agentleFS
Sign inStart free
rolandtolnayrolandtolnay/llm-toolkit/skills/searchexa/SKILL.md

searchexa

Skill1 starsChanged 3 months agoMITView on GitHub

Semantic web search with inline page content via EXA API. Returns actual page text with results — search + fetch in one free call. Use for discovery when you need content, not just URLs. Free tier: 1000 searches/month. Triggers on: "exa search", "search with exa", "free web search", "searchexa".

  • Reads credentials

The file

We split this skill 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. Very specific:

    Use this when you need to find AND read pages — not when you need AI-synthesized answers (use research ask for that).

    line 13
  2. Very specific:

    Add EXA_API_KEY=... to ~/.claude/research/.env (same file as Perplexity/Firecrawl keys).

    line 32
  3. Distinctive:

    Do NOT use when:

    line 43

≈ “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
<objective> Free semantic web search that returns page content inline with results. Unlike Perplexity (which synthesizes answers) or Firecrawl (which scrapes single URLs), EXA combines discovery and content extraction in one call.

Use this when you need to find AND read pages — not when you need AI-synthesized answers (use research ask for that). </objective>

<cli_cheatsheet> Script path: ~/.claude/skills/searchexa/scripts/exa.py

uv run <script> "<query>" [--limit N] [--site S] [--chars N] [--recency R]

--limit/-l:   Number of results (default 10)
--site/-s:    Restrict to domain, e.g. stripe.com (repeatable)
--chars/-c:   Max characters of page text per result (default 1500)
--recency/-r: Preset window — hour | day | week | month | year

Cost: Free (1000 searches/month)

</cli_cheatsheet>

<configuration> Add `EXA_API_KEY=...` to `~/.claude/research/.env` (same file as Perplexity/Firecrawl keys).

Get a free key at https://exa.ai — no credit card required. </configuration>

<when_to_use>

  • Need page content, not just URLs or AI summaries
  • Want search + fetch in a single call (faster than search → scrape)
  • Free tier is sufficient (1000/month)
  • Looking for blog posts, docs, tutorials, news articles

Do NOT use when:

  • You need a synthesized answer → use research ask
  • You need full-page markdown extraction → use research scrape
  • You need library API docs → use research docs </when_to_use>

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