agentleFS
Sign inStart free
nimajafarinimajafari/lighthouse-skill/AGENTS.md

lighthouse-skill

AGENTS.md4 starsChanged 5 months agoMITView on GitHub

Guidance for AI coding agents working in this repository. A single Agent Skill that teaches an agent to run Google Lighthouse — CLI, performance budgets, CI, and the programmatic API — to measure and verify web quality.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repositoryOne other file it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Code examples: use ❌ bad / ✅ good where it clarifies, and prefer copy-pasteable commands.

    line 35
  2. Very specific:

    Scripts: follow: #!/bin/bash + set -euo pipefail.

    line 36
  3. Very specific:

    Keep the lab-vs-field distinction prominent — Lighthouse is a lab tool.

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md

Guidance for AI coding agents working in this repository.

Project overview

A single Agent Skill that teaches an agent to run Google Lighthouse — CLI, performance budgets, CI, and the programmatic API — to measure and verify web quality.

Structure

lighthouse-skill/
├── README.md
├── LICENSE
├── .claude-plugin/            # Claude Code plugin + marketplace manifests
├── .antigravity-plugin/       # Antigravity plugin manifest (agy plugin install)
├── .cursor-plugin/            # Cursor plugin manifest
├── codex/, .agents/plugins/   # Codex plugin + marketplace (codex/skills → ../skills)
├── gemini-extension.json      # Gemini CLI extension manifest
└── skills/
    └── lighthouse/
        ├── SKILL.md           # main instructions (keep under 500 lines)
        ├── scripts/
        │   └── run-lighthouse.sh
        └── references/
            ├── CLI-FLAGS.md
            ├── CI.md
            └── PROGRAMMATIC-API.md

Conventions

  • SKILL.md stays under 500 lines; push deep/look-up material into references/.
  • Descriptions include trigger phrases so the skill activates on the right prompts.
  • Code examples use ❌ bad / ✅ good where it clarifies, and prefer copy-pasteable commands.
  • Scripts follow: #!/bin/bash + set -euo pipefail; human logs to stderr, machine-readable JSON to stdout; cleanup trap for temp files; document dependencies (jq, Node/npx).

Accuracy notes

  • Lighthouse evolves. Audit IDs and metric weights shift between major versions (see the v13 Insight Audits note in SKILL.md). When editing, prefer linking to upstream docs over hardcoding numbers that drift.
  • Keep the lab-vs-field distinction prominent — Lighthouse is a lab tool; INP and real-user data come from the field (CrUX / web-vitals).

Testing changes

  1. Validate the YAML frontmatter in SKILL.md.
  2. shellcheck skills/lighthouse/scripts/run-lighthouse.sh.
  3. Smoke-test the script against a real URL: skills/lighthouse/scripts/run-lighthouse.sh https://example.com 1.
  4. Confirm all referenced files exist and links resolve.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free