Agent skill

CI Perf PR Report

by OpenXiangShan in 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.

BSD-3-ClauseAuto-check passed

Install CI Perf PR Report

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

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

GitHub CLI
$ gh skill install OpenXiangShan/GEM5 ci-perf-pr-report --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-pr-report .claude/skills/ci-perf-pr-report && 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-pr-report
GitHub stars
162
Token cost
~462 tokens
SKILL.md length
133 words
Files
2
Skills in repo
10
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

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.

  • Works in 7 steps: 复用已有可追溯的归档和处理结果;需要定位或处理 CI 数据时读取… → 检查 candidate 和 baseline 的… → baseline 优先级:用户明确指定 > 同 SHA 的… → …
  • SKILL.md covers 输入, 工作流, PR 评论结构 and 完成标准
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

CI Perf PR Report is an agent skill from 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。

Its SKILL.md is about 460 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The licence is BSD-3-Clause.

Example prompts

  • “/ci-perf-pr-report”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. 复用已有可追溯的归档和处理结果;需要定位或处理 CI 数据时读取 ../ci-perf-analysis/SKILL.md。
  2. 检查 candidate 和 baseline 的 status、conclusion、SHA、workflow、配置、
  3. baseline 优先级:用户明确指定 > 同 SHA 的 feature-off control > 同配置的相邻
  4. 从原始 score.txt 和处理后的 CSV 交叉核对 Overall、SPECint、SPECfp;展开
  5. 只选择能解释 feature 的少量 stats
  6. 用重点 benchmark 和计数器证据解释收益/回退,区分确认事实、合理推断和未决问题。
  7. 生成简洁的英文 PR 评论;已有明确发布授权时直接发布并回查评论 URL,否则交付 draft。

What it can do on your machine

Read from SKILL.md and the folder at commit 0785475. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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 PR Report loads about 462 tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 133 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~17
When it runs · the whole SKILL.md, loaded when a task matches
~462

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 OpenXiangShan/GEM5 at commit 0785475, republished under its BSD-3-Clause licence (© OpenXiangShan). 133 words, ~462 tokens.

Download SKILL.mdSave it as .claude/skills/ci-perf-pr-report/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ci-perf-pr-report
description
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。

CI 性能 PR 报告

把已完成的性能 CI 转成可审阅、可追溯的 PR 评论。复用相邻的 ci-perf-analysis skill 取数;不包含 RTL 对齐或特定 predictor 分析。

输入

尽量取得:

  • candidate run URL/ID;
  • baseline run URL/ID,或足以定位 baseline 的 commit/config/profile;
  • 目标 PR;
  • feature 说明,以及是否明确授权发布评论。

缺少 baseline 时可以搜索,但不得静默选择口径不一致的 run。

工作流

  1. 复用已有可追溯的归档和处理结果;需要定位或处理 CI 数据时读取 ../ci-perf-analysis/SKILL.md。
  2. 检查 candidate 和 baseline 的 status、conclusion、SHA、workflow、配置、 benchmark/profile、coverage、extra args 和 abort 数。run 未完成时说明状态和缺口; 用户要求等待完成或持续跟进时才继续监控,不把“已创建”写成“已通过”。
  3. baseline 优先级:用户明确指定 > 同 SHA 的 feature-off control > 同配置的相邻 main/weekly baseline。若编译器、checkpoint、coverage 或关键参数不同,明确标注 confounder,不做严格因果归因。
  4. 从原始 score.txt 和处理后的 CSV 交叉核对 Overall、SPECint、SPECfp;展开 benchmark 子项的 raw delta 和相对变化,不只报告总分。
  5. 只选择能解释 feature 的少量 stats:
    • 通用:IPC/CPI、Topdown frontend/bad-spec/backend/memory;
    • 前端:fetch/recovery bubble、fragment stall、branch miss;
    • 后端/访存:dispatch stall、core/memory bound、cache MPKI/latency。 优先比较 rate、MPKI 或 weighted 指标;指令数不同时不要直接解释 raw count。
  6. 用重点 benchmark 和计数器证据解释收益/回退,区分确认事实、合理推断和未决问题。
  7. 生成简洁的英文 PR 评论;已有明确发布授权时直接发布并回查评论 URL,否则交付 draft。

PR 评论结构

markdown
## Performance result

- Candidate: <run, SHA, config/profile>
- Baseline: <run, SHA, config/profile>
- Completeness: <coverage, aborts>

### Score
| Suite | Baseline | Candidate | Change |

### Benchmark breakdown
<主要收益、回退及完整 suite 子项>

### Counter evidence
<少量与 feature 直接相关的 weighted stats>

### Interpretation
<结论、因果边界和剩余风险>

PR 评论中直接链接 Actions run;不要包含 Codex memory citation。若数据不完整,只准备状态更新;已有发布授权时才发布,不给最终性能结论。除非用户明确要求更新既有评论,否则发布一条新评论。

完成标准

  • 两组数据的比较口径已审计;
  • score 与 benchmark 子项已交叉核对;
  • 有可比 stats 时,至少一组相关计数器支持或限制结论;否则明确数据缺口;
  • 已授权时评论发布成功并返回 URL,否则提供可直接发布的 draft。

© 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 in .agents/skills/ci-perf-pr-report of OpenXiangShan/GEM5.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 0785475

Compare with similar skills

CI Perf PR Report 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 PR Report compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CI Perf PR Report this skillOpenXiangShan/GEM5162—~462Automated safety check: PassBSD-3-Clause
Build Perf Baselinedotnet/skills5.6k1 repos~3.6kAutomated safety check: PassMIT
Perf Baseline Managercomposio-community/awesome-claude-plugins1.9k—~167Automated safety check: PassNone
Build Perf Baselinemicrosoft/testfx1k—~3.1kAutomated safety check: PassMIT
Perf ComparisonClickHouse/ClickHouse50k—~3.9kAutomated safety check: NotesApache-2.0
Studio Perfremotion-dev/remotion63k—~370Automated safety check: PassCustom licence

Similar skills

  • Build Perf Baseline

    dotnet/skills

    Official

    Establish MSBuild/.NET build performance baselines before optimizing.

    5.6k GitHub starsUsed in 1 repo~3.6k tokens
    Backend & APIsAuto-check passed
  • Perf Baseline Manager

    composio-community/awesome-claude-plugins

    A skill your agent uses when managing perf baselines, consolidating results, or comparing versions.

    1.9k GitHub stars~167 tokensUpdated 2 mo ago
    Auto-check passed
  • Build Perf Baseline

    microsoft/testfx

    Official

    Establish build performance baselines and apply systematic optimization techniques.

    1k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check passed
  • 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 yesterday
    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

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.

    162 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.

    162 GitHub stars~629 tokensUpdated today
    Auto-check passed
  • CI Perf Analysis

    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.

    162 GitHub stars~545 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.

    162 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.

    162 GitHub stars~389 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。

    162 GitHub stars~763 tokensUpdated today
    Auto-check passed

Questions about CI Perf PR Report

What does CI Perf PR Report do?

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. CI Perf PR Report is an agent skill from OpenXiangShan/GEM5.

How do I install CI Perf PR Report in Claude Code?

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

How do I install CI Perf PR Report in Codex?

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

Can I use CI Perf PR Report 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-pr-report -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-pr-report, .gemini/skills/ci-perf-pr-report, .github/skills/ci-perf-pr-report and .opencode/skills/ci-perf-pr-report in your project.

What does CI Perf PR Report need to run?

SKILL.md names no scripts, command-line tools or credentials: CI Perf PR Report is instructions for the agent only.

Does CI Perf PR Report 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 PR Report 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 CI Perf PR Report use?

CI Perf PR Report 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 PR Report use?

About 462 tokens (SKILL.md is roughly 1.8k 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 PR Report?

Skills that share tags, products or a category with CI Perf PR Report: Build Perf Baseline (dotnet/skills, 5.6k stars), Perf Baseline Manager (composio-community/awesome-claude-plugins, 1.9k stars), Build Perf Baseline (microsoft/testfx, 1k stars) and Perf Comparison (ClickHouse/ClickHouse, 50k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CI Perf PR Report?

OpenXiangShan (a GitHub organization) maintains it in OpenXiangShan/GEM5, which has 162 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 10, 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.