Menu
从 api.openalex.org 抽取学术作品：标题、URL、出版年份、DOI、类型
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
搜索学术论文（Semantic Scholar + DBLP + arXiv 三源并行），返回标题、作者、摘要、引用数、链接
从 api.crossref.org 抽取学术文献：标题、链接、DOI、摘要片段及引用数
搜索微信公众号文章并提取全文（通过 Sogou 微信搜索），返回标题、真实 URL、发布时间、正文内容
搜索近期新闻文章（NewsAPI + Google News RSS 双源回退），返回标题、来源、日期、摘要
抽取 hn_story：title、url、author、points、created_at
抽取 so_question：title、url、score、answer_count、tags
| name | openalex_work |
| description | 从 api.openalex.org 抽取学术作品：标题、URL、出版年份、DOI、类型 |
| layer | access |
| invocation | agent_called |
| entity_type | openalex_work |
| template | public_api |
| status | mined |
Search api.openalex.org — openalex_work. Returns raw JSON data instead of HTML; standard CSS selectors are invalid.
Agent-called skill — sub-agents invoke it as the typed tool skill_openalex_work(...). The dispatcher does not auto-route; the agent decides.
query (required) — The search query string (e.g., 'graph neural networks')per_page (default 3) — Number of results to return per pageAuto-generated by the access-skill baker (template: public_api). Hand-edit freely; the runtime only executes executor.py and reads params_schema from manifest.yaml.