Projects | Sau-Chin Chen's Website

Claude Lit Workflow

Thu, 09 Jul 2026 00:00:00 +0000

This repository now hosts Claude Lit Workflow, a literature-processing toolkit that generates academic slides and Zettelkasten atomic notes directly from a PDF, a URL, or a topic, outputting plain Markdown that imports cleanly into Obsidian and similar note-taking apps. It can be driven through a CLI, an MCP server (stdio or Streamable HTTP), or an Obsidian QuickAdd wrapper.

Two generators sit at its core: a slide generator that supports seven academic styles, five levels of detail, and three languages, producing Obsidian Slides/Marp-compatible Markdown or PPTX; and a Zettelkasten card generator that produces atomic, cross-paper-linkable notes for knowledge-base integration. It supports multiple LLM providers, including Google Gemini, OpenAI, Anthropic, Ollama, and NVIDIA NIM, selectable per run.

The project is written in Python, installed and run with uv, and documents its behavior specs under openspec/ following a spec-driven development process.

Status: Active — under regular maintenance, currently at version 0.12.0.

TWCC Ollama Proxy

Sun, 28 Jun 2026 00:00:00 +0000

TWCC Ollama Proxy forwards local Ollama API requests to a TWCC (Taiwan Computing Cloud) development-type container (CCS) for LLM inference, exposing an endpoint at localhost:11434 that is API-compatible with standard Ollama. It currently supports the CrystalMind and GemmaPro GGUF models, with a reasoning-tuned GemmaPro-r variant for more complex extraction tasks.

Any tool that lets you point at a custom Ollama URL, such as Open WebUI or Continue.dev, can connect to it directly. Each API call spins up a TWCC CCS container with one GPU, runs the requested inference, and tears the container down afterward, so cost is billed only for the container’s short lifetime (typically one to two minutes per call). Setup requires a Windows machine, Python 3.10+ managed with uv, a TWCC account with CCS access, and an uploaded SSH key; model files are staged once on TWCC’s shared HFS storage.

Status: Active — under regular maintenance.

LSJ 2026 Lecture Slides

Tue, 16 Jun 2026 00:00:00 +0000

This repository collects the lecture slides for the 2026 basic statistics course taught at Tzu-Chi University’s Department of Human Development, published as a browsable Traditional Chinese slide-deck site.

The slides are aimed at students taking the course, giving them an always-available online reference to the semester’s lecture material alongside classroom instruction.

Status: Active — updated over the course of the 2026 teaching term.

Learning Statistics with jamovi (Traditional Chinese Translation)

Thu, 04 Jun 2026 00:00:00 +0000

This repository contains the Traditional Chinese translation source for Learning Statistics with jamovi: A Tutorial for Psychology Students and Other Beginners by Danielle Navarro and David Foxcroft, itself an adaptation of Navarro’s earlier Learning Statistics with R. The book is built from Quarto (.qmd) source files and renders to HTML, PDF, and EPUB.

The translation is intended for Chinese-speaking psychology students and instructors who want a free, open introductory statistics textbook that pairs with jamovi rather than R. In principle the repository contains everything needed to rebuild the book from scratch, and the rendered site is published online for direct reading.

The book is released under a CC BY-SA 4.0 license, so it can be reused, remixed, and redistributed, including commercially, as long as appropriate credit is given and derivative versions carry the same license.

Status: Active — under regular maintenance.

P-CSO: Pinker's Cognitive Style Optimization for Academic Writing

Fri, 22 May 2026 00:00:00 +0000

P-CSO (Pinker’s Cognitive Style Optimization) is a Claude Code skill set for academic writing, built around the sentence-level and paragraph-level principles from Chapters 4 and 5 of Steven Pinker’s The Sense of Style. It aims to reduce the cognitive burden a text places on its reader by improving syntax clarity and paragraph coherence.

The system ships six skills covering a full drafting workflow: p-cso-workflow runs the complete pipeline from notes to optimized draft, pinker-syntax and pinker-coherence apply the sentence- and paragraph-level rules individually, pinker-quick gives fast feedback during active drafting, notes-to-manuscript scaffolds structured drafts from raw notes, and english-editing handles final grammar and article-usage polish. It installs either through the Claude Code plugin marketplace or by placing the skill files locally in a project.

Every skill returns a diagnostic report explaining what was changed and why, so the writer can learn to apply the same principles unassisted in future drafts, rather than treating the tool as a black box.

Status: Active — currently version 0.9.0 (preview), under regular development.

ACT_Base: Annotation-Connection-Thought Workflow for Obsidian

Fri, 24 Apr 2026 00:00:00 +0000

ACT_Base is a minimal Obsidian vault that demonstrates the Annotation → Connection → Thought (ACT) knowledge workflow, driven by Claude Code skills run from a terminal inside Obsidian. Users drop in atomic Zettelkasten cards generated from papers, then run dedicated skills to turn isolated cards into a cross-paper knowledge network.

The vault organizes twelve skills across three layers: Annotation (card-review, gear-coaching, cross-link, monitor), Connection (gear-aggregate, framework-synthesize, query, tension-resolve), and Thought (provenance-audit, refine, question-assess, question-challenge). It ships with three pre-loaded demo annotations and a video walkthrough covering setup through the first Connection note. It is designed to pair with the claude_lit_workflow repository, which can generate the atomic cards from source PDFs, and with the lean-obsidian-terminal community plugin for running Claude Code inside Obsidian.

Status: Active — under regular maintenance.

Annotation_Blank (miniverse)

Tue, 21 Apr 2026 00:00:00 +0000

Annotation_Blank, internally named miniverse, is a minimal Obsidian vault for converting academic PDFs into structured Annotation notes using AI. It strips down the author’s full Program_verse workflow to a single pipeline: drop a PDF into the vault, run three commands from an ALT+L menu inside Obsidian, and get a fully formed Annotation note with 20 atomic Zettelkasten cards.

The three steps generate a Markdown slide outline from the PDF, generate 20 atomic cards from that outline, and import both into an Author-Year Annotation note under the vault’s ACT folder structure. It depends on the claude_lit_workflow repository as its AI backend, on the QuickAdd and Templater Obsidian plugins for the menu, and on at least one LLM API key (Gemini, OpenAI, or Anthropic). It is one piece of the author’s broader CSC PKM system, which also includes ACT_Base for note templates and twcc-ollama-proxy for local inference.

Status: Active — under regular maintenance.

Justify Your Alpha

Sun, 09 Feb 2025 00:00:00 +0000

This project responds to the widely discussed proposal by Benjamin et al. (2018, Nature Human Behaviour) to redefine statistical significance by lowering the conventional alpha threshold to p ≤ .005. Rather than adopting a single fixed threshold, the collaborating authors argue that researchers should transparently report and justify the alpha level chosen for a given study, treating the significance threshold as a design decision that depends on context rather than a universal constant.

Sau-Chin Chen is a co-author of this large multi-author methodology project, which brought together statisticians and methodologists across many institutions to formulate a shared position on error control in study design.

The project’s significance lies in shifting the debate on statistical significance away from a search for a single “correct” threshold and toward a broader emphasis on transparency and justification in research design choices, a position that has since informed wider discussions of statistical practice.

Status: Stable — completed and archived on OSF.

Investigating Object Orientation Effects Across 14 Languages

Wed, 08 Jan 2025 00:00:00 +0000

This project, PSA 002 of the Psychological Science Accelerator, examined whether people mentally simulate the orientation of objects while reading sentences that describe them, extending decades of research on mental simulation in language comprehension. Earlier work using the sentence-picture verification task had found robust match advantages for shape, color, and size, but evidence for orientation was limited and confined mostly to Western samples. The study combined a large cross-linguistic replication with a mental rotation task to relate individual differences in mental imagery to the strength of the orientation effect.

Sau-Chin Chen proposed and led this project as a large-scale, multi-laboratory collaboration coordinated through the Psychological Science Accelerator network, bringing together dozens of contributing labs and languages. The resulting registered report, covering 18 languages and nearly 4,000 participants, was published as Investigating object orientation effects across 18 languages in Current Psychology (2025).

By testing the same paradigm across speakers of many different languages, the project offered one of the most direct tests to date of whether object-orientation simulation generalizes beyond the languages in which it was first documented, and it produced a well-powered dataset connecting the phenomenon to individual differences in mental imagery ability.

Status: Stable — completed and archived on OSF.

EXPPSY Opensci: An Open Textbook for Experimental Psychology Methods

Mon, 23 Dec 2024 00:00:00 +0000

EXPPSY Opensci is an open-source textbook on experimental psychology methods, built on R Markdown and the booktem template. It is published as a browsable online book so students and instructors can read the material directly without building it locally.

The book targets students learning the logic and practice of experimental design in psychology, and it is structured so that the source repository can reproduce the published site end to end.

Status: Stable — content is complete and the repository is kept available with no active new-chapter development.

Teaching Experimental Psychology in Taiwan

Mon, 24 Feb 2020 00:00:00 +0000

This project collects the OSF-based experimental psychology course projects that Sau-Chin Chen has taught at Tzu-Chi University over several academic years, gathering student and course materials produced as part of hands-on training in open research practices.

As the instructor, Sau-Chin Chen created and maintains this parent OSF node as a running archive, adding course projects from successive years of teaching experimental psychology to undergraduate students.

The collection illustrates a sustained effort to integrate open science practices, including preregistration and data sharing through OSF, directly into undergraduate experimental psychology training rather than treating them as separate add-on skills.

Status: Stable — an ongoing teaching archive, updated as new course years are added.

Basic Statistics for Psychological Science (OSF Companion)

Fri, 07 Jun 2019 00:00:00 +0000

This project is the OSF companion to Sau-Chin Chen’s online statistics textbook for psychological science, hosting the demonstration materials and downloadable exercise modules that accompany the text.

Sau-Chin Chen created and maintains this project as an instructor, using it to distribute datasets and practice modules that let students apply the concepts covered in the textbook directly.

By keeping the practical materials on OSF, the project makes the exercises openly accessible and reusable alongside the textbook, supporting students learning basic statistics for psychological research.

Status: Stable — a companion resource maintained alongside the textbook.

Translation Project: Improving Your Statistical Inferences

Thu, 10 Aug 2017 00:00:00 +0000

This project coordinated a collaborative effort to translate Daniël Lakens' well-known Coursera course, “Improving Your Statistical Inferences,” into Chinese, aiming to bring its material on statistical inference and research methodology to a wider Chinese-speaking audience.

Sau-Chin Chen organized this project as a community translation effort, working with other contributors on OSF to push the course’s content out to a broader audience beyond its original English-language delivery.

The project reflects a community-driven contribution to open statistics education, extending the reach of well-regarded methodology training materials across a language barrier.

Status: Stable — completed and archived on OSF.

Mental Simulation in Reading Sentence

Mon, 01 Jan 0001 00:00:00 +0000

When we are reading the sentences describing the status of objects, such as ‘The painter is cleaning his brush’, how our minds catch the details? This issue has been explored longer than a decade since the match advantages of sentence-picture verification task have been robustly replicated across shape, color, size and orientation. The sentence-picture verification task requires the participants read the sentence then verify the target picture. When the target picture match the visual feature implied by the sentence, the reponses are usually faster than the pictures that mismatch the implied visual feature. For example, the responses to the “standing eagle” are faster after the sentence “The ranger saw the eagle in the nest” than the sentence “The hunber aims the eagle flying on the sky”.

The accumulated findings show the decreasing match advantages from shape, color, size, then orientation. Because these findings are from Western societies, it appears to be that the object orientations are difficultly simulated in Western minds.

Under construction