Search

Self-hosted decision server for the dbt-state client, with pluggable state storage.

The Hirundo platform provides APIs for: LLM behavior unlearning & dataset QA.

Automated cell annotation from scRNA-seq data using LLMs

k-NN-based mapping of cells across representations

Python client SDK for IIPOS distributed blob storage

Push alerts when your Claude Code subscription usage crosses a limit.

LLM toolkit for file management, citation extraction, content idealization, and document generation.

Data Contract eXtended — AI-native, platform-extensible data contracts: LLM enrichment (descriptions, tags, data quality), live import, and apply. Built on datacontract-cli.

A generation-time correction layer for LLMs — debias before you generate, not after.

Turn Claude into a disciplined research analyst — verify facts against primary sources, brief any topic, draft flagship reports. Standalone or chained; runs across LLM terminals. | 把 Claude 变成讲纪律的研究分析师：核实事实、主题简报、旗舰研报，引用一手来源、绝不造数；可单用或串联，跨 LLM 终端。

Verify a computational result by re-running it and recomputing the number from the raw outputs. An open-source Claude Code skill.

Claude Code skill: check job ads for gender-coded language (Gaucher et al. 2011) — deterministic scorer + LLM context review and balanced rewrite.

学习.skill —— 让 Agent 成为你的赛博老师，帮你备课，陪你学习

Give Claude Code a voice on Windows: a Stop-hook + edge-tts daemon speaks each reply aloud, with a skill to switch voices, mute, and interrupt.

硬件开发助手 — 一个为 Claude Code 打造的 Skill：逐引脚、逐器件、有证据地审查从原理图到固件的设计。Evidence before claims.

Claude Code skills for developers who code like cats — never more effort than the problem requires.

26 production-grade Go skills for Claude Code, Gemini CLI, and opencode.

Practical AI management toolkit: weekly planning, meeting agendas, feedback scripts, performance reviews, and decision briefs.

Self-Evolving AI Agent Framework | Decision-Loop Driven Microkernel Architecture with Hot-Pluggable Components & Triple-Layer Memory | Agent Infinite Evolution Engine that Learns from Failures

A high-performance lossy audio compression engine inspired by LLM weight quantization