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

src-skill

Skill16 starsChanged 31 days agoMITView on GitHub

How to work in `src/`. Read before editing here.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Kevin-Liu-01/Claude-of-Tanks★ 531same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep automatic notices terminal-only and startup-only, with daily caching, bounded HTTPS requests, and an opt-out.

    line 23
  2. Distinctive:

    Keep command handlers thin enough to read from top to bottom.

    line 34
  3. Very specific:

    Prefer typed Error variants over ad hoc strings.

    line 35
  4. Very specific:

    Do not put CDP JSON protocol plumbing in command handlers when it belongs in src/browser/.

    line 38

≈ “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 / src

Purpose

Application code for the CLI, including argument parsing, command dispatch, typed errors, browser control, and output rendering.

Mental model & key files

  • src/bin/lsearch.rs parses Clap arguments and turns typed errors into stable stderr JSON.
  • lib.rs exposes the async run entry point.
  • cli.rs is declarative command/argument structure.
  • commands/mod.rs is orchestration: attach browser, execute command, print result.
  • commands/search.rs owns search, browser-scoped caching, output, and content enrichment. Keep cache hits behind live connection verification, but avoid attaching a page unless content or an explicit target needs it.
  • updates.rs checks published releases independently of browser commands. Keep automatic notices terminal-only and startup-only, with daily caching, bounded HTTPS requests, and an opt-out. update-check is explicit JSON output; registry failures are advisory, never an implicit install or browser fallback.
  • error.rs keeps operator-facing messages and machine-readable error codes in one place.
  • policy.rs decides whether a URL or tab is off limits; profiles.rs stores named profiles and the agent's tab record. commands::Boundary applies them: attach checks tab access, page commands check the current URL, and navigation helpers check the destination and where it lands.

Patterns to follow / invariants

  • Keep command handlers thin enough to read from top to bottom.
  • Prefer typed Error variants over ad hoc strings.
  • Any command that may expose browser credentials should redact by default or require an explicit opt-in flag.
  • Do not put CDP JSON protocol plumbing in command handlers when it belongs in src/browser/.

Common tasks → first action

  • New command: add Clap args, add command branch, update README, add CLI test.
  • Managed browser cleanup: keep cleanup dry-run by default, kill exact managed listener PIDs only, and never delete profile cookies/data. Use graceful CDP shutdown by default; SIGKILL requires explicit --force.
  • New output mode: update output.rs only if the envelope contract changes.
  • New error: add variant in error.rs and stable code() mapping.

Gotchas

  • run owns the parsed Cli; avoid async closures borrowing &mut CdpClient across helper boundaries unless lifetimes are explicit.
  • read --format text|markdown and html without a path intentionally write raw body content instead of JSON.

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