All skills

X/Twitter research via xAI Grok API with x_search tool. Digests, thread analysis, trending topics, custom search. Designed for finding Telegram post ideas from X discussions. Triggers: x research, twitter research, x digest, twitter digest, что в твиттере, дайджест твиттера, тренды x, trending x, analyze tweet, анализ твита, x search, поиск в твиттере.

Use this Skill: https://skilld.dev/gh/artwist-polyakov/polyakov-claude-skills/x-research

This session only. Nothing lands on disk.

configREADME.md

≈532 tokens on demand. Your agent reads this file only when SKILL.md points to it.

X Research — Config Setup

1. Get xAI API Key

  1. Go to console.x.ai
  2. Sign up / log in
  3. Navigate to API Keys
  4. Create a new key (starts with xai-)

2. Create .env

cp .env.example .env

Edit .env and paste your key into XAI_API_KEY.

Important: keep .env shell-compatible. If a value contains spaces, wrap the whole value in quotes. Some runners use . config/.env, and unquoted values such as Claude Code will be treated as commands.

Перед запуском скриптов из установленного скилла сначала создайте рабочую копию:

sh scripts/prepare_runtime.sh
cd /home/claude/x-research

Подготовка также запускает sed -i для скопированного config/.env и заключает некавыченные значения с пробелами в кавычки. Не выводите содержимое .env при разборе ошибок настройки; указывайте пользователю только имена переменных, которые нужно исправить.

3. Configure accounts & topics

Edit .env to add X accounts you want to follow and topics you care about.

Category system (same as telegram-channel-parser):

# Register categories
X_CATEGORIES=ai,crypto

# Define each category
X_ACCOUNTS_AI_LABEL="AI & ML"
X_ACCOUNTS_AI=elonmusk,sama,AndrewYNg

X_ACCOUNTS_CRYPTO_LABEL="Crypto"
X_ACCOUNTS_CRYPTO=VitalikButerin,cz_binance

# Quote values with spaces
X_TOPICS_OPENAI="GPT,ChatGPT,OpenAI,Codex,gpt 5.4"
X_TOPICS_ANTHROPIC="Claude,Anthropic,ClaudeCode,Claude Code"

Note: allowed_x_handles API limit is 10 per request. Categories with >10 accounts are automatically batched.

4. Model selection

Default model: grok-4-1-fast-reasoning (fast & cheap).

If unavailable, auto-fallback to grok-4.20-reasoning.

Override in .env:

XAI_MODEL=grok-4.20-reasoning

Check available models: docs.x.ai/developers/models

Source: SKILL.md on GitHub

1 warning17d3 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    The skill facilitates research of X (Twitter) content via the xAI Grok API. It implements good security practices including input validation and environment variable sanitization. The primary security considerations are the inherent risk of indirect prompt injection from external social media data and the use of dynamic shell variable resolution, which is properly restricted to prevent exploitation.

  • Socket17d

    No alerts

  • Snyk17d

    Risk: MEDIUM · 1 issue

Signed by skilld at 0c3198c. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 5 months ago

README badge

README badge for artwist-polyakov/polyakov-claude-skills/x-research