القائمة
When the user wants to research academic papers → search ArXiv, extract PDFs, summarize/review/Q&A, generate experiment code.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
When prompt, tool, or agent logic changes need regression testing → run eval benchmarks to detect regressions or improvements.
When a task can be parallelized (bulk code review, multi-module refactor, batch analysis) → split into subtasks running in isolated git worktrees via multiple workers.
When you need to interact with web pages using the user's logged-in browser → control Chrome via @playwright/cli daemon, reusing cookies/session with persistent tabs.
When user needs AnyGenIO content generation → unified CLI for task execution with progressive disclosure.
When you need to persist files (reports, docs, evidence) beyond the session → create/query/delete durable artifacts.
When the user wants text-to-speech audio → generate voice files locally (macOS say + afconvert, outputs m4a).
| name | openseed |
| description | When the user wants to research academic papers → search ArXiv, extract PDFs, summarize/review/Q&A, generate experiment code. |
| triggers | {"intent_patterns":["openseed|论文|paper|arxiv|学术|research.*paper|文献|调研.*论文|survey","最新.*研究|latest.*research|state.*of.*art|SOTA","引用.*论文|cite.*paper|参考文献|bibliography|reference","读.*论文|read.*paper|论文.*摘要|abstract|论文.*总结","对比.*论文|compare.*papers|文献.*综述|literature.*review","实验.*复现|reproduce|代码.*实现|implementation","这篇.*论文|this.*paper|帮我找.*paper|search.*paper"],"context_signals":{"keywords":["openseed","paper","arxiv","论文","文献","survey","research","SOTA","引用","摘要","综述","复现","实验"]},"confidence_threshold":0.65} |
| priority | 9 |
| requires_tools | ["bash"] |
| max_tokens | 200 |
| cooldown | 30 |
| capabilities | ["research","paper_search","summarization","analysis"] |
| activation_mode | explicit |
| output | {"format":"markdown","artifacts":false} |
AI-powered research CLI — 论文检索、摘要、评审、问答、实验代码生成。
openseed paper search "diffusion models"openseed agent search "multi-agent systems"openseed agent pipeline "ViT image classification"openseed agent summarize <id> / openseed agent review <id>openseed agent ask "What is RLHF?"openseed agent codegen <id># 搜索论文（按引用数排序）
openseed paper search "attention" --count 20
# 添加论文到本地库
openseed paper add https://arxiv.org/abs/1706.03762
# AI 摘要（支持 --cn 中文）
openseed agent summarize <id>
# 研究问答
openseed agent ask "What is RLHF?"
# 一键调研流水线
openseed agent pipeline "ViT image classification"
pip install openseedANTHROPIC_API_KEY 或 claude setup-tokenopenseed doctor 检查环境，openseed setup 配置认证