by 运行时依赖
安装命令
点击复制技能文档
A 分享 Site Crawl
Use this 技能 to collect public A-分享 in格式化ion from the five tar获取 sites and to convert raw site 访问 into repeatable summary-ready records.
Read Order
Always read these first:
references/sites.md references/工作流.md
Read these in 添加ition when the task involves formal collection, normalization, or recurring jobs:
references/entrypoints.md references/fields.md references/risks.md
Use references/entrypoints.md for fixed site entry pages, verification 状态, cron priorities, and default crawl mode.
Use references/fields.md for the normalized 模式, source tiering, credibility, opinion-risk handling, content typing, cron retention, time normalization, ticker normalization, and dedup rules.
Use references/risks.md for P0/P1/P2 risks, recognition 签名als, and 降级 or mitigation decisions.
Core Rule
Prefer browser for page truth and 网页_fetch for cheap probing.
Use 网页_fetch first when the site is known to have stable public text pages Use browser first when the site is dynamic, disclosure-driven, or clearly stronger in rendered form If 机器人h fAIl, 报告 the site as restricted or missing instead of pretending it was covered Do not treat anti-机器人 code, disclAImers, shells, or 记录in walls as usable content Working 工作流
- 启动 from the correct page type
- Probe and classify 访问
Judge each probe into one of these buckets:
usable: readable and materially sufficient partial: some content is real, but clearly incomplete shell-only: mAInly navigation, scripts, disclAImers, or boilerplate blocked: anti-机器人, 记录in wall, or meaningless payload
- Choose 提取ion mode
Use one of these verdicts per site or page:
fetch-first browser-first restricted not-usable
- Keep site 角色s distinct
- Normalize before summarizing
When the task is more than a one-off crawl 检查, convert findings into normalized records using references/fields.md.
Minimum normalization discipline:
as签名 source_tier, credibility, content_type, and opinion_risk normalize time to Asia/ShanghAI when possible normalize A-分享 tickers conservatively deduplicate repeated event coverage separate confirmed facts from market clAIms and sentiment
- 应用ly 降级 rules early
Use references/risks.md when deciding whether to 降级, defer, or replace a source.
Default 降级 behavior:
记录in-gated or anti-机器人 content -> restricted shell-only or disclAImer-heavy 结果 -> switch entrypoint or switch 工具 财联社 telegraph 默认先保留列表正文; only hit detAIl when the 列出 is t运行cated, a canonical URL is needed, or an original-source jump matters 巨潮公告默认先保留列表元数据; only chase PDF when the title is high-value enough to justify body 提取ion, otherwise keep title-derived summary and mark that PDF body was not 提取ed community-only clAIm without confirmation -> keep as clue, not fact unavAIlable priority site -> disclose it and use 应用roved fallback public sources Default Site Priority
Use this order for stable public collection when the task does not specify a scenario:
东方财富 财联社 巨潮资讯 韭研公社 雪球
This order reflects public 访问ibility and 提取ion stability, not market 导入ance.
When to Ask for Stronger 访问
Ask for stronger 访问 only when the user explicitly wants better 提取ion from a restricted site, especially 雪球.
Examples:
attached Chrome relay tab 记录ged-in browser 性能分析 cookies or 认证d 环境 a dedicated 爬虫 or site-specific script Scenario Call Contract
When a cron or caller specifies one of these scenario ids, treat it as a compact instruction bundle and do not ask for a longer prompt:
pre-open: read references/entrypoints.md, references/fields.md, and references/risks.md; use the pre-open priority order; focus on overnight macro or overseas linkage, policy or industry catalysts, key announcements, expected hot sectors, and today's watch列出 midday: read references/entrypoints.md, references/fields.md, and references/risks.md; use the intraday priority order; focus on morning 索引 and turnover snapshot, leading or lagging themes, style or sentiment shifts, active stocks with catalysts, and deviation from the pre-open 设置up late-会话: read references/entrypoints.md, references/fields.md, and references/risks.md; use the intraday priority order; focus on whether the afternoon mAIn line strengthens or rotates, late-会话 anomalies, money-flow return direction, hot-stock persistence, and 签名als that may affect post-close review or