agentleFS
Sign inStart free
bettyguobettyguo/browser-skills/skills/search-and-filter/SKILL.md

search-and-filter

Skill8 starsChanged 7 months agoMITView on GitHub

Types a query into a site's search input, submits, and optionally applies one or more filter facets (categories, price ranges, attributes). Common on e-commerce, doc-search, and listing sites.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Sites where pressing Enter doesn't submit: add a follow-on click against a search button — most sites surface one.

    line 67
  2. Distinctive:

    Document per-site if discovered.

    line 71

≈ “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

Search and Filter

When to invoke

User wants to search a site for vars.query and optionally apply filters from vars.filters (a dict of facet-name → value).

The matcher fires this skill on any page with a visible search input.

Recipe

  1. wait_for_dom_ready timeout=3s
  2. try_each selectors=[ "input[type='search']", "input[name='q']", "input[name='query']", "[role='search'] input", "input[aria-label*='search' i]", ] action=fill value="$vars.query" on_success=stop timeout=1500ms
  3. press_key key=Enter
  4. wait extra=600ms

Success criteria

  • assert results_pane_visible OR url_changed_since=step1

Filter application

The recipe above is the search part only. Applying filters is a composition with click for facet checkboxes — the agent receives the list of available filters from extract_text and decides which to toggle.

When NOT to use

  • Sites with custom search-as-you-type that doesn't accept Enter submission. Agents fall back to clicking the search button after fill.
  • Sites that ToS-prohibit automated search (LinkedIn, etc., per benchmarks/sites.yaml).

Known failures

  • Sites where pressing Enter doesn't submit: add a follow-on click against a search button — most sites surface one.
  • Search inputs inside <form> elements that submit on a different path: the recipe's Enter press may navigate to a stale URL. Document per-site if discovered.
  • Search inputs that show typeahead before submission: the typeahead overlays the results. press_key key=Escape first if it's blocking.

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