Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readable. An Agent Skill for Claude Code & any SKILL.md-compatible agent.

DeepSeek Harness (DSH) academic writing guard for papers — 论文去AI味 / AI-writing style detection, evidence preservation, journal-fit calibration, manuscript proofreading, writing_audit & automatic checks. Local, zero network, zero LLM.

Evidence-based learning engine for Claude Code — first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable artifacts. Learn anything; keep it.

Evidence-based learning engine for OpenCode — learn anything, verify by free recall, schedule with FSRS, adapt from your own data.

An intent-calibrated DSH discussion mode that prevents complex conversations from drifting and turns them into evidence-based next steps.