agentleFS
baofeng-techbaofeng-tech/agent-skills-so/perplexity-search/SKILL.md

perplexity-search

Skill0 starsChanged 7 months agoMITView on GitHub

Perplexity Sonar search and answer generation through AIsa. Use when the task is specifically to call Perplexity Sonar, Sonar Pro, Sonar Reasoning Pro, or Sonar Deep Research for citation-backed web answers, analytical reasoning, or long-form research reports.

  • Reads credentials
  • Sends data out

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ena-database, gwas-database and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • garri333Skill

    ena-database

    Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats.

    Also in 7 projects that use this

  • garri333Skill

    gwas-database

    Query NHGRI-EBI GWAS Catalog for SNP-trait associations. Search variants by rs ID, disease/trait, gene, retrieve p-values and summary statistics, for genetic epidemiology and polygenic risk scores.

    Also in 7 projects that use this

  • +10 more from garri333

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 3 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user specifically wants Perplexity-powered search and answer generation through AIsa, especially for …

    line 19
  2. Very specific:

    Use the bundled client at scripts/perplexity_search_client.py

    line 43
  3. Very specific:

    Use sonar for fast, lightweight answers with citations

    line 47
  4. Very specific:

    Use sonar-pro for stronger synthesis and comparison tasks

    line 48
  5. Very specific:

    Use sonar-reasoning-pro for analytical or multi-step reasoning questions

    line 49
  6. Very specific:

    Use sonar-deep-research for exhaustive reports.

    line 50
  7. Distinctive:

    Add a system message when you want a more specific output format:

    line 61
  8. Distinctive:

    If it still times out, narrow the query or retry later

    line 130
  9. Very specific:

    If the user wants a faster answer, fall back to sonar-pro or sonar-reasoning-pro

    line 131

“Common” is measured: kept by at least 6 in 10 of the 12 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

Perplexity Search

Use this skill when the user specifically wants Perplexity-powered search and answer generation through AIsa, especially for citation-backed web answers, analytical reasoning, or long-form research reports.

This skill covers four AIsa endpoints:

  • /perplexity/sonar
  • /perplexity/sonar-pro
  • /perplexity/sonar-reasoning-pro
  • /perplexity/sonar-deep-research

Compatibility

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

  • Claude Code and Claude
  • OpenAI Codex
  • Cursor
  • Gemini CLI
  • OpenCode, Goose, OpenClaw, Hermes
  • and other harnesses that implement the Agent Skills specification

Requires Python 3, a POSIX shell, and AISA_API_KEY (available from aisa.one).

Requirements

  • Set AISA_API_KEY
  • Use the bundled client at scripts/perplexity_search_client.py

Model Selection

  • Use sonar for fast, lightweight answers with citations
  • Use sonar-pro for stronger synthesis and comparison tasks
  • Use sonar-reasoning-pro for analytical or multi-step reasoning questions
  • Use sonar-deep-research for exhaustive reports; expect slower responses and occasional timeouts

Python Client

python3 scripts/perplexity_search_client.py sonar --query "What changed in AI this week?"
python3 scripts/perplexity_search_client.py sonar-pro --query "Compare coding agents with citations"
python3 scripts/perplexity_search_client.py sonar-reasoning-pro --query "Analyze whether vertical AI agents can defend against general copilots"
python3 scripts/perplexity_search_client.py sonar-deep-research --query "Create a deep research report on AI coding agents in 2026"

Add a system message when you want a more specific output format:

python3 scripts/perplexity_search_client.py sonar-pro \
  --query "Map the top coding agent products" \
  --system "Respond in markdown with an executive summary first."

Curl Examples

Sonar

curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonar",
    "messages": [
      {"role": "user", "content": "What changed in the AI agent ecosystem this week?"}
    ]
  }'

Sonar Pro

curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar-pro" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonar-pro",
    "messages": [
      {"role": "user", "content": "Compare the top coding agents and cite the key differences."}
    ]
  }'

Sonar Reasoning Pro

curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar-reasoning-pro" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonar-reasoning-pro",
    "messages": [
      {"role": "user", "content": "Analyze whether vertical AI agents can defend against general copilots."}
    ]
  }'

Sonar Deep Research

curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar-deep-research" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonar-deep-research",
    "messages": [
      {"role": "user", "content": "Create a deep research report on AI coding agents in 2026."}
    ]
  }'

Timeout Behavior

  • sonar-deep-research uses a longer timeout and automatic retries in the bundled client
  • If it still times out, narrow the query or retry later
  • If the user wants a faster answer, fall back to sonar-pro or sonar-reasoning-pro

References

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.