Sglang Diffusion Benchmark Profile
sgl-project/sglang
A skill your agent uses when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
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。
AGPL-3.0Auto-check passed
Install Performance Engineering
$ npx skills add devcodex-labs/devcodex --skill performance-engineering -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install devcodex-labs/devcodex performance-engineering --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/content/skills/performance-engineering .claude/skills/performance-engineering && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "performance-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/performance-engineering into .claude/skills/performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-engineering", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/devcodex-labs/devcodex/tree/main/content/skills/performance-engineeringType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add devcodex-labs/devcodex --skill performance-engineering -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install devcodex-labs/devcodex performance-engineering --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .agents/skills && cp -r skills-src/content/skills/performance-engineering .agents/skills/performance-engineering && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "performance-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/performance-engineering into .agents/skills/performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-engineering", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add devcodex-labs/devcodex --skill performance-engineering -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install devcodex-labs/devcodex performance-engineering --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/content/skills/performance-engineering .cursor/skills/performance-engineering && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "performance-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/performance-engineering into .cursor/skills/performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-engineering", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/devcodex-labs/devcodex.git --path content/skills/performance-engineering--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add devcodex-labs/devcodex --skill performance-engineering -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install devcodex-labs/devcodex performance-engineering --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/content/skills/performance-engineering .gemini/skills/performance-engineering && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "performance-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/performance-engineering into .gemini/skills/performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-engineering", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install devcodex-labs/devcodex performance-engineeringInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add devcodex-labs/devcodex --skill performance-engineering -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .github/skills && cp -r skills-src/content/skills/performance-engineering .github/skills/performance-engineering && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "performance-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/performance-engineering into .github/skills/performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-engineering", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add devcodex-labs/devcodex --skill performance-engineering -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install devcodex-labs/devcodex performance-engineering --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/content/skills/performance-engineering .opencode/skills/performance-engineering && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "performance-engineering" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/performance-engineering into .opencode/skills/performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-engineering", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
performance-engineering- GitHub stars
- 439
- Token cost
- ~873 tokens
- SKILL.md length
- 202 words
- Files
- 3
- Skills in repo
- 70
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
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。
- Works in 7 steps: 冻结当前基线、目标用户路径和不可牺牲的正确性/稳定性。 → 建立代表 workload；区分 cold/warm… → 先测基线，再 profiling；禁止先改代码后寻找支持结论的数据。 → …
- SKILL.md covers 职责, PerformanceEngineeringGate, 执行流程 and ModulePerformanceCoverageAndMai…, plus 4 more sections
- Calls npm
What it does
Performance Engineering is an agent skill from devcodex-labs/devcodex. 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。
Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `agents/openai.yaml` and `intent.json`).
The repository describes itself as: Intent-driven AI coding workflow runtime for consistent context, skills, approvals, validation, and handoffs across six AI coding hosts. The licence is AGPL-3.0.
Example prompts
- “/performance-engineering”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- 冻结当前基线、目标用户路径和不可牺牲的正确性/稳定性。
- 建立代表 workload；区分 cold/warm cache、steady/burst 和 local/CI/prod-like。
- 先测基线，再 profiling；禁止先改代码后寻找支持结论的数据。
- 一次改变一个主要变量，保留版本、硬件、配置、数据和命令。
- 同时看 latency distribution、throughput、errors、CPU/memory/I/O/GC 和尾延迟。
- 输出 capacity/headroom 与成本权衡；优化不能靠隐藏限流或丢请求。
- 用同协议重跑对照，达到阈值才判 accepted。
What it can do on your machine
Read from SKILL.md and the folder at commit 1dd4525. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Performance Engineering loads about 873 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 202 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from devcodex-labs/devcodex at commit 1dd4525, republished under its AGPL-3.0 licence (© devcodex-labs). 202 words, ~873 tokens.
Download SKILL.mdSave it as
.claude/skills/performance-engineering/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- performance-engineering
- description
- 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。
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 |
| performanceBudget | latency percentile、throughput、resource、error/saturation 阈值 |
| benchmarkProtocol | 环境、版本、warmup、sample、duration、重复次数、噪声控制 |
| profilingEvidence | CPU/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
- 冻结当前基线、目标用户路径和不可牺牲的正确性/稳定性。
- 建立代表 workload；区分 cold/warm cache、steady/burst 和 local/CI/prod-like。
- 先测基线，再 profiling；禁止先改代码后寻找支持结论的数据。
- 一次改变一个主要变量，保留版本、硬件、配置、数据和命令。
- 同时看 latency distribution、throughput、errors、CPU/memory/I/O/GC 和尾延迟。
- 输出 capacity/headroom 与成本权衡；优化不能靠隐藏限流或丢请求。
- 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 |
|---|---|
| moduleProtocol | workload、budget、immutable baseline、candidate comparison |
| capacityResource | capacity/headroom、CPU/memory/I/O/GC、饱和点和成本 |
| stabilityRecovery | leak/pressure（适用时）、故障/冷却/恢复、正确性守恒 |
| maintenanceTriggers | PR、main、scheduled、RC、post-release 的触发与升级关系 |
| evidenceGovernance | retention、freshness、drift、owner、skip/N/A/flake 处理 |
| coverageState | total/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。
© devcodex-labs, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in content/skills/performance-engineering of devcodex-labs/devcodex.
- SKILL.md
- agents/openai.yaml
- intent.json
Open the folder on GitHubat commit 1dd4525
Compare with similar skills
Performance Engineering next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Performance Engineering this skilldevcodex-labs/devcodex | 439 | — | ~873 | Automated safety check: Pass | AGPL-3.0 | |
| Sglang Diffusion Benchmark Profilesgl-project/sglang | 37k | 2 repos | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Benchmarkaffaan-m/ECC | 274k | 3 repos | ~654 | Automated safety check: Pass | MIT | |
| Benchmarkaffaan-m/ECC | 274k | — | ~412 | Automated safety check: Pass | MIT | |
| Benchmarkaffaan-m/ECC | 274k | — | ~330 | Automated safety check: Pass | MIT | |
| Profileccusage/ccusage | 19k | — | ~430 | Automated safety check: Pass | Custom licence |
Similar skills
Benchmark
affaan-m/ECC
Measure performance baselines and detect regressions across browser Core Web Vitals (LCP, INP, CLS, page weight), API endpoint latency percentiles, and build/test feedback times, with before/after…
Benchmark
affaan-m/ECC
このスキルを使用して、パフォーマンスベースラインを測定し、PR前後の回帰を検出し、スタック代替案を比較します. An agent skill from affaan-m/ECC.
Benchmark
affaan-m/ECC
使用此技能测量性能基线，检测PR前后的回归，并比较堆栈替代方案。
Profile
ccusage/ccusage
Profiles ccusage performance. An agent skill from ccusage/ccusage.
Benchmark Methodology
affaan-m/ECC
Score a scoped competitor set into comparable profile cards: nine weighted dimensions (positioning, voice, visual craft, offer packaging, evidence, enterprise-readiness, thought leadership, pricing…
More from devcodex-labs/devcodex
All 70 skills in this repoAccessibility I18n
devcodex-labs/devcodex
无障碍与国际化专家 Owner — 当任务涉及可访问性、键盘操作、焦点、屏幕阅读器、ARIA、语言地区、本地化、RTL、翻译资源、用户可见文案或多语言文档时使用；要求把包容性体验和本地化验证绑定到真实用户路径。
AI Agent System Architecture
devcodex-labs/devcodex
AI Agent 系统架构专家 Owner — 当任务涉及 Agent 路由、工具调用、上下文管理、记忆、状态机、权限、人机协作、可观测性、回放验证或模型辅助治理时使用；要求把 Agent 行为设计成可解释、可恢复、可审计。
API Contract Architecture
devcodex-labs/devcodex
API 契约架构专家 Owner — 当任务涉及 public API、HTTP/SDK/CLI 契约、版本兼容、错误模型、分页过滤、幂等、Schema、类型、迁移或消费者影响时使用；要求先冻结消费者契约，再设计实现与验证。
Architecture Design
devcodex-labs/devcodex
架构设计文档编排 Owner — 当用户要求架构设计、系统设计、技术架构或可指导开发、Review 与任务拆分的完整方案时使用；要求从业务流程反推节点、状态、数据、一致性、异常补偿、ADR 与实施任务。
Audit Common
devcodex-labs/devcodex
审查公共维度 G0~G5 + Profile Freshness Check — 所有 audit 子类型必先执行的基础维度层
Audit Session
devcodex-labs/devcodex
审计工作流的跨会话状态机 — 在 <audit-root/.audit-state/<session-id.json 持久化轮次/发现项/收敛状态，支持 Token 中断后精准恢复
Questions about Performance Engineering
What does Performance Engineering 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。. Performance Engineering is an agent skill from devcodex-labs/devcodex.
How do I install Performance Engineering in Claude Code?
Run `npx skills add devcodex-labs/devcodex --skill performance-engineering -a claude-code`. Or copy the skill folder (content/skills/performance-engineering in devcodex-labs/devcodex) into .claude/skills/performance-engineering in your project. Claude Code loads it when a task matches its description.
How do I install Performance Engineering in Codex?
Run `npx skills add devcodex-labs/devcodex --skill performance-engineering -a codex`. Or copy the skill folder (content/skills/performance-engineering in devcodex-labs/devcodex) into .agents/skills/performance-engineering in your project. Codex loads it when a task matches its description.
Can I use Performance Engineering in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add devcodex-labs/devcodex --skill performance-engineering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/performance-engineering, .gemini/skills/performance-engineering, .github/skills/performance-engineering and .opencode/skills/performance-engineering in your project.
What does Performance Engineering need to run?
Going by SKILL.md and its folder, Performance Engineering needs the command-line tools its instructions call (npm).
Does Performance Engineering access the network?
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Performance Engineering safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Performance Engineering use?
Performance Engineering is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Performance Engineering use?
About 873 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Performance Engineering?
Skills that share tags, products or a category with Performance Engineering: Sglang Diffusion Benchmark Profile (sgl-project/sglang, 37k stars), Benchmark (affaan-m/ECC, 274k stars), Benchmark (affaan-m/ECC, 274k stars) and Benchmark (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Performance Engineering?
devcodex-labs (a GitHub organization) maintains it in devcodex-labs/devcodex, which has 439 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on September 17, 2026.
Source: devcodex-labs/devcodex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.