agentleFS
Sign inStart free
Kevin-Liu-01Kevin-Liu-01/Local-Search/site/SKILL.md

site-skill

Skill16 starsChanged 31 days agoMITView on GitHub

Next.js landing page, browser workflow, benchmarks, and social assets.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep existing Chrome approval distinct from a separate persistent profile.

    line 20
  2. Distinctive:

    Do not imply automatic login access or credentials remaining outside agent context when returned pages contain private data.

    line 21
  3. Distinctive:

    Run pnpm lint, pnpm typecheck, pnpm build.

    line 26
  4. Distinctive:

    Do not publish the site or packages without explicit user authorization.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
SKILL.md

Local-Search / site

Purpose

<!-- agent-docs:fill:purpose -->

Present the local browser API clearly, with readable product proof and explicit browser authority. Read DESIGN.md before visual or marketing changes.

Mental model & key files

<!-- agent-docs:fill:model -->

app/ owns routes, metadata and global CSS; components/ owns interactive displays; lib/ owns shared product facts; public/ owns collected logos and launch media.

Patterns to follow / invariants

<!-- agent-docs:fill:patterns -->

Keep existing Chrome approval distinct from a separate persistent profile. Do not imply automatic login access or credentials remaining outside agent context when returned pages contain private data. Keep supporting text ≥16px.

Common tasks → first action

<!-- agent-docs:fill:tasks -->

Run pnpm lint, pnpm typecheck, pnpm build. Verify desktop/mobile through agent-browser. Use the committed benchmark evidence for numeric claims.

Gotchas

<!-- agent-docs:fill:gotchas -->

The site is a static export: serving out/ requires rebuilding after edits. Do not publish the site or packages without explicit user authorization.

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