Evidence-first reading for AI agents — turn articles, books and PDFs into traceable claims, evidence, source locations and knowledge maps.

Agent Skill: make Claude write in Barbara Minto's Pyramid Principle - answer first, grouped reasons, evidence under each.

Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback.

Agent Skills for working UX designers. Challenge ideas, find blind spots, use the real design system, preserve evidence and decisions, and carry UX intent into engineering.

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

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable specs and evidence in your repo. Works with Claude Code, Codex, Gemini, OpenCode, and plain CLI.

Open-source Agent Skills for planning, drafting, revising, and polishing SCI/SSCI papers—while preserving evidence, citations, and claim strength.

Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-first methods, powered by TypeScript and Bun.

汇报.skill · pitchcraft — Structured persuasion for tech leads, PMs, and founders: kickoff, status, wrap-up, pitch, and solution selling on one 5-part framework (Hook→Context→Proposal→Evidence→Ask), with AI material intake and a pre-submit checklist. Works with Claude Code, Cursor, Codex, and more.

ffprobe for documents — probe PDF, Microsoft Office, and Apple iWork files without opening them. Rust CLI + browser WASM SDK returning structured JSON with confidence, evidence, and measured I/O cost.

MCP server for predictive maintenance and machinery fault diagnosis. Gives AI assistants evidence-based vibration analysis - FFT, envelope, bearing fault detection, ISO 20816-3 severity - with a measured, blind CWRU benchmark. Local-first: raw signals never leave your machine. Includes a Claude Code plugin.

GPS-aligned AI prompts and Agent Skills for genealogical research (CC-BY-NC-SA-4.0)

The automated approach leverages the cross-combination of high-quality papers from top conferences to uncover feasible research and innovation ideas. Through multi-level verification and convergence screening, it identifies research schemes that are feasible and have in-depth value.

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.