# Perplexity Research

> 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.

- Skill: `baofeng-tech/perplexity-research-2` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add baofeng-tech/perplexity-research-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/baofeng-tech/perplexity-research-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Product & Planning
- Author: baofeng-tech (https://skillmd.com/u/baofeng-tech)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/baofeng-tech/perplexity-research-2

---


# perplexity-research

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.

## When to Use

- Use this release when the user needs the runtime packaged under `scripts/`.
- Prefer the bundled Python or shell entrypoints instead of copying raw API examples into the chat.
- For Hermes community installs, keep setup explicit and review the command help text before the first run.

## Setup

- Review `README.md` for the release-specific summary and structure.
- Use repo-relative paths under `scripts/`.
- Prefer explicit CLI auth flags such as `--api-key` or `--aisa-api-key` when a script exposes them.

## Quick Reference

- `python3 scripts/search_client.py --help`

## Verification

- Confirm the command returns structured output or a successful API response.
- If the workflow stores local state, verify it writes under a repo-local data directory rather than a home-directory default.