Exa Search

Community

jikssha

exa-search

Neural web search for source-first research, especially official docs, API references, pricing pages, product specs, company pages, and any task where low-noise results and direct text extraction matter. Use when you need precise, high-quality, non-SEO-biased web results or extracted page text/highlights. Prefer this over generic web search for official documentation and structured source retrieval. Prefer grok-search instead for breaking news, X/Twitter dynamics, real-time sentiment, or broad multi-source live synthesis.

Overview

Publisher	jikssha
Repository	`openclaw-dae-skills`
Skill name	`exa-search`
Stars	98
Forks	11
Bundled files	4
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
4 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by jikssha on GitHub. Read the source before you install it.

Installation

Install the Exa Search AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/jikssha/openclaw-dae-skills/tree/main/exa-search
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/jikssha/openclaw-dae-skills.git /tmp/openclaw-dae-skills
mkdir -p .claude/skills
cp -r /tmp/openclaw-dae-skills/exa-search .claude/skills/exa-search

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Exa Search in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Exa Search on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Exa Search is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Exa Search

Use Exa for source-first retrieval.

Prefer it when the task is about:

official documentation
API/reference pages
pricing/plan details
product/company pages
extracting the text of a page instead of just finding the link
expanding from one canonical page to similar pages

Do not default to Exa for:

breaking news
X/Twitter chatter
live sentiment / fast-moving discourse
broad real-time synthesis across many fresh sources

For those, prefer grok-search.

Workflow

Start with docs for official documentation lookups.
Use search --text or research when you need extracted body text.
Restrict domains aggressively when the user wants official sources.
Use similar when you already have the best canonical page and want adjacent sources.
For official-doc-only work, prefer docs plus domain restriction over similar; similar is semantic, not source-pure.
Return links plus extracted evidence, not just titles.

Config

Preferred key resolution order:

--api-key
EXA_API_KEY
EXA_API_KEYS (comma-separated)
config.local.json
config.json
~/.codex/config/exa-search.json

Recommended setup for this workspace: keep the real key inside the skill folder in config.local.json so the entire skill can be backed up or moved as one directory.

Single key

json
{
  "profiles": [
    { "id": "main", "api_key": "YOUR_EXA_API_KEY" }
  ],
  "base_url": "https://api.exa.ai",
  "timeout_seconds": 30
}

Multiple keys with auto failover

json
{
  "profiles": [
    { "id": "main", "api_key": "KEY_1" },
    { "id": "backup-1", "api_key": "KEY_2" },
    { "id": "backup-2", "api_key": "KEY_3" }
  ],
  "base_url": "https://api.exa.ai",
  "timeout_seconds": 30
}

Failover behavior:

profiles are tried in order
401 / 403 / 429 and quota / billing / rate-limit style errors automatically move to the next key
the output includes profileId and attempts so you can see which key was used

Commands

Official docs search

bash
python3 scripts/exa_search.py docs --query "telegram streaming openclaw"

Official docs search with extracted text

bash
python3 scripts/exa_search.py docs --query "model failover openclaw" --text --num 2

General source-first search

bash
python3 scripts/exa_search.py search --query "OpenClaw Telegram streaming" --num 5

Deep extraction / research

bash
python3 scripts/exa_search.py research --query "OpenClaw model failover" --num 3

Force a specific key/profile

bash
python3 scripts/exa_search.py docs --query "telegram streaming openclaw" --profile main

Find similar pages

bash
python3 scripts/exa_search.py similar --url "https://docs.openclaw.ai/channels/telegram" --num 5

Notes

docs defaults to includeDomains=docs.openclaw.ai.
research defaults to text extraction.
output is normalized JSON so downstream agents can consume it reliably.
use references/query-recipes.md for ready-made query patterns.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Exa Search AI skill do?

Why use Exa Search on TypingMind?

Because you install it once and use it with any model. Exa Search is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Exa Search in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jikssha/openclaw-dae-skills/tree/main/exa-search. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Exa Search?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Exa Search?

As many as you like. As long as a model supports skills, you can use Exa Search with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Exa Search AI skill free?

Yes. It is published on GitHub by jikssha under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Create Agent Adapter

paperclipai

OrganizationPopular

Create or modify Paperclip agent adapters across server, UI, and CLI surfaces. Use when adding support for a new CLI agent, API agent, custom process, or adapter package.

Create Paperclip Bundled Skill

paperclipai

OrganizationPopular

Turn an idea, tweet, or task into a skill in the Paperclip skills catalog (packages/skills-catalog). Use when asked to FIND or MAKE a skill and publish it as a bundled/optional catalog skill: research…

Tavily

Tavily web search, content extraction, and research tools.

Deep Research

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Exa Search

Workflow

Config

Single key

Multiple keys with auto failover

Commands

Official docs search

Official docs search with extracted text

General source-first search

Deep extraction / research

Force a specific key/profile

Find similar pages

Notes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now