By sisibeloved
CPython/CinderX 性能优化与设计文档技能仓库:编译、基准测试、JIT 分析、Docker 隔离、远程环境、设计文档
在需要分析 JIT/非JIT 用例性能、dump HIR/LIR、定位性能瓶颈或优化点时使用
在目标环境中编译 CPython 或 CinderX 并强制覆盖安装时使用,涵盖版本基线、编译选项和安装验证
在需要编写系统设计、架构设计、功能设计或详细设计文档时使用
在需要创建/管理 Docker 容器、挂载目录、镜像复用、双线结构选择时使用
在需要记录实验结果、写性能分析报告、规范产物格式时使用
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
面向个人工作流的 CPython/CinderX 性能优化与设计文档技能集合,以 Claude Code 技能插件 形式交付。
| 技能 | 用途 | 自带资源 |
|---|---|---|
🎯 using-cpython-optimize | 引导入口,自动注入 | — |
🔌 remote-environment | SSH、tmux、rsync | — |
🔨 cpython-build | CPython/CinderX 编译与安装 | — |
🐳 docker-runtime | Docker 双线隔离 | templates/、scripts/ |
📊 pyperformance-test | 基准测试、性能口径、crash triage | references/、scripts/ |
🔬 cinderx-analysis | JIT/非 JIT 分析、HIR/LIR 定位 | references/ |
📝 experiment-documentation | 实验记录、报告模板 | references/ |
📐 design-documentation | 架构/系统/功能/详细设计文档 | references/ |
/plugin marketplace add https://github.com/sisibeloved/cpython-optimize-skill
/plugin install cpython-optimize-skill
安装后,新会话启动时 using-cpython-optimize 引导技能会通过 SessionStart hook 自动注入上下文。
codex plugin marketplace add https://github.com/sisibeloved/cpython-optimize-skill
codex plugin add cpython-optimize-skill
> 帮我在 Kunpeng 上编译 CinderX 并跑一次 pyperformance
> regex_compile 在容器里 SIGSEGV 了,帮我复现和定位
> 对比 stock CPython JIT 和 CinderX JIT 的 pyperformance 数据
> 帮我写一份 CinderX JIT 优化点的架构设计说明书
Agent 会根据任务自动选择对应技能,无需手动加载。
.
├── .claude-plugin/ # Claude Code 插件注册
│ ├── marketplace.json # 插件市场元数据
│ └── plugin.json # 插件描述
├── .codex-plugin/ # Codex 插件注册
│ └── plugin.json
├── .agents/plugins/ # Codex 插件市场元数据
│ └── marketplace.json
├── hooks/ # SessionStart 自动注入
│ ├── hooks.json
│ └── session-start
├── skills/ # 8 个自包含子技能
│ ├── using-cpython-optimize/
│ ├── remote-environment/
│ ├── cpython-build/
│ ├── docker-runtime/
│ ├── pyperformance-test/
│ ├── cinderx-analysis/
│ ├── experiment-documentation/
│ └── design-documentation/
├── tests/ # 结构验证 + 压力测试场景
├── docs/ # 仓库级文档(plans、design)
├── package.json
└── CHANGELOG.md
每个技能自包含 SKILL.md + 专属 references/、scripts/、templates/,技能间通过 Skill 工具互相调用。
python3 tests/validate_skill_layout.py
见 CHANGELOG.md。
MIT
npx claudepluginhub sisibeloved/cpython-optimize-skill --plugin cpython-optimize-skillPermanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.