agentleFS
Sign inStart free
ragnos-labsragnos-labs/agent-skills/skills/exa-research/SKILL.md

exa-research

Skill0 starsChanged 7 months agoApache-2.0View on GitHub

Search the web with Exa through a credential-safe, deterministic JSON CLI built on Exa's official Python SDK. Use when an agent needs Exa web research, source discovery, domain-filtered searches, or a local Exa CLI that receives EXA_API_KEY from a broker or environment without placing the key on the command line.

  • Reads credentials

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. BlockRunAI/blockrun-mcp★ 389same 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 repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 4 are distinctive, and 5 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.

  • 5

    Very specific

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

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

    Use the bundled exa client for bounded source discovery.

    line 8
  2. Distinctive:

    Run the installer from this skill directory:

    line 13
  3. Very specific:

    Run exa doctor. Treat credential: available as presence evidence only.

    line 29
  4. Distinctive:

    Run a bounded search:

    line 36
  5. Distinctive:

    Read the JSON result, use the returned URLs as citations, and distinguish the provider's current response from your own inference.

    line 48
  6. Very specific:

    Stop on credential_unavailable.

    line 54
  7. Very specific:

    Stop on provider_unavailable or provider_contract_invalid.

    line 55
  8. Distinctive:

    Do not add a plain-text or raw-response mode.

    line 58
  9. Very specific:

    Keep the API origin fixed at https://api.exa.ai so a credential cannot be redirected to an arbitrary host.

    line 60

≈ “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

Exa Research

Use the bundled exa client for bounded source discovery. It fixes the API origin, emits JSON only, and never accepts a credential as a command argument.

Install

Run the installer from this skill directory:

python3 scripts/install.py --bin-dir <user-bin-directory>

The installer creates an isolated virtual environment, installs the exact hash-locked official exa-py dependency set, copies the client into an immutable release directory, and writes an exa launcher. It supports macOS and Linux with Python 3.11 or newer. Windows is not currently supported because the launcher and installation lock use POSIX primitives. Release construction is serialized and staged privately before one atomic publication step. Use --replace only after identifying the existing command that will be replaced.

Check readiness

Run exa doctor. Treat credential: available as presence evidence only. Doctor does not call Exa and never prints the value. Provide EXA_API_KEY through the approved secret broker or process environment; never put it in shell history, Git, prompts, logs, or command arguments.

Search

Run a bounded search:

exa search "query" --num-results 5

Optional controls include --type, repeated --include-domain, repeated --exclude-domain, and --max-highlight-characters. Prefer the default highlight-only contents over full page text. Increase result or highlight limits only when the task requires it because provider cost and output size grow with them.

Read the JSON result, use the returned URLs as citations, and distinguish the provider's current response from your own inference. A successful process is not proof that every returned source is accurate or authoritative.

Failure rules

  • Stop on credential_unavailable; do not ask to print or inspect the key.
  • Stop on provider_unavailable or provider_contract_invalid; preserve the error code without relaying raw provider bodies that may contain private data.
  • Do not add a plain-text or raw-response mode. Extend the normalized JSON contract deliberately if another field is required.
  • Keep the API origin fixed at https://api.exa.ai so a credential cannot be redirected to an arbitrary host.

The client implementation is scripts/exa_cli.py. scripts/bootstrap.lock upgrades the isolated installer before scripts/requirements.lock installs the official SDK closure. Both are generated with hashes from their adjacent input files.

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