通过 WeKnora Wiki 只读检索鲲鹏、ARM、Linux 与应用调优知识，并保留来源依据
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin kunpeng-knowledge in openeuler-mirror/KPBot. Commands read from the repo's manifest — today.
kunpeng-knowledge通过 WeKnora Wiki 只读查询鲲鹏、ARM、Linux 和应用调优知识。 当用户、Agent 或其他 Skill 提到“知识库”并请求查询、搜索、检索或查找资料时使用； 也用于核对知识库中的调优依据或读取 Wiki 页面，无需使用“内部”限定。 不负责采集现场性能数据、执行优化或修改知识库。 skill_type: knowledge_base domain: kunpeng category: reference version: "1.0.0" activation_mode: passive side_effect_free: "true
鲲鹏/ARM 代码优化 — 自动化 C/C++ 性能分析与优化 Pipeline，支持向量化、汇编优化、预取、分支消除、循环展开、访存优化、编译选项调优，以及 TensorFlow 纯 CPU 推理优化（图优化 + 自定义 fused kernel）、VSAG HGraph RaBitQ 并发查询批处理优化、PyTorch embedding lookup 流水线的并行 unique 自定义算子优化（__gnu_parallel::sort + OpenMP、TORCH_LIBRARY）、OpenZL 压缩框架调优（熵 codec 根表/位流优化、熵选型、无损逐字节验证 + unitBench 基准协议）、分配路径优化和 DPDK 数据面热路径代码优化（瓶颈建模 + 杠杆库 + 交错 A/B 验证）、热点路径机制开销消除，覆盖 Kunpeng-0xd01/0xd03/0xd06 微架构
80 skills
应用级调优 — 针对具体应用场景的深度性能调优
38 skills
OpenWiki 代码仓文档自动生成与同步 — 为代码仓生成 OpenWiki 并托管到独立 wiki 仓，记录代码仓与 wiki 仓的关联关系；代码 commit 后自动增量更新 wiki 仓并生成对应 commit，覆盖初次生成、关联恢复、增量更新、wiki 查询全场景，支持 GitCode/Gitee/GitHub/通用 git 平台
1 skill
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Knowledge graph construction — entity extraction, relation mapping, and pathfinder graph traversal
2 skills · 1 command · 1 agent
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
12 skills · 1 MCP server · hooks
Personalized AWS guidance built on patterns from 350,000+ startups. Get architecture, cost, and security recommendations matched to your stage, from day-one account setup to production-ready infrastructure. Migrate to AWS from Azure, GCP, or Heroku with resource discovery, cost estimates, and generated Terraform. Move OpenAI, Azure OpenAI, and Gemini code to Amazon Bedrock, and plan and prototype AI agents on AgentCore and other AWS runtimes. Includes AWS Activate credits eligibility, 60+ exclusive startup offers, and multi-account, multi-region support. Built by AWS Startup Solutions Architects.
13 skills · 1 command · 7 agents · 1 MCP server
HADS (Human-AI Document Standard) — semantic tagging convention for docs that work for both humans and AI models — plus the grounded-vault pattern for provenance-linked, drift-checked knowledge stores.
2 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.