Performance Engineering logo

Performance Engineering

Organization
devcodex-labs
performance-engineering

性能工程专家 Owner — 当任务涉及性能优化、性能预算、benchmark、profiling、p95/p99、吞吐、延迟、资源效率、容量规划、压测或性能回归时使用;要求先建立可比较基线,再定位瓶颈、评估容量并形成统计可信的回归结论。

Overview

Publisherdevcodex-labs
Repositorydevcodex
Skill nameperformance-engineering
Stars
433
Forks
44
Bundled files
2
LicenseAGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by devcodex-labs on GitHub. Read the source before you install it.

Installation

Install the Performance Engineering AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/devcodex-labs/devcodex/tree/main/content/skills/performance-engineering
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/devcodex-labs/devcodex.git /tmp/devcodex
mkdir -p .claude/skills
cp -r /tmp/devcodex/content/skills/performance-engineering .claude/skills/performance-engineering
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Performance Engineering in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Performance Engineering on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Performance Engineering is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Performance Engineering

职责

把“更快”转化为可复现的 workload、预算、基准、profiling、瓶颈归因、容量与回归合同。dev-optimization 负责开发流程,SRE 负责生产运行;本 Skill 负责性能证据的专业可信度。

PerformanceEngineeringGate

字段要求
workloadModel用户路径、数据规模、并发、读写比、缓存状态、突发与稳态
performanceBudgetlatency percentile、throughput、resource、error/saturation 阈值
benchmarkProtocol环境、版本、warmup、sample、duration、重复次数、噪声控制
profilingEvidenceCPU/heap/I/O/lock/network/GC 等证据和采样边界
bottleneckAttribution症状→资源→调用路径→因果实验,区分相关与因果
capacityModel单实例能力、扩展曲线、饱和点、headroom、成本
regressionThresholds绝对/相对阈值、置信区间、噪声带和阻断条件

执行流程

  1. 冻结当前基线、目标用户路径和不可牺牲的正确性/稳定性。
  2. 建立代表 workload;区分 cold/warm cache、steady/burst 和 local/CI/prod-like。
  3. 先测基线,再 profiling;禁止先改代码后寻找支持结论的数据。
  4. 一次改变一个主要变量,保留版本、硬件、配置、数据和命令。
  5. 同时看 latency distribution、throughput、errors、CPU/memory/I/O/GC 和尾延迟。
  6. 输出 capacity/headroom 与成本权衡;优化不能靠隐藏限流或丢请求。
  7. 用同协议重跑对照,达到阈值才判 accepted。

ModulePerformanceCoverageAndMaintenanceGate

当框架、SDK、CLI、runtime 或公共包声称“完整性能覆盖”时,单一 benchmark、全局 DIM 或一个 release gate 不足以通过。必须先为每个功能判定 performance applicability,再为每个适用模块建立:

维度必填证据
moduleProtocolworkload、budget、immutable baseline、candidate comparison
capacityResourcecapacity/headroom、CPU/memory/I/O/GC、饱和点和成本
stabilityRecoveryleak/pressure(适用时)、故障/冷却/恢复、正确性守恒
maintenanceTriggersPR、main、scheduled、RC、post-release 的触发与升级关系
evidenceGovernanceretention、freshness、drift、owner、skip/N/A/flake 处理
coverageStatetotal/applicable/executed/accepted/failed/skipped/stale,清单完成与执行完成分开

全部适用模块 accepted 前只能报告 partial;不可变基线变更必须有授权和迁移证据,不能通过减少适用模块、删除 flake 或重写基线制造通过率。

ExecutionChainBenchmarkGate

DevCodex 自身的任务续接、上下文/Profile/Skill 读取、验证 DAG 与增量分析优化统一输出 ExecutionChainBenchmarkResultV1。四个 direct-benefit 维度为 validation wall time、delivered bytes、analysis recompute work、resume setup cost;baseline/candidate 必须使用同一环境 identity、单位和样本策略,等权计算几何平均,禁止把不同量纲直接相加。

只有 correctness 指标全为 0、综合改善至少 25%、至少 3/4 维度改善 20%、任一维度回归不超过 5%、instrumentation overhead 不超过 3% 时,结果才可 accepted。样本不足、环境不一致或宿主 token/TTFT 不可观测时保持 provisional / N/A;不得用 bytes 冒充 token。任何默认晋级还必须有 prospective trial(至少 3 个可比 WorkUnit 或 2 个独立上下文),历史样例只能证明基线。

性能 accepted 还必须证明 lifecycle 能控制真实执行路径:将每个受控 feature 置为 rolled-back 后,task index、Context cache、changed validation、Profile section、Skill bundle 与 ProjectKnowledge 都必须通过 ExecutionOptimizationFeatureDecisionV1 回到安全非优化路径;changed validation 必须保留显式 intent/route 并执行 direct-validation-plan,不得暗升 full,其余消费者回到完整读取路径。只有 status/doctor 投影变化、消费者仍走加速时属于 correctness failure,收益数据作废。

基准 evaluator 使用 npm run benchmark:execution-chain -- --input <ExecutionChainBenchmarkInputV1.json>;只有显式 --output 才可写结果。benchmark、website build 与 package smoke 串行执行,避免派生产物污染可比性。

输出字段

workloadModel、performanceBudget、benchmarkProtocol、baselineEvidence、profilingEvidence、bottleneckAttribution、capacityModel、regressionThresholds、comparisonLimits、modulePerformanceCoverage、maintenanceTriggers、executionChainBenchmark、decision、evidenceMatrix。

反模式

  • 没有基线就声称提升、最快或无回归。
  • 只报平均值,不报 p95/p99、错误率和资源饱和。
  • 对比环境、版本、数据或缓存状态不同却给出百分比。
  • benchmark 本身写文件、重建 dist 或污染后续 pack。
  • 微基准变快就推断端到端用户路径变快。
  • 通过降低正确性、持久性、审计或安全换性能而不披露。

验证

至少覆盖 warmup/measurement 分离、重复样本、噪声带、环境元数据、基线可比性、资源瓶颈、正确性守恒、容量拐点和回归阈值;不可比较时结论必须为 inconclusive。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Performance Engineering AI skill do?

性能工程专家 Owner — 当任务涉及性能优化、性能预算、benchmark、profiling、p95/p99、吞吐、延迟、资源效率、容量规划、压测或性能回归时使用;要求先建立可比较基线,再定位瓶颈、评估容量并形成统计可信的回归结论。

Why use Performance Engineering on TypingMind?

Because you install it once and use it with any model. Performance Engineering is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Performance Engineering in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/devcodex-labs/devcodex/tree/main/content/skills/performance-engineering. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Performance Engineering?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Performance Engineering?

As many as you like. As long as a model supports skills, you can use Performance Engineering with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Performance Engineering AI skill free?

Yes. It is published on GitHub by devcodex-labs under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇