900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.
📖 Cross-agent research paper toolkit for Claude Code, Codex, OpenCode, and DeepSeek Harness—quick summaries, deep study materials, code demos, and a local web viewer.
dsh-excel-chat — talk to Excel in DeepSeek Harness: create, edit, repair, and verify spreadsheets by conversation (cells, formulas, styles, filters, tables, charts); every edit is auto-validated.
A DeepSeek Harness (DSH) agent preset that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style. 学习模式
DSH Math Modeling Team Plugin Pack: 2 role agent presets (modeling-coding / paper) for DeepSeek Harness, multi-folder Git collaboration + vision sub-agent; includes a full run on 2023 CUMCM-C. | DeepSeek Harness 数学建模团队插件包:2 套岗位Agent预设(建模编程+论文)、多文件夹协同+识图子代理,含2023国赛C题全流程跑通示例。
Paper → academic talk for DeepSeek Harness: reads the real full text, budgets the slot per venue (组会汇报/会议报告/答辩/开题/文献汇报), builds the deck around the figures and writes the speaker notes as the script. Drives dsh-ai4scholar + dsh-slides.