multi-search
Skill0 starsChanged 7 months agoMITView on GitHub
Parallel multi-source search combining Web, Scholar, Smart, and Tavily results with confidence scoring and AI synthesis. Best for comprehensive research requiring cross-source validation. Use when: the user needs web search, research, source discovery, or content extraction.
- Reads credentials
2 other projects use a version of this.
Adopted by
Most recently taken up by
- laubeing-droid/unified-legal-ai-cntheir own version, first seen Jun 12, 2026
- Nex-ZMH/Agent-websearch-skilltheir own version, first seen Feb 20, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- laubeing-droid/unified-legal-ai-cn★ 16same name
- Nex-ZMH/Agent-websearch-skill★ 11same 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 repository59 other files it gives its agents.
- aisa-multi-search-engineSkill
- aisa-providerSkill
- aisa-tavilySkill
- aisa-twitter-apiSkill
- aisa-twitter-command-centerSkill
- aisa-twitter-engagement-suiteSkill
- aisa-twitter-post-engageSkill
- aisa-youtube-searchSkill
- aisa-youtube-serp-scoutSkill
- cn-llmSkill
- crypto-market-dataSkill
- gmail-lead-deskSkill
- kol-creator-discoverySkill
- last30daysSkill
- last30days-zhSkill
- llm-routerSkill
- marketpulseSkill
- marketSkill
- media-genSkill
- multi-source-searchSkill
- notion-workspaceSkill
- openclaw-aisa-youtube-aisaSkill
- openclaw-media-genSkill
- openclaw-searchSkill
- openclaw-twitter-post-engageSkill
- openclaw-twitterSkill
- openclaw-youtubeSkill
- perplexity-researchSkill
- perplexity-searchSkill
- prediction-market-arbitrage-apiSkill
- prediction-market-arbitrageSkill
- prediction-market-arbitrage-zhSkill
- prediction-market-dataSkill
- prediction-market-data-zhSkill
- prediction-marketSkill
- saas-gatewaySkill
- scholar-searchSkill
- searchSkill
- seo-keyword-researchSkill
- smart-searchSkill
- stock-analysisSkill
- stock-dividendSkill
- stock-hotSkill
- stock-portfolioSkill
- stock-rumorsSkill
- stock-watchlistSkill
- tavily-extractSkill
- tavily-searchSkill
- trend-forecastSkill
- twitter-autopilotSkill
- twitter-command-center-search-post-interactSkill
- twitter-command-center-search-postSkill
- twitterSkill
- us-stock-analystSkill
- web-searchSkill
- x-intelligence-automationSkill
- youtube-searchSkill
- youtube-serpSkill
- youtubeSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Run the search client with the verity subcommand:
- Distinctive: line 69
Use this skill when the user needs the most thorough and reliable search results possible.
≈ “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.
Files
AIsa Multi-Source Search
The most comprehensive search tool in this plugin. Queries Web, Scholar, Smart, and Tavily sources in parallel, then computes a confidence score based on source availability, result quality, and diversity. Optionally generates an AI synthesis of all results.
Setup
This skill requires the AISA_API_KEY environment variable. When installed as a Claude plugin, the key is configured via the environment variables.
Usage
Run the search client with the verity subcommand:
python3 scripts/search_client.py verity --query "<search query>" --count <results_per_source>Arguments
| Argument | Required | Default | Description |
--query / -q | Yes | — | Search query |
--count / -c | No | 5 | Maximum results per source (1–20) |
Example
python3 scripts/search_client.py verity --query "impact of AI on healthcare diagnostics" --count 5Output
The script prints:
- Individual results from each source (Web, Smart, Scholar, Tavily)
- Confidence Assessment with:
- Score (0–100) — Overall confidence in the search results
- Level — Very High / High / Medium / Low / Very Low
- Sources queried and Sources OK — How many sources responded
- Total results — Combined result count across all sources
- AI Synthesis — A coherent summary combining insights from all sources, with citations
Confidence Scoring Breakdown
| Factor | Weight | Description |
| Source availability | 40% | How many of the 4 sources returned results |
| Result quality | 35% | Ratio of actual results to expected results |
| Source diversity | 15% | Whether both academic and web sources are present |
| Recency bonus | 10% | Bonus for having at least one successful source |
When to Use
Use this skill when the user needs the most thorough and reliable search results possible. Best for fact-checking, comprehensive research, verifying claims across multiple sources, or any query where cross-source validation adds significant value. This tool is slower but more reliable than individual search tools.
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
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.