multi-source-search

name	multi-source-search
description	Confidence-scored multi-source retrieval across web, scholar, Tavily, and Perplexity-backed research. Use when: the user needs cross-source verification, consensus checks, or one report that compares multiple search surfaces. Supports parallel retrieval, confidence scoring, and synthesis-ready outputs.
author	AIsa
version	1.0.1
license	MIT
user-invocable	true
primaryEnv	AISA_API_KEY
requires	{"bins":["python3"],"env":["AISA_API_KEY"]}
metadata	{"aisa":{"emoji":"🔎","requires":{"bins":"[Truncated]","env":"[Truncated]"},"primaryEnv":"AISA_API_KEY","compatibility":["openclaw","claude-code","hermes"]},"openclaw":{"emoji":"🔎","requires":{"bins":"[Truncated]","env":"[Truncated]"},"primaryEnv":"AISA_API_KEY"}}

Multi-Source Search Verification Engine

Compare multiple search surfaces in one pass and score how confident the result set looks before you synthesize it.

When to use

• The user wants the same topic checked across multiple search surfaces instead of one provider.
• The user needs confidence scoring, cross-source verification, or a consensus-style research output.
• The user wants a growth-variant search lane focused on validation, not just lookup.

When NOT to use

• The user only needs one flagship search entry for lookup, cited answers, or deep research; use search.
• The task is provider-specific and fits scholar-search, tavily-search, or perplexity-search.
• The workflow must avoid relay-based calls to api.aisa.one.

Capabilities

• Parallel retrieval across structured web, scholar, smart search, Tavily, and Perplexity-backed flows.
• Confidence scoring that highlights source coverage, diversity, and result quality.
• Synthesis-ready outputs for research comparison, verification, and decision support.

One API key gives you:

• Structured web search
• Scholar search
• Hybrid scholar search
• Tavily search and extraction tools
• Perplexity Sonar answer-generation endpoints with citations

Compatibility

Works with any agentskills.io-compatible harness, including:

• Claude Code and Claude (Anthropic)
• OpenAI Codex
• Cursor
• Gemini CLI (Google)
• OpenCode, Goose, OpenClaw, Hermes
• and any other harness that implements the Agent Skills specification

Requires Python 3, a POSIX shell, and AISA_API_KEY (get one at aisa.one).

What This Skill Is Best For

Fast web lookup

Search the latest AI infrastructure launches and summarize the top sources.

Scholar-backed research

Find recent papers on multimodal reasoning from 2024 onward.