markdown-browser
بواسطة 2233admin
Web & Frontend Developmentموجز
Wrapper skill for OpenClaw web_fetch results.
الوصف
ما الذي تفعله هذه المهارة
Post-processing wrapper for OpenClaw web_fetch results. Applies content policy decisions from Content-Signal headers, redacts sensitive path and query values from output URLs, and normalizes fetched content to markdown, HTML-fallback, or plain text. Outputs a stable schema for downstream agent logic without re-implementing network fetch.
Centralizes content policy, privacy redaction, and format normalization so individual agents don't each re-implement the same post-fetch logic.
متى تستخدمها
- Checking AI-input policy before feeding a fetched page into an LLM
- Stripping sensitive path and query values from URLs in agent logs
- Converting HTML responses to markdown for text-based agent pipelines
- Estimating token counts from fetched web content before processing
- Standardizing web fetch output schema across multiple agent tools
مثال على سير العمل
User asks: fetch this documentation page and extract key points, respecting content policies
- 1
Call OpenClaw web_fetch to retrieve the target page
- 2
Pass the result JSON and Content-Signal header to process_web_fetch_result
- 3
Check policy_action: proceed if 'allow_input', halt if 'block_input'
- 4
Use the normalized content field (markdown or text) for downstream summarization
- 5
Log source_url with sensitive values already redacted
Structured object with content, format, token_estimate, policy_action, and redacted source_url ready for agent consumption
التثبيت
clawhub install 2233admin/markdown-browserشغّل أمر واجهة سطر الأوامر، أو الصق النص في Claude Code أو Cursor أو Codex أو أي وكيل برمجة تستخدمه.