dianel555/dskills/exa

Name: exa
Author: dianel555

Claude Code and agent skill by dianel555/dskills

Trust tier 2

community

By dianel555
Coding
dianel555/dskills
skills/exa/SKILL.md
Updated 1 Sep 2026
Version 1.0.23 versions recorded

Source check pending

Checking that the SKILL.md file is still in the repository.

High-precision semantic search and content retrieval via Exa API. Use when: (1) Deep research requiring semantic understanding, (2) Code documentation and examples lookup, (3) Company/professional research, (4) AI-powered comprehensive research tasks, (5) URL content extraction with structured output. Triggers: "research", "find papers", "code examples", "company info", "LinkedIn profiles", "deep analysis". Differentiator: Exa excels at semantic/neural search while grok-search is better for real-time news and general web content.

Install

npx vskill@latest install dianel555/dskills/exa

SKILL.md

Exa Search

High-precision semantic search via Exa API. Standalone CLI only (no MCP dependency).

Execution Method

bash

# Prerequisites: pip install httpx tenacity
# Environment: EXA_API_KEY (required), EXA_API_URL (optional, default: https://api.exa.ai)
 
# All examples assume cwd == skills/exa/. The shim auto-chdirs if you launch
# it from elsewhere (e.g., the repo root).
cd skills/exa
python scripts/exa_cli.py --help

Available Tools

bash

# Basic semantic search (highlights always on; supports inline category:<type>)
python scripts/exa_cli.py web_search_exa --query "TypeScript design patterns" [--num-results 10]
python scripts/exa_cli.py web_search_exa --query "category:company Anthropic AI safety"
 
# Batch URL fetch (urls is a repeatable flag; payload field is upstream `ids`)
python scripts/exa_cli.py web_fetch_exa \
  --urls "https://a.com" --urls "https://b.com" \
  [--max-chars 3000] [--out content.json]
 
# Advanced filtered search (list params are repeatable flags, no comma syntax)
python scripts/exa_cli.py web_search_advanced_exa --query "transformer" \
  [--type auto|fast|instant] [--category research\ paper] \
  [--include-domains arxiv.org --include-domains papers.nips.cc] \
  [--exclude-domains medium.com] \
  [--include-text "attention"] [--exclude-text "tutorial"] \
  [--start-date 2024-01-01] [--end-date 2024-12-31] \
  [--num-results 10] [--max-age-hours 168] \
  [--text] [--highlights] [--summary] \
  [--max-chars 5000]   # only effective when --text is set; emits stderr warning otherwise
  [--out results.json]
 
# Configuration / connectivity probe (omit --no-test to run a numResults=1 ping)
python scripts/exa_cli.py get_config_info [--no-test]
 
# Create an Agent run or resume the same retained run
python scripts/exa_cli.py agent_run --query "Research an evidence-backed market map" [--effort low]
python scripts/exa_cli.py agent_run --run-id agent_run_123 [--wait-seconds 750]

Tool Capability Matrix

Tool	Required	Optional	Output
`web_search_exa`	`--query`	`--num-results` (1-100)	Search results JSON (highlights always present)
`web_fetch_exa`	`--urls` (repeatable, ≥1)	`--max-chars` (default 3000), `--out`	`/contents` response JSON
`web_search_advanced_exa`	`--query`	`--type`, `--category`, repeatable `--include-domains`/`--exclude-domains`/`--include-text`/`--exclude-text`, `--start-date`, `--end-date`, `--num-results`, `--max-age-hours`, `--text`, `--highlights`, `--summary`, `--max-chars`, `--out`	Filtered search results JSON
`get_config_info`	–	`--no-test`	Config + (default) `connection_test`
`agent_run`	exactly one of `--query` / `--run-id`	schema/input files, data sources, prior-run continuation, effort, wait controls, `--out`	Normalized retained-run lifecycle JSON

Global Options

Place before the subcommand:

Option	Purpose
`--api-url`	Override `EXA_API_URL` (does not write to `os.environ`)
`--api-key`	Override `EXA_API_KEY`
`--debug`	Enable JSON debug events on stderr (`EXA_DEBUG=true`) — never logs auth values
`--max-retry-wait <s>`	Cap (seconds) for single retry wait + exponential backoff (default 60, env: `EXA_MAX_RETRY_WAIT`)
`--auth-scheme <scheme>`	Authentication scheme: `x-api-key` (default) or `bearer` for third-party endpoints (env: `EXA_AUTH_SCHEME`)

Tool Routing Guide

Use Case	Recommended Tool
Real-time news, current events	grok-search
Semantic/conceptual research	exa (`web_search_exa`)
Domain or date-bounded research	exa (`web_search_advanced_exa`)
Read full content of one or more URLs	exa (`web_fetch_exa`)
Academic papers, technical docs	exa (`web_search_advanced_exa --include-domains arxiv.org ...`)
Open-ended discovery, multi-hop research, structured list building, prior-run follow-up	exa-agent (`agent_run`)
Homogeneous enrichment over known rows	Deterministic script with bounded concurrency, backoff, checkpoint, and stable output file

Workflow Patterns

Pattern 1: Quick Semantic Search

bash

python scripts/exa_cli.py web_search_exa --query "best practices for React hooks" --num-results 5

Pattern 2: Filtered Research (repeatable flags)

bash

python scripts/exa_cli.py web_search_advanced_exa --query "transformer architecture" \
  --include-domains arxiv.org --include-domains papers.nips.cc \
  --start-date 2023-01-01 --text --summary

Pattern 3: Batch URL Read

bash

python scripts/exa_cli.py web_fetch_exa \
  --urls "https://example.com/a" --urls "https://example.com/b" \
  --max-chars 4000 --out batch.json

Pattern 4: Third-Party Endpoint (Bearer Auth)

bash

# Connect to exa-pool or other Exa-compatible proxy
export EXA_API_URL=https://pool.example.com
export EXA_AUTH_SCHEME=bearer
export EXA_API_KEY=your-bearer-token
 
python scripts/exa_cli.py web_search_exa --query "AI agents" --num-results 5
 
# Or use CLI flags for one-off requests
python scripts/exa_cli.py --auth-scheme bearer --api-url https://pool.example.com \
  web_search_exa --query "AI agents"

Pattern 5: Exa Agent

Read exa-agent.md before creating a run. It defines objective/schema/coverage checks, --run-id versus --previous-run-id, evidence validation, and ZDR limits without duplicating that workflow here.

References

The references/ directory carries 11 prompt-engineering guides. Open them on demand when crafting queries:

File	When to read
`searching.md`	Crafting `web_search_exa` queries (semantic phrasing, category usage)
`extraction.md`	Choosing between highlights / text / summary on advanced search
`filtering.md`	Building include/exclude domain & date filters
`synthesis.md`	Aggregating multiple result sets into a coherent answer
`source-quality.md`	Vetting source credibility
`patterns-code.md`	Code/library research recipes
`patterns-companies.md`	Company research recipes
`patterns-news.md`	Current-events research recipes
`patterns-papers.md`	Academic paper recipes
`patterns-people.md`	People search recipes
`patterns-relationships.md`	Multi-entity relationship research

Error Handling

Error	Recovery
`EXA_API_KEY not configured`	Set environment variable or pass `--api-key`
Search/fetch HTTP 408/429/5xx	Automatic retry with exponential backoff (max 4 attempts, capped by `--max-retry-wait`)
Agent create network/408/429/5xx	Single attempt; report uncertain upstream state and do not create a duplicate
Agent running deadline	Resume the same ID with `agent_run --run-id ...`
HTTP 401	Verify API key
Timeout	Reduce `--num-results` or retry

Output Format

All commands print JSON (ensure_ascii=False, indent 2) to stdout. With --out <file>, the response JSON is written to that path and stdout becomes {"status":"ok","file":"<file>"}. Errors go to stderr as {"error":"<message>"} with non-zero exit.

Agent creation and interruption additionally emit one-line JSON progress events to stderr so the retained run ID remains recoverable without corrupting stdout.

Security

Security scanPassed, 100 of 100Pattern checks on the skill's files.
Model reviewPassed

See the full security report

Quality evaluation

Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

SKILL.md in the repositoryCheckingskills/exa/SKILL.md

Popularity

Repository stars: 64
Repository forks: 6
7-day trend score: 21

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 29 Mar 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

Claude Code
Cursor
GitHub Copilot
Windsurf
Codex
Gemini CLI
Cline
Amp
Roo Code
Goose
Continue
Kilo Code
Junie
Trae
OpenHands
Qwen Code
AI Agent
Tabnine Chat
Sourcegraph Cody
Amazon Q
Firebase Genkit
Sweep
Devin
Phind
Mentat
Claude Desktop
Aider
GPT Pilot
Plandex
bolt.new
v0
Replit Agent
Anse
TypingMind
BetterChatGPT
LibreChat
Warp AI
Pieces
Fig AI

Embed badge

[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/dianel555/dskills/exa/badge)](https://verified-skill.com/skills/dianel555/dskills/exa)

Something wrong with this skill or its page? Tell us.