agentleFS
qwwiwiqwwiwi/agentos-skills-public/skills/perplexity-research/SKILL.md

perplexity-research

Skill4 starsChanged 4 months agoMITView on GitHub

Веб-ресёрч через Perplexity Sonar API. Используй когда нужен актуальный поиск в интернете, факт-чек, анализ трендов, best practices. Триггеры: «загугли», «найди», «ресёрч», «что говорят про», «best practices», «как правильно», «perplexity».

  • Reads credentials

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Perplexity Web Research

Веб-ресёрч через Perplexity Sonar API с цитатами.

API Key

~/.claude/skills/perplexity-research/.secrets/perplexity.env

Загрузка: source ~/.claude/skills/perplexity-research/.secrets/perplexity.env → переменная PERPLEXITY_API_KEY

Set PERPLEXITY_API_KEY=<YOUR_API_KEY> in your environment or secrets file.

Использование

source ~/.claude/skills/perplexity-research/.secrets/perplexity.env

curl -s --max-time 60 "https://api.perplexity.ai/chat/completions" \
  -H "Authorization: Bearer $PERPLEXITY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "sonar-pro",
  "messages": [{"role": "user", "content": "your query here"}],
  "search_recency_filter": "month",
  "return_citations": true
}'

Модели

МодельДля чегоЦена
sonar-proГлубокий ресёрч, сложные вопросы~$3/1000 запросов
sonarБыстрый поиск, простые вопросы~$1/1000 запросов

Параметры

  • search_recency_filter: hour, day, week, month -- фильтр свежести
  • return_citations: true -- возвращает источники
  • temperature: 0.0-1.0 (по умолчанию 0.2)

Парсинг ответа

import json
data = json.loads(response)
text = data['choices'][0]['message']['content']
citations = data.get('citations', [])

Когда использовать

  • Актуальные данные из интернета
  • Best practices, how-to
  • Факт-чек утверждений
  • Анализ трендов и новостей
  • Сравнение технологий

Когда НЕ использовать

  • Internal data sources
  • Внутренние файлы/конфиги
  • Задачи не требующие веб-поиска

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.