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

Gem5 Manual Perf Trigger

by OpenXiangShan in 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。

BSD-3-ClauseAuto-check passed

Install Gem5 Manual Perf Trigger

skills CLI
$ npx skills add OpenXiangShan/GEM5 --skill gem5-manual-perf-trigger -a claude-code

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

GitHub CLI
$ gh skill install OpenXiangShan/GEM5 gem5-manual-perf-trigger --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/gem5-manual-perf-trigger .claude/skills/gem5-manual-perf-trigger && 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
gem5-manual-perf-trigger
GitHub stars
162
Token cost
~763 tokens
SKILL.md length
188 words
Files
2
Skills in repo
10
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

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。

  • Works in 4 steps: 读取目标 ref 的 workflow → 校验环境和参数 → 组装和触发 → …
  • SKILL.md covers 原则, 1. 读取目标 ref 的 workflow, 2. 校验环境和参数 and 3. 组装和触发, plus 3 more sections
  • Calls gh and git

What it does

Gem5 Manual Perf Trigger is an agent skill from 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。

Its SKILL.md is about 760 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

  • “/gem5-manual-perf-trigger”

Workflow steps

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

  1. 读取目标 ref 的 workflow
  2. 校验环境和参数
  3. 组装和触发
  4. 找到并检查新 run

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

    Shell commands in SKILL.md call:

    • gh
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use gh and git, 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

Gem5 Manual Perf Trigger loads about 763 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 188 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~763

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). 188 words, ~763 tokens.

Download SKILL.mdSave it as .claude/skills/gem5-manual-perf-trigger/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
gem5-manual-perf-trigger
description
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。

GEM5 Manual Perf Trigger

原则

manual-perf.yml 会持续变化，workflow 文件本身才是输入项、默认值和 choice 选项的事实来源。不要把这份 skill 中的历史选项当成固定接口。

区分两类请求：

  • 用户只要求校验或组装命令：只做只读检查并返回命令。
  • 用户明确要求触发：完成必要预检后直接触发，不再重复索要一次确认；触发后必须回查 run。

1. 读取目标 ref 的 workflow

先确定仓库和目标 ref，再读取本地及远端版本：

bash
sed -n '1,180p' .github/workflows/manual-perf.yml
gh workflow view manual-perf.yml \
  --repo OpenXiangShan/GEM5 \
  --ref <workflow-ref> \
  --yaml

以实际触发 ref 上的 workflow_dispatch.inputs 为准。当前常见字段包括：

  • note
  • configuration
  • benchmark_type
  • specific_benchmarks
  • extra_args
  • distributed_servers
  • distributed_jobs_per_server
  • branch

这只是字段示例，不替代读取 workflow。若目标 ref 尚未 push，远端无法使用该版本的 workflow。

特别检查 workflow 内的派生逻辑。例如当前 SMT benchmark 类型会强制选择 smt_idealkmhv3.py，此时用户传入的普通 configuration 不决定最终配置；报告中应把这一点说清楚。

2. 校验环境和参数

检查：

bash
gh --version
gh auth status
git rev-parse --abbrev-ref HEAD
git remote -v

沙箱中的 gh auth status 可能与正常 shell 不同；认证异常时先在正常 shell 复核，不要仅凭一次沙箱结果断言 token 已失效。

参数规则：

  • --ref 决定使用哪个远端 ref 上的 workflow 文件。
  • branch 决定 workflow 实际测试的 branch、tag 或 SHA；留空时通常使用 dispatch ref 的 SHA，具体看目标 workflow。
  • choice/required/default 均从目标 workflow 读取。
  • specific_benchmarks 为空通常表示跑所选集合的全部 benchmark。
  • extra_args 必须作为单个 -f 参数传递，避免 shell 拆词。
  • 不补猜用户没有表达的 workload 子集；可安全采用 workflow 明示的默认值。

触发前给出一段简短摘要：workflow ref、被测 ref、配置、benchmark 集合、子集以及额外参数。若这些信息会导致明显不同的实验，且无法从请求或 workflow 默认值确定，再向用户补问。

3. 组装和触发

标准形式：

bash
gh workflow run manual-perf.yml \
  --repo OpenXiangShan/GEM5 \
  --ref <workflow-ref> \
  -f configuration=<configuration> \
  -f benchmark_type=<benchmark_type> \
  -f specific_benchmarks=<specific_benchmarks> \
  -f 'extra_args=<extra_args>' \
  -f distributed_servers=<servers> \
  -f distributed_jobs_per_server=<jobs> \
  -f branch=<tested-ref>

只传需要覆盖的字段即可；让 workflow defaults 处理其余字段。不要因为旧 skill 没列出某个新选项就拒绝它，只要目标 workflow 明确支持。

4. 找到并检查新 run

gh workflow run 通常不直接返回 run ID。记录触发时间，然后从 workflow-dispatch runs 中匹配目标 head branch、创建时间和 run 名称：

bash
gh run list \
  --repo OpenXiangShan/GEM5 \
  --workflow manual-perf.yml \
  --event workflow_dispatch \
  --limit 20 \
  --json databaseId,createdAt,status,conclusion,url,name,displayTitle,headBranch,headSha

定位后读取：

bash
gh run view <run-id> \
  --repo OpenXiangShan/GEM5 \
  --json status,conclusion,url,name,headBranch,headSha

至少报告 URL、run ID、head、status 和 conclusion。queued 或 in_progress 只表示已创建并开始排队/执行，不等于通过。若用户只要求触发且无需持续盯守，确认 run 存在后停止轮询。

失败处理

  • gh 缺失：说明需要安装 GitHub CLI；不要静默改用未校验的 REST 脚本。
  • 认证失败：提示在正常 shell 复核 gh auth status。
  • 目标 ref 不存在：要求先 push 或改用已有 ref。
  • 输入不被接受：重新读取该 ref 的 workflow，核对字段名、choice 和类型。
  • 找不到新 run：检查 workflow ref、触发时间、head branch 和 token 的 Actions 权限；不要声称已经成功触发。

输出要求

清楚区分：准备触发、dispatch 已提交、run 已创建、run 已完成。没有最终 conclusion=success 时，不写“CI 已通过”。

© 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/gem5-manual-perf-trigger of OpenXiangShan/GEM5.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 0785475

Compare with similar skills

Gem5 Manual Perf Trigger 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.

Gem5 Manual Perf Trigger compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gem5 Manual Perf Trigger this skillOpenXiangShan/GEM5162—~763Automated safety check: PassBSD-3-Clause
Perf ComparisonClickHouse/ClickHouse50k—~3.9kAutomated safety check: NotesApache-2.0
Spreadsheet Manual Buildsickn33/agentic-awesome-skills47k1 repos~5.4kAutomated safety check: PassMIT
JSON Schema Manualsickn33/agentic-awesome-skills47k1 repos~2.9kAutomated safety check: PassMIT
CSV Manual Exportsickn33/agentic-awesome-skills47k1 repos~5.6kAutomated safety check: PassMIT
Notion Manual Importsickn33/agentic-awesome-skills47k1 repos~3.8kAutomated safety check: PassMIT

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

  • Spreadsheet Manual Build

    sickn33/agentic-awesome-skills

    Spreadsheet Manual Build: an empty Excel workbook or CSV from a confirmed field list, formatted and validated.

    47k GitHub starsUsed in 1 repo~5.4k tokens
    Documents & OfficeAuto-check passed

  • JSON Schema Manual

    sickn33/agentic-awesome-skills

    JSON Schema Manual: draft 2020-12 validation schema from a confirmed field list, with required and enum values only where confirmed.

    47k GitHub starsUsed in 1 repo~2.9k tokens
    Auto-check passed

  • CSV Manual Export

    sickn33/agentic-awesome-skills

    CSV Manual Export: a UTF-8 CSV template from a confirmed field list, empty by default, with no invented columns or values.

    47k GitHub starsUsed in 1 repo~5.6k tokens
    Documents & OfficeAuto-check passed

  • Notion Manual Import

    sickn33/agentic-awesome-skills

    Notion Manual Import: the Notion step for any module - CSV, property mapping, import steps and verification for the field list the active module confirmed.

    47k GitHub starsUsed in 1 repo~3.8k tokens
    Documents & OfficeAuto-check passed

  • 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

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

  • 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.

    162 GitHub stars~462 tokensUpdated today
    Auto-check passed

Questions about Gem5 Manual Perf Trigger

What does Gem5 Manual Perf Trigger do?

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。. Gem5 Manual Perf Trigger is an agent skill from OpenXiangShan/GEM5.

How do I install Gem5 Manual Perf Trigger in Claude Code?

Run `npx skills add OpenXiangShan/GEM5 --skill gem5-manual-perf-trigger -a claude-code`. Or copy the skill folder (.agents/skills/gem5-manual-perf-trigger in OpenXiangShan/GEM5) into .claude/skills/gem5-manual-perf-trigger in your project. Claude Code loads it when a task matches its description.

How do I install Gem5 Manual Perf Trigger in Codex?

Run `npx skills add OpenXiangShan/GEM5 --skill gem5-manual-perf-trigger -a codex`. Or copy the skill folder (.agents/skills/gem5-manual-perf-trigger in OpenXiangShan/GEM5) into .agents/skills/gem5-manual-perf-trigger in your project. Codex loads it when a task matches its description.

Can I use Gem5 Manual Perf Trigger 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 gem5-manual-perf-trigger -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gem5-manual-perf-trigger, .gemini/skills/gem5-manual-perf-trigger, .github/skills/gem5-manual-perf-trigger and .opencode/skills/gem5-manual-perf-trigger in your project.

What does Gem5 Manual Perf Trigger need to run?

Going by SKILL.md and its folder, Gem5 Manual Perf Trigger needs the command-line tools its instructions call (gh and git).

Does Gem5 Manual Perf Trigger access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Gem5 Manual Perf Trigger 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 Gem5 Manual Perf Trigger use?

Gem5 Manual Perf Trigger 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 Gem5 Manual Perf Trigger use?

About 763 tokens (SKILL.md is roughly 3.1k 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 Gem5 Manual Perf Trigger?

Skills that share tags, products or a category with Gem5 Manual Perf Trigger: Perf Comparison (ClickHouse/ClickHouse, 50k stars), Spreadsheet Manual Build (sickn33/agentic-awesome-skills, 47k stars), JSON Schema Manual (sickn33/agentic-awesome-skills, 47k stars) and CSV Manual Export (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gem5 Manual Perf Trigger?

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.