X/Twitter Research via Grok

What it does

When your agent uses it

• Building a digest of what tracked X accounts posted recently
• Pulling trending topics on X for a given category
• Researching a topic on X to find ideas for a Telegram post

Example prompts

• “Give me today's digest for the AI category accounts I follow on X.”
• “Search X for discussion of the latest crypto regulation news and summarize it.”
• “Show me trending X topics for the crypto category and cite the sources.”

Requirements

• An xAI API key
• A shell environment to run the bash scripts

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Read config/.env
2. 2Parse X_CATEGORIES to get available categories
3. 3For each: X_ACCOUNTS_ = handles, X_TOPICS_ = topics, X_ACCOUNTS__LABEL = name
4. 4Match user request to category label or use X_DEFAULT_CATEGORY
5. 5Pass to script via --accounts / --topics

What it can do on your machine

Read from SKILL.md and the folder at commit 8bbeead. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 10 files in scripts/ (Shell), which the agent can run.

  Shell commands in SKILL.md call:

  • bash
  • sh

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • x.com

  Also links to:

  • console.x.ai
  • docs.x.ai

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • XAI_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

X/Twitter Research via Grok loads about 1.8k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 91 tokens; SKILL.md has 546 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~91

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:25

  .sh` копирует скилл и, если есть `config/.env`, нормализует его через `sed -i`: некавыченные значения с пробелами оборач

• NoteMentions a .env fileSKILL.md:31

  cp config/.env.example config/.env

• NoteMentions a .env fileSKILL.md:34

  Edit `config/.env`: paste your key into `XAI_API_KEY`, configure accounts and topics.

• NoteMentions a .env fileSKILL.md:35

  ые значения с пробелами в скопированном `.env`.

• NoteMentions a .env fileSKILL.md:37

  **Without `.env`:** skill works with explicit `--accounts`, `--query`, `--topics`.

• NoteMentions a .env fileSKILL.md:39

  **With `.env`:** digests and trending ready out of the box.

• NoteMentions a .env fileSKILL.md:53

  1. Read `config/.env`

• NoteMentions a .env fileSKILL.md:59

  ts`/`--topics` explicit > category from `.env` > agent asks.

• NoteMentions a .env fileSKILL.md:69

  **Config-driven model** — model set in `.env`, auto-fallback if unavailable.

• NoteMentions a .env fileSKILL.md:76

  # Default category from .env

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from artwist-polyakov/polyakov-claude-skills at commit 8bbeead, republished under its MIT licence (© artwist-polyakov). 546 words, ~1,810 tokens.

name

x-research

description

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.

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

cp config/.env.example config/.env

X_CATEGORIES=ai,crypto         # available categories
X_DEFAULT_CATEGORY=ai           # default for "digest" without specifying

X_ACCOUNTS_AI_LABEL="AI & ML"
X_ACCOUNTS_AI=elonmusk,sama,AndrewYNg

X_TOPICS_AI=AI,LLM,GPT,Claude,agents,AGI

# Default category from .env
bash scripts/digest.sh --period today

# Specific category
bash scripts/digest.sh --category crypto --period week

# Explicit accounts (no .env needed)
bash scripts/digest.sh --accounts "elonmusk,sama" --period today

# By description
bash scripts/analyze.sh --query "Elon Musk's thread about open source AI"

# By URL
bash scripts/analyze.sh --url "https://x.com/elonmusk/status/123456" --query "context about the post"

# With time period
bash scripts/analyze.sh --query "debate about AI regulation" --period week

# Default topics from .env
bash scripts/trending.sh --period today

# Specific topics
bash scripts/trending.sh --topics "Bitcoin,Ethereum,DeFi" --period today

# Category
bash scripts/trending.sh --category ai --period week

# Free search
bash scripts/search.sh --query "Claude 4 reactions" --period week

# Search within specific accounts
bash scripts/search.sh --query "AI safety" --accounts "sama,ylecun" --period today

# Read last digest without making an API call
bash scripts/digest.sh --category ai --period today --prefer-cache

# Find artifact manually
bash scripts/find_latest.sh --script digest --category ai --period today

bash scripts/<script>.sh [params]

{
  "meta": {
    "script": "digest",
    "category": "ai",
    "handles": ["elonmusk", "sama"],
    "period": "today",
    "from_date": "2026-04-01",
    "to_date": "2026-04-01",
    "model": "grok-4-1-fast-reasoning",
    "created_at": "2026-04-01T14:30:22Z",
    "run_id": "a1b2c3"
  },
  "items": [...],
  "ideas": [...],
  "summary": "...",
  "text": "...",
  "citations": [...]
}

© artwist-polyakov, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 14 other files (scripts, references) in plugins/x-research/skills/x-research of artwist-polyakov/polyakov-claude-skills.

• SKILL.md
• .gitignore
• config/.env.example
• config/README.md
• references/API_REFERENCE.md
• scripts/analyze.sh
• scripts/common.sh
• scripts/digest.sh
• scripts/find_latest.sh
• scripts/prepare_runtime.sh
• scripts/sanitize_env.sh
• scripts/search.sh
• scripts/tests/run.sh
• scripts/tests/test_config_loader.sh
• scripts/trending.sh

Open the folder on GitHubat commit 8bbeead