agentleFS
Sign inStart free
srezai-teamsrezai-team/srezai-web-search-pro-skill/llms.txt

srezai-web-search-pro-skill

llms.txt3 starsChanged 8 days agoApache-2.0View on GitHub

13 tools over MCP at https://srezai.ru/api/mcp; the same tools via CLI srezai (npm package srezai-cli, zero dependencies) and REST base https://srezai.ru. Runet-first coverage, PDF, screenshots, site crawls, schema extraction, claim verification with quotes, synthesized answers and deep research. Generated from src/tools.json v0.5.0.

Create a free account to mount
Files
llms.txt
# srezai — web access for AI agents

13 tools over MCP at https://srezai.ru/api/mcp; the same tools via CLI `srezai`
(npm package `srezai-cli`, zero dependencies) and REST base https://srezai.ru.
Runet-first coverage, PDF, screenshots, site crawls, schema extraction, claim
verification with quotes, synthesized answers and deep research.

## Skills (6 narrow skills, Apache-2.0)

```bash
npx skills add srezai-team/srezai-web-search-pro-skill
```

- srezai-web: веб-доступ для агентов: точка входа
- srezai-search: найти ссылки, факты и картинки
- srezai-read: прочитать страницу, вытащить поля, увидеть вёрстку
- srezai-site: карта сайта и обход раздела
- srezai-research: проверить факт, собрать ответ, исследовать тему
- srezai-transcript: субтитры и текст видео YouTube

## Tools

- web_search: Search the web: links, facts, snippets. Price: 1 credit per call.
- image_search: Find images and direct file URLs. Price: 1 credit per call.
- read_url: Read the text of a page whose URL you already have. Price: 1 credit per call.
- read_urls: Read several known pages in one batch. Price: 1 credit per link.
- extract: Pull a few specific values off a page with a JSON schema. Price: 2 credits per link.
- fetch_page: See the layout, typography or a broken page as a screenshot. Price: 3 credits; 1 if the browser could not render the page.
- map: Map a site: sections, URLs, how large it is. Price: 1 credit per 10 URLs returned, minimum 1.
- crawl: Walk a section of a site and read its pages. Price: map + 1 credit per page read.
- verify_claim: Check one claim and get a verdict with verbatim quotes. Price: 8 credits per call.
- answer_search: Get one synthesized answer across several sources. Price: 3 (fast) / 5 (balanced) / 10 (deep) credits.
- deep_research: Run multi-step research and get a finished answer with sources. Price: 20 credits + 3 per 1000 output tokens.
- yt_srt: YouTube video text: transcripts, summaries, quotes. Price: 1 credit per video; 15 with speaker labeling.
- get_usage: Check balance, remaining quota, spend and the price list. Price: free; does not use the quota.

Generated from src/tools.json v0.5.0.

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