New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

CI Perf Analysis

by OpenXiangShan in OpenXiangShan/GEM5

定位 GEM5 性能 CI 的归档与分数，比较 run 的 benchmark 表现并用 stats 分析变化. An agent skill from OpenXiangShan/GEM5.

BSD-3-ClauseAuto-check passed

Install CI Perf Analysis

skills CLI
$ npx skills add OpenXiangShan/GEM5 --skill ci-perf-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OpenXiangShan/GEM5 ci-perf-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OpenXiangShan/GEM5.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ci-perf-analysis .claude/skills/ci-perf-analysis && rm -rf skills-src

Use ~/.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/

Facts

Skill name
ci-perf-analysis
GitHub stars
161
Token cost
~545 tokens
SKILL.md length
155 words
Files
2 (incl. scripts)
Skills in repo
10
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

定位 GEM5 性能 CI 的归档与分数，比较 run 的 benchmark 表现并用 stats 分析变化. An agent skill from OpenXiangShan/GEM5.

  • Works in 4 steps: 定位归档 → 选择 gem5_data_proc → 处理归档 → …
  • SKILL.md covers 概览, 1. 定位归档, 2. 选择 gem5_data_proc and 3. 处理归档, plus 3 more sections
  • Runs Python scripts from its folder; calls python3

What it does

CI Perf Analysis is an agent skill from OpenXiangShan/GEM5. 定位 GEM5 性能 CI 的归档与分数，比较 run 的 benchmark 表现并用 stats 分析变化。

Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/ci_perf_info.py`).

The licence is BSD-3-Clause.

Example prompts

  • “/ci-perf-analysis”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. 定位归档
  2. 选择 gem5_data_proc
  3. 处理归档
  4. 比较两个 run

What it can do on your machine

Read from SKILL.md and the folder at commit 096f9e1. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

CI Perf Analysis loads about 545 tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 155 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~18
When it runs · the whole SKILL.md, loaded when a task matches
~545

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); the scripts in this folder are not scanned.

SKILL.md

The full file from OpenXiangShan/GEM5 at commit 096f9e1, republished under its BSD-3-Clause licence (© OpenXiangShan). 155 words, ~545 tokens.

Download SKILL.mdSave it as .claude/skills/ci-perf-analysis/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ci-perf-analysis
description
定位 GEM5 性能 CI 的归档与分数，比较 run 的 benchmark 表现并用 stats 分析变化。

CI 性能分析

概览

这个 skill 处理以下链路：

  1. 从 CI run 的所有 jobs 中定位真实性能归档目录和 score.txt。
  2. 用本地 gem5_data_proc/run.py 生成 CSV、weighted CSV 和 score CSV。
  3. 对比 benchmark 级变化；必要时再下钻 stats.txt。

1. 定位归档

优先使用仓库内脚本：

bash
python3 .agents/skills/ci-perf-analysis/scripts/ci_perf_info.py \
  https://github.com/OpenXiangShan/GEM5/actions/runs/<run_id>

脚本会遍历 run 的 jobs，并兼容当前和旧版 workflow 的归档日志格式。输出包括：

  • job_id 和 job_name
  • archive_path
  • spec_all
  • 本地可访问时的 score.txt 尾部

不要默认取第一个 job，也不要从日志中的示例文本推断归档位置。

非默认仓库可使用 --repo <owner/repo>。

2. 选择 gem5_data_proc

路径优先级：

  1. 用户明确给出的路径
  2. 环境变量 GEM5_DATA_PROC_HOME
  3. 本机常见默认值 /nfs/home/yanyue/workspace/gem5_data_proc
bash
export GEM5_DATA_PROC_HOME="${GEM5_DATA_PROC_HOME:-/nfs/home/yanyue/workspace/gem5_data_proc}"
test -f "$GEM5_DATA_PROC_HOME/run.py"

若以上路径均不可用，先说明缺失并征得用户同意，再安装或 clone；不要把个人 home 路径当成所有机器的前提。

3. 处理归档

始终使用步骤 1 返回的完整 <archive_path>，不要手写固定的 benchmark 套件目录：

bash
python3 "$GEM5_DATA_PROC_HOME/run.py" <archive_path> \
  --out-dir /tmp/gem5_proc_runA \
  --tag runA

常用输出：

  • <tag>.csv：原始 point 或 benchmark 聚合结果
  • <tag>-weighted.csv：按权重聚合的 benchmark 统计
  • <tag>-score.csv：score、time 和 coverage

若 run.py 在个别 point 上报数据处理异常，但已生成 score.txt 或部分 CSV，要明确标注数据缺口；不要把部分输出说成完整成功。

4. 比较两个 run

bash
python3 .agents/skills/ci-perf-analysis/scripts/ci_perf_info.py <runA>
python3 .agents/skills/ci-perf-analysis/scripts/ci_perf_info.py <runB>

python3 "$GEM5_DATA_PROC_HOME/run.py" <archiveA> \
  --out-dir /tmp/gem5_proc_A --tag A
python3 "$GEM5_DATA_PROC_HOME/run.py" <archiveB> \
  --out-dir /tmp/gem5_proc_B --tag B

分析顺序：

  1. 固定 commit、workflow、配置和 workload 口径。
  2. 比较总 score、time 和 coverage。
  3. 按 benchmark 的 score/time delta 排序。
  4. 从 weighted CSV 查看前端、后端、内存和分支等指标。
  5. 只对重点 benchmark 下钻 <archive_path>/spec_all/<slice>/m5out/stats.txt。

输出要求

回答优先给出：

  1. run、commit、配置和 workload 差异
  2. 总分变化
  3. 主要收益和回退 benchmark
  4. 相关 stats 证据
  5. 根因判断与未决风险

区分事实、推断和数据缺口。尤其不要把“run 已创建”写成“性能 CI 已通过”。

资源

  • scripts/ci_perf_info.py：从 run URL 或 ID 定位归档路径并打印 score 尾部。

© OpenXiangShan, BSD-3-Clause. 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 1 other file (scripts) in .agents/skills/ci-perf-analysis of OpenXiangShan/GEM5.

  • SKILL.md
  • scripts/ci_perf_info.py

Open the folder on GitHubat commit 096f9e1

Compare with similar skills

CI Perf Analysis 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.

CI Perf Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CI Perf Analysis this skillOpenXiangShan/GEM5161—~545Automated safety check: PassBSD-3-Clause
Perf ComparisonClickHouse/ClickHouse50k—~3.9kAutomated safety check: NotesApache-2.0
Studio Perfremotion-dev/remotion63k—~370Automated safety check: PassCustom licence
Perf ReportClickHouse/ClickHouse50k—~2.6kAutomated safety check: NotesApache-2.0
Perfhashgraph-online/awesome-codex-plugins1.3k—~3.2kAutomated safety check: PassApache-2.0
Perf Labs Perfperf-labs/perf110—~5.3kAutomated safety check: NotesMIT

Similar skills

  • Perf Comparison

    ClickHouse/ClickHouse

    Evaluate ClickHouse performance test results from existing CI/dashboard data or local perf.py runs.

    50k GitHub stars~3.9k tokensUpdated today
    DatabasesAuto-check: notes

  • Studio Perf

    remotion-dev/remotion

    Official

    Optimize Remotion Studio render performance by minimizing frame-reactive component surfaces, preferring imperative timeline state reads, and memoizing stable render boundaries.

    63k GitHub stars~370 tokensUpdated today
    Media & CreativeAuto-check passed

  • Perf Report

    ClickHouse/ClickHouse

    Analyze CI performance comparison reports for a ClickHouse PR.

    50k GitHub stars~2.6k tokensUpdated today
    DatabasesAuto-check: notes

  • Perf

    hashgraph-online/awesome-codex-plugins

    Make a studio's game run faster with a measured loop, and keep only what really helped.

    1.3k GitHub stars~3.2k tokensUpdated today
    Auto-check passed

  • Perf Labs Perf

    perf-labs/perf

    Performance engineering on x86-64 Linux with the perf-labs/perf toolkit (perf benchmark, perf profile, perf analyze, perf view, perf plot, perf compare, perf info) and system perf.

    110 GitHub stars~5.3k tokensUpdated today
    Auto-check: notes

  • PlotJuggler 4 Perf Profiling

    PlotJuggler/PlotJuggler

    Guides CPU profiling of PlotJuggler 4 on Linux with perf: count first, record cheaply with LBR, then read per-thread, flat, flamegraph or time-window views.

    6.2k GitHub stars~1.6k tokensUpdated 8 days ago
    DevelopmentAuto-check: notes

More from OpenXiangShan/GEM5

All 10 skills in this repo

  • Mgsc Table Probe

    OpenXiangShan/GEM5

    运行或分析 MGSC 微测试的 SC 子表 A/B 实验，用分支与 MGSCTRACE 统计归因并改进测试. An agent skill from OpenXiangShan/GEM5.

    161 GitHub stars~628 tokensUpdated today
    Auto-check passed

  • Tage Trace Workflow

    OpenXiangShan/GEM5

    采集或分析 gem5/XiangShan TAGE trace，比较统计、热点分支和事件分叉. An agent skill from OpenXiangShan/GEM5.

    161 GitHub stars~629 tokensUpdated today
    Auto-check passed

  • Frontend Pmu Analysis

    OpenXiangShan/GEM5

    仅做 BPU 计数器提取与批量汇总（机器可读 JSON/CSV）。配置文件只需要写原始 stats 计数器名. An agent skill from OpenXiangShan/GEM5.

    161 GitHub stars~305 tokensUpdated today
    Auto-check passed

  • CI Param Solver

    OpenXiangShan/GEM5

    编写或校验 GEM5 SolveSpec 参数搜索，并按请求准备或触发 manual-solve.yml. An agent skill from OpenXiangShan/GEM5.

    161 GitHub stars~389 tokensUpdated today
    Auto-check passed

  • CI Perf PR Report

    OpenXiangShan/GEM5

    为 GEM5 PR 准备或发布性能对比报告，选择可比 baseline 并汇总分数与关键计数器证据. An agent skill from OpenXiangShan/GEM5.

    161 GitHub stars~462 tokensUpdated today
    Auto-check passed

  • Gem5 Manual Perf Trigger

    OpenXiangShan/GEM5

    用于在本地通过 gh 远程触发 OpenXiangShan/GEM5 的 manual-perf.yml，并在触发后检查 run 是否正常创建。适用于用户明确要求触发 manual-perf、组装 gh workflow run 命令、校验 workflow 输入项、或确认触发后的 Actions run 状态。

    161 GitHub stars~763 tokensUpdated today
    Auto-check passed

Questions about CI Perf Analysis

What does CI Perf Analysis do?

定位 GEM5 性能 CI 的归档与分数，比较 run 的 benchmark 表现并用 stats 分析变化. An agent skill from OpenXiangShan/GEM5. CI Perf Analysis is an agent skill from OpenXiangShan/GEM5.

How do I install CI Perf Analysis in Claude Code?

Run `npx skills add OpenXiangShan/GEM5 --skill ci-perf-analysis -a claude-code`. Or copy the skill folder (.agents/skills/ci-perf-analysis in OpenXiangShan/GEM5) into .claude/skills/ci-perf-analysis in your project. Claude Code loads it when a task matches its description.

How do I install CI Perf Analysis in Codex?

Run `npx skills add OpenXiangShan/GEM5 --skill ci-perf-analysis -a codex`. Or copy the skill folder (.agents/skills/ci-perf-analysis in OpenXiangShan/GEM5) into .agents/skills/ci-perf-analysis in your project. Codex loads it when a task matches its description.

Can I use CI Perf Analysis 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 OpenXiangShan/GEM5 --skill ci-perf-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ci-perf-analysis, .gemini/skills/ci-perf-analysis, .github/skills/ci-perf-analysis and .opencode/skills/ci-perf-analysis in your project.

What does CI Perf Analysis need to run?

Going by SKILL.md and its folder, CI Perf Analysis needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does CI Perf Analysis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is CI Perf Analysis 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does CI Perf Analysis use?

CI Perf Analysis is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does CI Perf Analysis use?

About 545 tokens (SKILL.md is roughly 2.2k 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 CI Perf Analysis?

Skills that share tags, products or a category with CI Perf Analysis: Perf Comparison (ClickHouse/ClickHouse, 50k stars), Studio Perf (remotion-dev/remotion, 63k stars), Perf Report (ClickHouse/ClickHouse, 50k stars) and Perf (hashgraph-online/awesome-codex-plugins, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CI Perf Analysis?

OpenXiangShan (a GitHub organization) maintains it in OpenXiangShan/GEM5, which has 161 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 9, 2026.

Source: OpenXiangShan/GEM5 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.