Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Using Cpython Optimize

ASecurity

Use when CPython/CinderX 任务需要跨环境、跑分、crash 或 JIT 分析选择工作流;单项操作直接用对应技能。

2 stars
0 votes
0 copies
0 views
Added 9/20/2026
researchpythonperformance

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add sisibeloved/cpython-optimize-skill --skill using-cpython-optimize --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Using Cpython Optimize?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Using Cpython Optimize
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sisibeloved-using-cpython-optimize/badge)](https://www.skillsdirectory.com/skills/sisibeloved-using-cpython-optimize)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: using-cpython-optimize
description: Use when CPython/CinderX 任务需要跨环境、跑分、crash 或 JIT 分析选择工作流;单项操作直接用对应技能。
---

# CPython/CinderX Optimize Router

根据用户目标选择所需 Skill 或 Workflow。已指定技能、只读结果、局部代码审查和文档修改可直接完成,不必经过 Orchestrator → Workflow → Agent 全链路。

## 单项任务

| 当前需要 | 技能 |
|----------|------|
| 审计 / 初始化 / 清理 lab | `cinderx-env-validate` / `cinderx-env-bootstrap` / `cinderx-env-clean` |
| 远程操作或卡顿诊断 | `cinderx-remote-lab-ops` |
| A/B 资源隔离 | `cinderx-ab-run-slot` |
| 功能或集成测试 / 最小 JIT | `cpython-runtime-test-run` / `cinderx-smoke-check` |
| 单 worker / 正式 suite / 并行队列 | `pyperformance-worker-run` / `pyperformance-suite-run` / `cinderx-parallel-pyperformance` |
| 已有结果比较 / 统计图表 / 实验报告 | `pyperformance-result-compare` / `pyperformance-stat-report` / `cinderx-optimization-report` |
| native crash / HIR dump | `cinderx-gdb-core-triage` / `cinderx-hir-dump` |
| JIT 进入判定 / HIR-LIR / 解释执行分析 | `cinderx-jit-entry-check` / `cinderx-hir-lir-analyze` / `cinderx-interpreter-case-analyze` |
| 平台归因 / 单用例证据表 | `cinderx-isa-microarch-compare` / `cinderx-evidence-table` |
| 指令规格 / 编译器理论 | `isa-instruction-lookup` / `compiler-optimization-theory` |
| 验证范围或成本取舍 | `validation-strategy` |

## 多阶段任务

- 已有双平台差距:`workflow-cross-platform-delta-triage`
- 实施已知优化:`workflow-feature-driven-optimization`
- 尚未选定用例的系统扫描:`workflow-platform-differential-discovery`
- 深钻已选用例:`workflow-platform-differential-discovery-deepdive`
- 远程环境准备:`workflow-remote-cinderx-lab-setup`
- crash 复现到报告:`workflow-cinderx-crash-triage`
- 正式 A/B 回归:`workflow-pyperformance-regression`
- 单 benchmark 路径与优化分析:`workflow-jit-optimization-analysis`

只读取当前阶段需要的材料。已有环境和实验指纹未变时复用证据;源码、解释器、安装、flags 或 CPU 分配变化后重查受影响项。环境三态由 `cinderx-env-validate` 定义;正式 A/B 还需独立证明 baseline source 可信。

Workflow 的 Agent 列表示阶段职责,不要求创建子代理。需要角色交接或宿主允许委派时,查 [角色索引](references/agent-routing.md) 并只读选定角色;否则主 Agent 顺序执行相同职责。

## 决策与完成

用户当前要求和已有授权优先于技能中的默认流程。自行选择可从证据确定的路线、子集、日志目录和可逆隔离方案;不要让用户替你选择内部 Workflow 或验证等级。

只有目标/实验轴确实不明、将删除用户产物、影响其他任务或超出已知预算时,才询问阻塞部分,并继续独立的只读分析。需要提问格式时查 [澄清模板](references/clarifying-question-templates.md),遵循当前宿主工具约束。

按请求完成实现、适当验证和结果交付;测试通过后仅因新改动、失败或未解风险扩大验证。证据门禁限制结论,不要求停下所有工作:baseline 不可信不能跑正式 A/B,缺 native 栈不能声称 crash 根因,未证明 benchmark 进入 JIT 不能给 HIR 优化结论。说明缺口并推进可验证部分。

指令集规格(编码、汇编语法、伪代码、`FEAT_xxx` 依赖、跨平台等价候选)使用 `isa-instruction-lookup` 查证,不凭记忆回答;引用带 `source_doc` 和页码。编译器理论使用 `compiler-optimization-theory` 的相关分支,落到具体指令时仍需查库。

Attribution

sisibelovedsisibeloved
View sourceMore from sisibeloved →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Competitor Analysis

This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.

1823 votes

Deep Research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review...

452202 votes

Paperclip Distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.

805541 votes

Academic Pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publi...

452201 votes

Exa Search

Semantic search, similar content discovery, and structured research using Exa API

304951 votes
View all in research →