Agent skill

Speedupskill

by jjcm in jjcm/makefaster

Use this when speeding up a web or Electron app's load or input.

No licenceAuto-check passedFrontend & Design

Install Speedupskill

skills CLI
$ npx skills add jjcm/makefaster --skill speedupskill -a claude-code

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

GitHub CLI
$ gh skill install jjcm/makefaster speedupskill --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/jjcm/makefaster.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill .claude/skills/speedupskill && 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
speedupskill
GitHub stars
162
Token cost
~4.8k tokens
SKILL.md length
2,737 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
None found

At a glance

Use this when speeding up a web or Electron app's load or input.

  • Works in 7 steps: Do not wait on unused workspace data —… → Cut the critical JS graph to the first… → Stop the warm 304 storm → …
  • Tasks that involve Web performance
  • SKILL.md covers Run it as a packaged loop: npx…, Impact: largest (boot payload…, Impact: large (images, LCP,… and Impact: input path (Electron /…, plus 4 more sections
  • Calls npx

What it does

Speedupskill is an agent skill from jjcm/makefaster. Use this when speeding up a web or Electron app's load or input. Concrete techniques that moved the needle in measured speed labs (DiffUI boot/LCP, bb large-paste jank) — not generic advice.

Its SKILL.md is about 4.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

It sits in Frontend & Design, covering Web performance and Mobile performance. It works with Electron. The repository describes itself as: Make Faster — website performance tools and site leaderboard.

When your agent uses it

  • Tasks that involve Web performance
  • Tasks that involve Mobile performance

Example prompts

  • “/speedupskill”

Requirements

  • Node.js

Workflow steps

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

  1. Do not wait on unused workspace data — embed what this route needs
  2. Cut the critical JS graph to the first view
  3. Stop the warm 304 storm
  4. Serve the rung that matches the CSS slot
  5. Immutable / success-only cache for write-once /files/
  6. Large paste: O(n) parse, no full-text rescan per keystroke
  7. ThumbHash: average color now, budgeted decode, encode off the GET path

What it can do on your machine

Read from SKILL.md and the folder at commit ac0d115. 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:

    • npx

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

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    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

Speedupskill loads about 4.8k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 2,737 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~4.8k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 2,737 words (~4,812 tokens).

“When to use: the job is to make a web or Electron app faster to load or to type into — first content, LCP, TBT, or input latency after a large paste. Not visual polish, not ink/bleed filters, not a…”

— opening of SKILL.md by jjcm
name
speedupskill

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in skill of jjcm/makefaster.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit ac0d115

Compare with similar skills

Speedupskill 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.

Speedupskill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Speedupskill this skilljjcm/makefaster162—~4.8kAutomated safety check: PassNone
Web Performancemillionco/debug-agent303—~4.8kAutomated safety check: PassMIT
Optimize Loadtextura-agency/next16-claude-starter132—~4.6kAutomated safety check: NotesUnlicense
React Native Best Practicescallstackincubator/agent-skills1.7k4 repos~3.1kAutomated safety check: PassMIT
Production Bundle Auditkeybase/client9.3k—~620Automated safety check: PassBSD-3-Clause
React Doctormakeplane/plane60k12 repos~657Automated safety check: PassAGPL-3.0

Similar skills

  • Web Performance

    millionco/debug-agent

    A skill your agent uses when the user reports jank, dropped frames, janky scrolling, slow click or typing response, poor INP, slow LCP, layout shifts (CLS), unresponsive pages, or asks to debug…

    303 GitHub stars~4.8k tokensUpdated 4 mo ago
    Frontend & DesignAuto-check passed
  • Optimize Load

    textura-agency/next16-claude-starter

    Get a page into Lighthouse's green zone on desktop and mobile, for people AND for the robot form crawlers get — build it, audit all four categories (Performance, Accessibility, Best Practices, SEO)…

    132 GitHub stars~4.6k tokensUpdated today
    Frontend & DesignAuto-check: notes
  • React Native Best Practices

    callstackincubator/agent-skills

    Official

    Provides React Native performance optimization guidelines for FPS, TTI, bundle size, memory leaks, re-renders, and animations.

    1.7k GitHub starsUsed in 4 repos~3.1k tokens
    MobileAuto-check passed
  • Builds the desktop Vite and iOS or Android Metro production bundles and checks them for tree-shaking problems, such as mobile-only modules leaking into the desktop build.

    9.3k GitHub stars~620 tokensUpdated today
    Frontend & DesignAuto-check passed
  • React Doctor

    makeplane/plane

    Scans React code for lint, accessibility, bundle size and architecture issues, reports a health score and checks that changes do not lower it.

    60k GitHub starsUsed in 12 repos~657 tokens
    Frontend & DesignAuto-check passed
  • React Native Best Practices

    vercel-labs/openreview

    Official

    A prioritized rule set for React Native and Expo apps covering list performance, animation, navigation, UI patterns, state, rendering, monorepos and configuration.

    1.7k GitHub starsUsed in 17 repos~1.1k tokens
    MobileAuto-check passed

More from jjcm/makefaster

  • Makefaster

    jjcm/makefaster

    Autoresearch loop that makes the site in this repo measurably faster.

    162 GitHub stars~9.4k tokensUpdated 20 days ago
    Auto-check passed

Works with

Questions about Speedupskill

What does Speedupskill do?

Use this when speeding up a web or Electron app's load or input. Speedupskill is an agent skill from jjcm/makefaster. Use this when speeding up a web or Electron app's load or input.

When should I use Speedupskill?

Speedupskill fits situations like: tasks that involve Web performance; tasks that involve Mobile performance.

How do I install Speedupskill in Claude Code?

Run `npx skills add jjcm/makefaster --skill speedupskill -a claude-code`. Or copy the skill folder (skill in jjcm/makefaster) into .claude/skills/speedupskill in your project. Claude Code loads it when a task matches its description.

How do I install Speedupskill in Codex?

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

Can I use Speedupskill 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 jjcm/makefaster --skill speedupskill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/speedupskill, .gemini/skills/speedupskill, .github/skills/speedupskill and .opencode/skills/speedupskill in your project.

What does Speedupskill need to run?

Going by SKILL.md and its folder, Speedupskill needs the command-line tools its instructions call (npx). Our summary lists: Node.js.

Does Speedupskill access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Speedupskill 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 Speedupskill use?

No licence was found for Speedupskill or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Speedupskill use?

About 4.8k tokens (SKILL.md is roughly 19k 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 Speedupskill?

Skills that share tags, products or a category with Speedupskill: Web Performance (millionco/debug-agent, 303 stars), Optimize Load (textura-agency/next16-claude-starter, 132 stars), React Native Best Practices (callstackincubator/agent-skills, 1.7k stars) and Production Bundle Audit (keybase/client, 9.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Speedupskill?

jjcm (a GitHub user) maintains it in jjcm/makefaster, which has 162 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 16, 2026.

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