# Skills For Real Engineers [](https://skills.sh/mattpocock/skills) My agent skills that I use every day to d
若代理經常過度設計，這套決策階梯可能直接降低程式碼量與審查負擔；但安全與效率結論尚未經廣泛外部驗證，而且 Claude Code、Codex 的常駐掛鉤需要 Node.js 位於非互動 shell 的 PATH。
原文節錄
DietrichGebert/ponytail
~54% less code (up to 94%) · ~20% cheaper · ~27% faster · 100% safe Measured on real Claude Code sessions editing a real open-source
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
anthropics/skills 是 Anthropic 公開的 Claude Skills 實作與範例庫，每項技能以包含 SKILL.md、指令、腳本及資源的資料夾封裝，涵蓋創作、開發、企業流程與文件處理。它可透過 Claude Code 外掛市集、Claude.ai 付費方案或 Claude API 使用，也附有技能規格與最小模板，適合作為建立內部工作流程的官方參考。授權並不完全一致：多數技能採 Apache 2.0，但 docx、pdf、pptx、xlsx 等實際支撐 Claude 文件功能的技能僅開放原始碼查看；Anthropic 也明示本庫以示範與教學為主，實際行為可能不同。
# Humanizer [](https://skills.sh/blader/humanizer) Humanizer rewrites AI-sounding text so it reads li
# Hermes Agent ☤ Hermes Agent | Hermes Desktop **The self-improving AI agent built by [Nous Research](https://nousresearch.com).** It's the only agent with a bu
Open source inference server that runs the best local models for your hardware, plugged into the agent you already use. Works with Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline.
A single archive of public exploit PoCs and vulnerability research writeups. At the time I post these, none have been reported. Feel free to report them yourself and take credit for the CVE if handed out lulz. Please do not abuse these. I do this so to allure people into the field, and I've always found this is the most efficient way.
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
Google Research 的 TimesFM 是用於時間序列預測的預訓練基礎模型，論文曾收錄於 ICML 2024；README 將 3.0 列為最新版，加入原生多變量預測及過去或未來共變量支援。專案宣稱 3.0 在 fev-bench、TIME Benchmark 與 GIFT-Eval 取得領先名次，但摘錄未提供各項實驗設定或可直接核對的結果表。程式碼與 2.5 以前權重採 Apache-2.0，3.0 權重目前則限非商業、非正式環境使用，而且這個開源版本不是 Google 官方支援產品。
一龍馬判讀
企業可用統一模型處理需求、營運或感測資料預測，也能透過 PyTorch 套件、BigQuery ML 等不同介面導入；但 3.0 的權重限制直接阻擋商業及正式部署。採用者還需自行驗證基準成績能否轉移到自身資料分布，並承擔開源版本的維運責任。
原文節錄
google-research/timesfm
# TimesFM TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
### **Enterprise-Grade Reinforcement Learning for Large-Scale Model Post-Training** []
