agentleFS
Sign inStart free
baofeng-techbaofeng-tech/agent-skills-so/perplexity-research/SKILL.md

perplexity-research

Skill0 starsChanged 7 months agoMITView on GitHub

Deep research using Perplexity Sonar models via AIsa API. Provides synthesized answers with citations. Supports 4 models from fast to exhaustive deep research. Use when: the user needs web search, research, source discovery, or content extraction.

  • Reads credentials

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    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
  1. Very specific:

    Run the search client with the sonar subcommand:

    line 26
  2. Distinctive:

    Use this skill when the user needs a synthesized, well-researched answer rather than raw search results.

    line 73

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

AIsa Perplexity Deep Research

Conduct deep research using Perplexity Sonar models via the AIsa API. Returns synthesized, citation-backed answers instead of raw search results. Choose from four models depending on the depth and complexity needed.

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 sonar subcommand:

python3 scripts/search_client.py sonar --query "<research question>" --model <model_name>

Arguments

ArgumentRequiredDefaultDescription
--query / -qYes—Research question or query
--model / -mNosonarModel to use (see below)

Available Models

ModelSpeedDepthBest For
sonarFastStandardQuick factual lookups
sonar-proMediumDetailedIn-depth topic exploration
sonar-reasoning-proSlowerDeepComplex reasoning and analysis
sonar-deep-researchSlowestExhaustiveComprehensive research reports

Examples

# Quick factual lookup
python3 scripts/search_client.py sonar --query "What is the current state of quantum computing?"

# Detailed research
python3 scripts/search_client.py sonar --query "Compare transformer and state-space model architectures" --model sonar-pro

# Complex reasoning
python3 scripts/search_client.py sonar --query "Will AGI be achieved by 2030? Analyze arguments for and against." --model sonar-reasoning-pro

# Exhaustive deep research
python3 scripts/search_client.py sonar --query "Comprehensive analysis of AI regulation frameworks worldwide" --model sonar-deep-research

Output

The script prints:

  • Synthesized answer — A coherent, well-structured response
  • Citations — Source URLs backing the answer
  • Cost — API usage cost (when available)

When to Use

Use this skill when the user needs a synthesized, well-researched answer rather than raw search results. Best for complex questions, comparative analyses, trend reports, and any query where a thoughtful, citation-backed response is more valuable than a list of links.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free