Data Processing

Persistent memory for Claude Code. Bring your own database.

Production pipeline and Claude Code skill for Vocaloid-style hand-drawn (手書き) lyric music videos: deterministic Canvas2D/WebGL2 animation engine, JIZURA lyric motion, AI illustration, Blender toon 3D, headless rendering to 16:9 and 9:16.

Influencer discovery & contact enrichment pipeline that runs as a Claude Code skill — 15 channels, stdlib only, appends to a Google Sheet

A collection of AI skills for working with Dagster

Turn your scattered AI coding sessions into a queryable knowledge graph. Multi-platform (Claude Code, ChatGPT, DeepSeek, Grok, Warp), W3C ontology, Wikidata entity linking, SPARQL.

論文學習雷達 — a personal literature-tracking & learning radar: dozens of journal/PubMed feeds → interest-scored → private web triage → flows into your notes. Discovery end of a pipeline: pair with paper-fetch (full-text download) and paper-review-and-digest (appraisal/digest).

Publisher-aware full-text PDF fetcher — DOI in, PDF out via OA → publisher TDM APIs → your own institutional proxy. Download end of a paper pipeline; pair with paper-radar (discovery) and paper-review-and-digest (reading).

Claude Code and Codex skills for empirical applied-micro research: reproducibility auditing, LLM-pipeline methods, event studies, WRDS, Stata, publication-grade tables

datasec_skill

SWI is a single-process reference pipeline for security and workflow integrity. Module 00 orchestrates security probing, context checks, PII redaction, drift analysis, memory validation, and audit logging. Modules 01, 04, 08 and 10 provide standalone integrity, encryption, authentication and execution utilities.

A Claude Project skill system for disciplined, data-driven sports betting. One prompt → structured bet recommendation with EV%, unit sizing, and reasoning.