>_Skillful
Need help with advanced AI agent engineering?Contact FirmAdapt
Yufeng He

Yufeng He

@he-yufeng

AI Researcher @ Moonshot AI (Kimi) | MS CS @ HKU | Champion, Shanghai Global AI Contest | 3× ACM-ICPC Silver | Former Intern @ Baidu, Maimai, Kuaishou

Moonshot AI Hong Kong www.linkedin.com/in/yufenghe On GitHub since June 2018

13

Published Tools

377

Total Stars

0

Weekly Downloads

439

GitHub Followers

122

Public Repos

Published Tools

1 MCP Server4 Skills8 Agentsacross 5 categories

corecoder

Minimal AI coding agent (~1300 LoC) inspired by Claude Code. Works with any LLM. (formerly NanoCoder)

Agentai-agents
3261 dir

nanocoderagent

Minimal AI coding agent (~1300 LoC) inspired by Claude Code. Works with any LLM.

Agentai-agents
401 dir

anycoder

AI coding agent CLI that works with any LLM - DeepSeek, Qwen, GPT, Claude, Gemini, local models, you name it

Agentai-agents
61 dir

Agentcikit

he-yufeng

CI-grade evidence and safety tools for AI agents, MCP servers, and open-source work — one CLI: ci-repro, patch-context, mcp-gate, mcp-replay, tool-fence.

...more
Agentdevtools
53 dirs

agentpoke

Yufeng He <[email protected]>

Drop-in pytest plugin for regression-testing AI agents — snapshot baselines, semantic comparison, mock LLMs

Agentuncategorised
2 dirs

batchllm-ai

Yufeng He <[email protected]>

Batch processing for LLM APIs - CSV/JSONL in, processed out. With retries, rate limiting, and cost tracking.

Skilluncategorised
2 dirs

mcpready

Yufeng He

CI gate for MCP servers

MCP Servermcp
2 dirs

promptdelta

Yufeng He <[email protected]>

Semantic diff for LLM prompts — compare prompt versions like git diff

Skilluncategorised
2 dirs

ruleforge-ai

Yufeng He <[email protected]>

Generate AI assistant rules (CLAUDE.md, .cursorrules, copilot-instructions) from codebase analysis

Skilluncategorised
2 dirs

codejoust

A CLI arena for AI coding agents. Throw one bug at Claude Code, Codex, aider — let them race, auto-score, and pick the winner.

...more
Agentai-agents
1 dir

flightbox

Yufeng He

Black-box flight recorder for AI agents — record, replay, and diff LLM sessions

Agentai-agents
1 dir

litebench

A pip-installable benchmark runner for LLMs and agents. 5 minutes to your first eval.

Agentai-agents
1 dir

toktally

Drop-in LLM cost tracker — change one import line, see where your money goes

Skillai-ml
1 dir