Perplexity Sonar

Perplexity Sonar search and answer generation through AIsa. Use when the task is specifically to call Perplexity Sonar, Sonar Pro, Sonar Reasoning Pro, or So...

Security Scan

The skill's code, instructions, and requested credential (AISA_API_KEY) are coherent with its stated purpose of calling AIsa/Perplexity Sonar endpoints; it appears to do exactly that and nothing unrelated.

Purpose & Capability

Name/description match the actual behavior: the SKILL.md and bundled Python client call AIsa Perplexity Sonar endpoints. Requested binaries (curl, python3) and the single env var AISA_API_KEY are appropriate for this purpose.

Instruction Scope

SKILL.md instructs the agent to use the bundled client or curl to call the documented API endpoints. The instructions do not reference other system files, credentials, or external endpoints beyond api.aisa.one, and they do not instruct broad data collection.

Install Mechanism

No install spec; this is instruction-only plus a small bundled Python script. Nothing is downloaded or extracted at install time.

Credentials

Only one required environment variable (AISA_API_KEY) is declared and used by the client. That key is necessary and proportional to calling the AIsa API; no unrelated credentials are requested.

Persistence & Privilege

Skill is not marked always:true and does not request persistent/privileged system changes. disable-model-invocation is false (normal), so the agent can call the skill autonomously, but that is expected for skills.

Assessment

This skill forwards queries (and any optional system instructions) to the external AIsa API at api.aisa.one using the AISA_API_KEY you provide. Only install if you trust the AIsa service and are comfortable sending the query text to an external endpoint. Do not use this skill for sensitive secrets or private data unless you have reviewed AIsa's privacy/security policies. Confirm you want the agent to be able to call this skill autonomously (default behavior) and keep your AISA_API_KEY secret and rotated per your usual practices.

Perplexity-Search

Use this skill when the user specifically wants Perplexity-powered search answers instead of structured scholar/web retrieval.

This skill covers four AIsa endpoints:

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

Requirements

• Set AISA_API_KEY
• Use the bundled client at {baseDir}/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 {baseDir}/scripts/perplexity_search_client.py sonar --query "What changed in AI this week?"
python3 {baseDir}/scripts/perplexity_search_client.py sonar-pro --query "Compare coding agents with citations"
python3 {baseDir}/scripts/perplexity_search_client.py sonar-reasoning-pro --query "Analyze whether vertical AI agents can defend against general copilots"
python3 {baseDir}/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 {baseDir}/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

• Sonar
• Sonar Pro
• Sonar Reasoning Pro
• Sonar Deep Research