Amazon Working Backwards PR/FAQ process — generate well-grounded professional documents for product discovery and decision-making.

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.

DSH 插件雷达：定时扫描 GitHub 上 topic:dsh-plugin 的新插件，在 DeepSeek Harness Web 界面左下角推送卡片流，支持 README 关键词搜索与一键安装。

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.