 current installs · 1 all-time installs
⭐ 0
安装量（当前） 1
🛡 VirusTotal ：可疑 · OpenClaw ：可疑
Package：2233admin/markdown-browser
安全扫描（ClawHub）
- VirusTotal ：可疑
- OpenClaw ：可疑
OpenClaw 评估
The skill's code and instructions match its stated purpose (post-processing web_fetch results), but the included package lock references non-standard package tarball hosts which makes the install step potentially risky.
目的
Name/description describe a wrapper for OpenClaw web_fetch; the included browser.js implements exactly that: parsing Content-Signal, redacting URL parts, converting HTML→Markdown, and producing a stable JSON schema. It does not request unrelated credentials or access.
说明范围
SKILL.md confines runtime behavior to: accept a web_fetch payload, optional header values, and run local normalization/redaction. The instructions explicitly forbid making direct HTTP fetches and the code follows that. It reads only the provided web_fetch JSON (stdin or file) and prints normalized JSON.
安装机制
The package is instruction-only in the registry, but runtime/README recommend running 'npm install' to obtain 'turndown'. The shipped package-lock.json contains resolved tarball URLs pointing at mirrors.tencentyun.com (a third-party mirror) rather than the default npm registry or a well-known release host. That makes the install step higher risk because it could cause code to be fetched from an unexpected host. There is no explicit install spe…
证书
The skill declares no required environment variables or credentials and the code does not access environment secrets or external configs. It only reads a provided web_fetch JSON and optional header strings.
持久
The skill is not always-enabled and does not request system-level persistence or modify other skills/config. It only runs as a wrapper when invoked; nothing in the package attempts to alter agent configuration.
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Markdown Browser」。简介：Wrapper skill for OpenClaw web_fetch results. Use when you need MECE post-proce…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/2233admin/markdown-browser/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: markdown-browser
description: "Wrapper skill for OpenClaw web_fetch results. Use when you need MECE post-processing on fetched pages: policy decision from Content-Signal, privacy redaction, optional markdown normalization fallback, and stable output schema without re-implementing network fetch."
---
# Markdown Browser Skills
This skill is an orchestration layer, not a replacement fetcher. It always keeps official `web_fetch` as the fetch source of truth.
## MECE Architecture
1. Fetch layer (official, exclusive)
- Use OpenClaw `web_fetch` to retrieve the page.
- Do not call direct HTTP fetch inside this skill for normal operation.
2. Policy layer (these skills)
- Parse `Content-Signal` and compute `policy_action`.
- Current action focuses on `ai-input` semantics: `allow_input`, `block_input`, `needs_review`.
3. Privacy layer (these skills)
- Redact path/fragment/query values in output URL fields.
- Keep URL shape useful for debugging without leaking sensitive values.
4. Normalization layer (these skills)
- If `contentType=text/markdown`, keep content as-is.
- If `contentType=text/html`, convert with `turndown` as fallback enhancement.
- For other content types, pass through text.
## Execution Order
1. Call official `web_fetch`.
2. Pass the result JSON into this wrapper.
3. Optionally pass `Content-Signal` and `x-markdown-tokens` header values if available.
4. Use the returned normalized object for downstream agent logic.
## Wrapper Tool
`process_web_fetch_result({ web_fetch_result, content_signal_header, markdown_tokens_header })`
Input:
- `web_fetch_result` (required): JSON payload returned by OpenClaw `web_fetch`.
- `content_signal_header` (optional): raw `Content-Signal` header string.
- `markdown_tokens_header` (optional): raw `x-markdown-tokens` header value.
Output:
- `content`
- `format` (`markdown` | `html-fallback` | `text`)
- `token_estimate` (`number | null`)
- `content_signal`
- `policy_action`
- `source_url` (redacted)
- `status_code`
- `fallback_used`
## CLI Usage
```bash
# Install runtime dependency once inside the skill directory
npm install --omit=dev
# 1) Obtain a web_fetch payload first (from OpenClaw runtime)
# 2) Save it as /tmp/web_fetch.json
# 3) Run wrapper post-processing
node browser.js
--input /tmp/web_fetch.json
--content-signal "ai-input=yes, search=yes, ai-train=no"
--markdown-tokens "1820"
```