Skip to content
View wellkilo's full-sized avatar

Highlights

  • Pro

Block or report wellkilo

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
wellkilo/README.md

Hi there, I'm He Dong 👋

🎓 保研至:北京理工大学

🚀 关注方向:AI for Code · 深度强化学习 · LLM Agents


🧑‍💻 About Me

  • 🔭 在字节跳动从事过 AI 辅助研发工作流 相关工作,把 MR 缺陷回溯 + CR 自动化的耗时从 30 min → 3 min
  • 🌱 正在深入 LLM AgentCodemod / AST分布式强化学习
  • 🛠️ 喜欢把零散痛点抽象成可复用的开源工具,已在迭代命令行工具 conda-helper

🧰 Tech Stack


📌 Featured Projects

Project Stack Description
🦀 codemod-pilot Rust 智能 codemod 引擎:从 before/after 代码片段反推 AST 级转换规则,并在仓库范围内批量应用
🤖 CaseAI TypeScript 上传 PRD 即可自动生成测试用例集的智能体系统
🦿 DRL_MuJoCo Python 基于 Ray 的分布式 Actor-Learner 架构,在 MuJoCo 环境下并行采样与学习
📚 wellkilo.github.io HTML 个人博客,分享计算机学习笔记与工程实践

📊 GitHub Stats


「Stay hungry, stay foolish.」

Pinned Loading

  1. affaan-m/ECC affaan-m/ECC Public

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    JavaScript 224k 34.3k

  2. conda-helper conda-helper Public

    An enhanced, cross-platform CLI on top of conda. One-liner backup, restore, clone, offline pack, batch cleanup, and an interactive panel — plus friendly error hints that translate raw conda stack t…

    Python 2

  3. walkinglabs/learn-harness-engineering walkinglabs/learn-harness-engineering Public

    Harness engineering beginner tutorial, from 0 to 1

    TypeScript 9.6k 1k

  4. codemod-pilot codemod-pilot Public

    🛩️ Transform your codebase by example — an intelligent codemod engine that infers AST-level transformation rules from before/after code snippets, then safely applies them across your entire codebas…

    Rust 4 1

  5. SlideCraft SlideCraft Public

    AI skill that generates stunning presentations in HTML (animated, zero-dependency) and PPTX (PowerPoint-editable) formats. 12 curated visual themes with anti-AI-slop design philosophy.

    Python 1 1

  6. DRL_MuJoCo DRL_MuJoCo Public

    Distributed Actor-Learner architecture based on Ray for parallel sampling and learning in the MuJoCo environment

    Python 1 1