AI Agent Skills

Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7%…

Drive the skvm CLI on behalf of a user to profile models, AOT-compile skills, run skill-assisted tasks, run benchmarks, and manage compiled proposals. Trigger when the u…

Claude Code / Cursor 开源替代。部署在你自己的服务器上，团队用浏览器打开就能编程——包括手机。CLI & Web UI 双入口，Multi-Agent 协作，原生直连千问/DeepSeek 等国产大模型。SWE-bench Lite 56%，不是玩具。技能/插件/跨会话记忆，8 层安全沙箱，数据不离开你的机器。Doc…

Trigger `skvm jit-optimize` with post-task evidence so it generates a reviewable optimization proposal for a skill. Use after finishing a task that was driven by any ski…

Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when…

Production-grade RAG API built in Rust. Hybrid search with HNSW dense vectors and BM25 sparse matching, cross-encoder reranking, layout-aware document extraction via Doc…

Electronics and embedded engineering judgment, distilled from a stronger model - invoke when CHOOSING components, MCUs, modules, or interfaces; designing or reviewing a…

Use when reviewing or validating Frappe/ERPNext code against best practices and common pitfalls. Checks generated code before deployment, validates against all 61 frappe…

Use when implementing translations/i18n in Frappe v14-v16 apps. Covers _() in Python, __() in JavaScript, CSV translation files, bench commands, string extraction rules,…