askill
exa

exaSafety 90Repository

Perform semantic search using Exa AI. Use when you need to: (1) find content by meaning not keywords, (2) discover similar documents, or (3) perform neural web searches.

148 stars
3k downloads
Updated 2/4/2026

Package Files

Loading files...
SKILL.md

Exa

Perform semantic search using Exa AI. Use when you need to: (1) find content by meaning not keywords, (2) discover similar documents, or (3) perform neural web searches.

Input

Provide input as JSON:

{
  "search_query": "The search query or topic you want to explore using semantic search",
  "num_results": "Number of search results to retrieve (e.g., 5, 10, 20)"
}

Execution (Pattern B: Text/Data)

Step 1: Run the Skill and Get Run ID

RESULT=$(refly skill run --id skpi-j39cg6h58kgt89qy41chi1ay --input '{
  "query": "latest developments in artificial intelligence",
  "num_results": "10"
}')
RUN_ID=$(echo "$RESULT" | jq -r '.payload.workflowExecutions[0].id')
# RUN_ID is we-xxx format, use this for workflow commands

Step 2: Open Workflow in Browser and Wait for Completion

open "https://refly.ai/workflow/c-eptydufr83h9gket8xdjbnan"
refly workflow status "$RUN_ID" --watch --interval 30000

Step 3: Extract Text Content

# Get text content from toolcalls
CONTENT=$(refly workflow toolcalls "$RUN_ID" --files --latest | jq -r '.payload.nodes[].content')
echo "$CONTENT"

Expected Output

  • Type: Text content
  • Format: Semantic search results
  • Action: Display content to user

Rules

Follow base skill workflow: ~/.claude/skills/refly/SKILL.md

Install

Download ZIP
Requires askill CLI v1.0+

AI Quality Score

78/100Analyzed 2/16/2026

Well-structured skill for Exa AI semantic search with clear step-by-step execution instructions and proper metadata. Limited reusability due to platform-specific IDs, but good documentation quality overall.

90
85
60
75
80

Metadata

Licenseunknown
Version1.0.0
Updated2/4/2026
Publisherrefly-ai

Tags

github-actionsllm