Agent skill

Loadline

Running and analyzing LoadLine 1 and 2 benchmarks on Android using Crossbench.

BSD-3-ClauseAuto-check passedMobile

Install Loadline

skills CLI

$ npx skills add nwjs/chromium.src --skill loadline -a claude-code

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

GitHub CLI

$ gh skill install nwjs/chromium.src loadline --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/nwjs/chromium.src.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/skills/loadline .claude/skills/loadline && 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/

Paste into Claude Code

Install the "loadline" agent skill from https://github.com/nwjs/chromium.src/tree/main/agents/skills/loadline into .claude/skills/loadline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loadline", 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

$skill-installer install https://github.com/nwjs/chromium.src/tree/main/agents/skills/loadline

Type 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.

skills CLI

$ npx skills add nwjs/chromium.src --skill loadline -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install nwjs/chromium.src loadline --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nwjs/chromium.src.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agents/skills/loadline .agents/skills/loadline && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "loadline" agent skill from https://github.com/nwjs/chromium.src/tree/main/agents/skills/loadline into .agents/skills/loadline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loadline", 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.

skills CLI

$ npx skills add nwjs/chromium.src --skill loadline -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install nwjs/chromium.src loadline --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nwjs/chromium.src.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agents/skills/loadline .cursor/skills/loadline && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "loadline" agent skill from https://github.com/nwjs/chromium.src/tree/main/agents/skills/loadline into .cursor/skills/loadline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loadline", 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

$ gemini skills install https://github.com/nwjs/chromium.src.git --path agents/skills/loadline

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add nwjs/chromium.src --skill loadline -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install nwjs/chromium.src loadline --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nwjs/chromium.src.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agents/skills/loadline .gemini/skills/loadline && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "loadline" agent skill from https://github.com/nwjs/chromium.src/tree/main/agents/skills/loadline into .gemini/skills/loadline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loadline", 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.

GitHub CLI

$ gh skill install nwjs/chromium.src loadline

Installs 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).

skills CLI

$ npx skills add nwjs/chromium.src --skill loadline -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/nwjs/chromium.src.git skills-src && mkdir -p .github/skills && cp -r skills-src/agents/skills/loadline .github/skills/loadline && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "loadline" agent skill from https://github.com/nwjs/chromium.src/tree/main/agents/skills/loadline into .github/skills/loadline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loadline", 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.

skills CLI

$ npx skills add nwjs/chromium.src --skill loadline -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install nwjs/chromium.src loadline --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nwjs/chromium.src.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agents/skills/loadline .opencode/skills/loadline && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "loadline" agent skill from https://github.com/nwjs/chromium.src/tree/main/agents/skills/loadline into .opencode/skills/loadline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loadline", 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: loadline
GitHub stars: 160
Token cost: ~1.3k tokens
SKILL.md length: 473 words
Files: 2
Skills in repo: 64
Repo updated: Oct 3, 2026
First seen: Oct 8, 2026
Licence: BSD-3-Clause

At a glance

Running and analyzing LoadLine 1 and 2 benchmarks on Android using Crossbench.

Works in 4 steps: Build Chrome for Android with… → Uninstall existing Chrome Canary from… → Install the custom built Chrome: adb… → …
You need to measure page loading performance
SKILL.md covers Quick Start, Benchmark Variants, Target Browsers (--browser) and Stories (--stories), plus 2 more sections
Calls adb

What it does

Loadline is an agent skill from nwjs/chromium.src. Running and analyzing LoadLine 1 and 2 benchmarks on Android using Crossbench. Use when you need to measure page loading performance, evaluate performance-related changes in Chrome, or collect Perfetto traces with realistic Chrome workload.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in Mobile. It works with Android. The repository describes itself as: Chromium codebase with NW.js modifications. Based on https://chromium.googlesource.com/chromium/src.git. The licence is BSD-3-Clause.

When your agent uses it

You need to measure page loading performance
Evaluate performance-related changes in Chrome
Collect Perfetto traces with realistic Chrome workload

Example prompts

“/loadline”

Workflow steps

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

Build Chrome for Android with android_channel="canary" gn arg.
Uninstall existing Chrome Canary from the device
Install the custom built Chrome: adb install out/$OUT_DIR/apks/Chrome.apk
Run LoadLine on chrome-canary

What it can do on your machine

Read from SKILL.md and the folder at commit a9e8946. 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:
- adb
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

Loadline loads about 1.3k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 473 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~62
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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 nwjs/chromium.src at commit a9e8946, republished under its BSD-3-Clause licence (© nwjs). 473 words, ~1,253 tokens.

Download SKILL.mdSave it as .claude/skills/loadline/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: loadline
description: Running and analyzing LoadLine 1 and 2 benchmarks on Android using Crossbench. Use when you need to measure page loading performance, evaluate performance-related changes in Chrome, or collect Perfetto traces with realistic Chrome workload.

LoadLine Benchmark

This skill guides the usage of LoadLine benchmarks to measure browser page loading performance by simulating real-world user journeys (loading a web page).

Quick Start

Read third_party/crossbench/config/benchmark/loadline2/README.md for basic info on the LoadLine benchmark.

The entry point for all LoadLine benchmarks is the Crossbench script: third_party/crossbench/cb.py

Common Command Pattern

bash

third_party/crossbench/cb.py <variant> --browser=<browser> --stories=<stories> --repetitions=<N>

Benchmark Variants

Variant	Description
`loadline2-phone`	The latest LoadLine 2 benchmark optimized for mobile phones.
`loadline2-tablet`	LoadLine 2 benchmark optimized for tablets.
`loadline-phone`	Legacy LoadLine 1 benchmark for phones.
`loadline-tablet`	Legacy LoadLine 1 benchmark for tablets.
`*-debug`	Appends more tracing categories for easier debugging.

Target Browsers (`--browser`)

Android (Chrome): Use --browser=adb:chrome (if one device) or --browser=$SERIAL:chrome.
Local Build: Use the path to the output directory, e.g., --browser=out/Release/chrome.
System Chrome: Use --browser=chrome-stable, chrome-canary, etc.

Stories (`--stories`)

Default stories for LoadLine 2:

amazon_product
cnn_article
wikipedia_article
globo_homepage
google_search_result

Skip --stories flag to run everything or provide a comma-separated list for specific stories.

Analyzing Results

LoadLine outputs two kinds of numbers: scores and breakdown.

Scores are in runs-per-minute, so higher is better. The main metric is called TOTAL_SCORE, this is the most stable and representative number.

Breakdown values are in milliseconds, so lower is better. Can be useful for analyzing which loading stage was affected in particular.

Statistical Significance

Noise: Benchmark results are inherently noisy. A single repetition should only be used for smoke-testing.
Reliability: To confidently determine changes of 1% or higher, run the benchmark with at least 50 repetitions.
Interpretation: Changes below 1% are typically not considered statistically significant, even with 50 repetitions.

Identifying Tested Version

You can find the exact version of Chrome being tested in the benchmark logs by looking for the 🏷️ STARTING BROWSER Version: line:

🏷️  STARTING BROWSER Version: 138.0.7204.168 stable

Common Workflows

Show full SKILL.md (195 more words)Show less

Full Basic Run

Run the full benchmark on a connected Android device:

bash

third_party/crossbench/cb.py loadline2-phone --browser=adb:chrome

Test a feature flag

See if a feature flag affects page loading performance:

bash

third_party/crossbench/cb.py loadline2-phone --browser-config=feature_flag.hjson

where feature_flag.hjson looks like this:

{
  flags: {
    "experiment": {
      "enabled": "--enable-features=YourFeature",
      "disabled": "--disable-features=YourFeature",
    },
  },
  browsers: {
    "chrome": {
      browser: "chrome",
      driver: "adb",
      flags: [ "experiment" ],
    },
  },
}

Compare past versions of Chrome

Check if clank/bin/install_chrome.py exists. If not (chromium-only checkouts), see the next section for building Chromium locally.

Use clank/bin/install_chrome.py to install past versions on the connected device. E.g.

clank/bin/install_chrome.py --channel dev --milestone 146 --signed

will install M146 with "Dev" channel branding. You can use multiple brandings to compare versions on the same device. E.g. install Canary:

clank/bin/install_chrome.py --channel canary --milestone 147 --signed

And then run LoadLine with two browsers:

third_party/crossbench/cb.py loadline2-phone --browser=adb:chrome-dev --browser=adb:chrome-canary

This will compare M146 and M147 on the same device.

Custom-built Chrome

Build Chrome for Android with android_channel="canary" gn arg.
Uninstall existing Chrome Canary from the device: adb shell pm uninstall com.chrome.canary (this command fails if it's not installed; this is fine and can be ignored)
Install the custom built Chrome: adb install out/$OUT_DIR/apks/Chrome.apk
Run LoadLine on chrome-canary: third_party/crossbench/cb.py loadline2-phone --browser=adb:chrome-canary

Short run

Before running a full run on a custom-built Chrome, first try with a single repetition

bash

third_party/crossbench/cb.py loadline2-phone --browser=adb:chrome-canary --repetitions=1

Don't trust the numbers, they are going to be very noisy. Do it just to verify that the benchmark runs without errors.

Files

SKILL.md and 1 other file in agents/skills/loadline of nwjs/chromium.src.

SKILL.md
OWNERS

Open the folder on GitHubat commit a9e8946

Compare with similar skills

Loadline 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.

Loadline compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Loadline this skillnwjs/chromium.src	160	—	~1.3k	Automated safety check: Pass	BSD-3-Clause	4 days ago
Compose Multiplatform Patternsmonta-app/ocpp-emulator	180	5 repos	~2k	Automated safety check: Pass	Apache-2.0	7 days ago
Phone HarnessShawnPana/phone-harness	3.2k	—	~4.3k	Automated safety check: Pass	MIT	10 days ago
Stylesarindamxd/camerax-android	132	4 repos	~2.3k	Automated safety check: Pass	Apache-2.0	6 days ago
Verified Emailarindamxd/camerax-android	132	4 repos	~4.7k	Automated safety check: Pass	Apache-2.0	6 days ago
Argent Metro Debuggerbbplayer-app/BBPlayer	1.1k	—	~3.4k	Automated safety check: Pass	MIT	today

Similar skills

Compose Multiplatform Patterns
monta-app/ocpp-emulator
Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI.
180 GitHub starsUsed in 5 repos~2k tokens
MobileAuto-check passed
Phone Harness
ShawnPana/phone-harness
Control the user's phone — an iPhone through the Mac's iPhone Mirroring window, an Android over adb, or a rented cloud Android: open apps, tap, type, swipe, read the screen.
3.2k GitHub stars~4.3k tokensUpdated 10 days ago
MobileAuto-check passed
Styles
arindamxd/camerax-android
A skill your agent uses to integrate the Jetpack Compose Styles API into an Android project.
132 GitHub starsUsed in 4 repos~2.3k tokens
MobileAuto-check passed
Verified Email
arindamxd/camerax-android
Provides a complete workflow for implementing verified email retrieval on Android Credential Manager API.
132 GitHub starsUsed in 4 repos~4.7k tokens
MobileAuto-check passed
Argent Metro Debugger
bbplayer-app/BBPlayer
Debug a JS runtime via CDP using argent debugger tools. An agent skill from bbplayer-app/BBPlayer.
1.1k GitHub stars~3.4k tokensUpdated today
MobileAuto-check passed
Android XML Resource
afkT/DevUtils
统一 Android XML 资源命名：layout、drawable、mipmap、color、values、id 的前缀与 snakecase 规则；把颜色/圆角/描边/状态编码进文件名（bg、border、textcolor…selector）。
1.6k GitHub stars~1.3k tokensUpdated 1 mo ago
MobileAuto-check passed

More from nwjs/chromium.src

All 64 skills in this repo

Analyzing SQL Traces
nwjs/chromium.src
Extracts raw trace data from Perfetto traces, runs arbitrary SQL queries for custom follow-up analysis, and applies expert cognitive principles (Tiered Flow Analysis, Semantic Mismatch, Redundancy)…
160 GitHub stars~2.9k tokensUpdated 4 days ago
Auto-check passed
Chrome Performance Optimizer
nwjs/chromium.src
Autonomous multi-agent performance optimization loop for Chromium and V8.
160 GitHub stars~4.2k tokensUpdated 4 days ago
Auto-check passed
Automated Tracing
nwjs/chromium.src
Automated Tracing & Performance Telemetry in Chromium using Perfetto and Telemetry benchmarks.
160 GitHub stars~1.5k tokensUpdated 4 days ago
Auto-check passed
Chrome Releases
nwjs/chromium.src
Queries Chrome commit, version, release, and milestone metadata.
160 GitHub stars~1.3k tokensUpdated 4 days ago
Auto-check passed
Chromium Docs
nwjs/chromium.src
Search and reference Chromium documentation from the local docs index, including design docs, APIs, and development guides.
160 GitHub stars~1.2k tokensUpdated 4 days ago
Auto-check passed
Gn Deps Debugging
nwjs/chromium.src
Diagnose Chromium GN dependency and include-visibility failures, including BUILD.gn deps/publicdeps, DEPS include rules, private headers, and circular dependencies.
160 GitHub stars~1.5k tokensUpdated 4 days ago
Auto-check passed

Works with

Android

Questions about Loadline

What does Loadline do?

Running and analyzing LoadLine 1 and 2 benchmarks on Android using Crossbench. src. Running and analyzing LoadLine 1 and 2 benchmarks on Android using Crossbench.

When should I use Loadline?

Loadline fits situations like: you need to measure page loading performance; evaluate performance-related changes in Chrome; collect Perfetto traces with realistic Chrome workload.

How do I install Loadline in Claude Code?

Run `npx skills add nwjs/chromium.src --skill loadline -a claude-code`. Or copy the skill folder (agents/skills/loadline in nwjs/chromium.src) into .claude/skills/loadline in your project. Claude Code loads it when a task matches its description.

How do I install Loadline in Codex?

Run `npx skills add nwjs/chromium.src --skill loadline -a codex`. Or copy the skill folder (agents/skills/loadline in nwjs/chromium.src) into .agents/skills/loadline in your project. Codex loads it when a task matches its description.

Can I use Loadline 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 nwjs/chromium.src --skill loadline -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loadline, .gemini/skills/loadline, .github/skills/loadline and .opencode/skills/loadline in your project.

What does Loadline need to run?

Going by SKILL.md and its folder, Loadline needs the command-line tools its instructions call (adb).

Does Loadline 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 Loadline 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 Loadline use?

Loadline 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 Loadline use?

About 1.3k tokens (SKILL.md is roughly 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 Loadline?

Skills that share tags, products or a category with Loadline: Compose Multiplatform Patterns (monta-app/ocpp-emulator, 180 stars), Phone Harness (ShawnPana/phone-harness, 3.2k stars), Styles (arindamxd/camerax-android, 132 stars) and Verified Email (arindamxd/camerax-android, 132 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Loadline?

nwjs (a GitHub organization) maintains it in nwjs/chromium.src, which has 160 GitHub stars. The repository holds 64 skills in this directory. The repository was last updated on October 3, 2026.

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

Install Loadline

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

LoadLine Benchmark

Quick Start

Common Command Pattern

Benchmark Variants

Target Browsers (--browser)

Stories (--stories)

Analyzing Results

Statistical Significance

Identifying Tested Version

Common Workflows

Full Basic Run

Test a feature flag

Compare past versions of Chrome

Custom-built Chrome

Short run

Files

Compare with similar skills

Similar skills

More from nwjs/chromium.src

Related

Questions about Loadline

Target Browsers (`--browser`)

Stories (`--stories`)