| name | x-audience-warmup |
|---|---|
| description | Use when starting an X (Twitter) account from scratch, when follower count is below 500, or when preparing an account to receive viral traffic before posting demo videos or trend-hijacking content. |
A cold X account with no followers wastes viral content. This skill covers the warm-up phase: getting from 0 to 500-1000 followers before deploying x-viral-demo-video or x-trend-hijacking posts.
Expected timeline: ~9 months from first post to first viral moment.
Anthropic changed billing so third-party API apps draw from "extra usage" credits, not plan limits. If you're on a Max/Pro subscription, using the anthropic/ provider hits API billing instead of your subscription. The claude-cli/ backend routes through the Claude Code CLI binary, which authenticates via your subscription β no API credits needed.
| # /// script | |
| # dependencies = [ "transformers", "accelerate" ] | |
| # /// | |
| # run on 2xH200 rented from primeintellect.ai | |
| import gc | |
| import torch | |
| from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer |
| # Frontend Design Guideline | |
| This document summarizes key frontend design principles and rules, showcasing | |
| recommended patterns. Follow these guidelines when writing frontend code. | |
| # Readability | |
| Improving the clarity and ease of understanding code. |
| from datetime import datetime | |
| import json | |
| import re | |
| import timeit | |
| from contextlib import contextmanager | |
| from dataclasses import dataclass | |
| from typing import Annotated, Any, Callable, Iterator, TypedDict | |
| from pydantic.annotated_handlers import GetJsonSchemaHandler |
| import "dotenv/config"; | |
| import { OpenAIEmbeddings } from "@langchain/openai"; | |
| import { TextLoader } from "langchain/document_loaders/fs/text"; | |
| import natural from "natural"; | |
| import * as math from "mathjs"; | |
| import { quantile } from "d3-array"; | |
| interface SentenceObject { | |
| sentence: string; | |
| index: number; |
| pub fn get_splade_vector( | |
| input: String, | |
| model: Model, | |
| tokenizer: &Tokenizer, | |
| ) -> Result<Vec<f32>, ServiceError> { | |
| let tokenized_inputs = tokenizer.encode(input, false).unwrap(); | |
| let tokens = tokenized_inputs.get_ids().to_vec(); | |
| let token_ids = Tensor::new(tokens.as_slice(), &candle_core::Device::Cpu) | |
| .map_err(|e| ServiceError::BadRequest(format!("Could not create tensor: {}", e)))?; |
| # Based on younesbelkada/finetune_llama_v2.py | |
| # Install the following libraries: | |
| # pip install accelerate==0.21.0 peft==0.4.0 bitsandbytes==0.40.2 transformers==4.31.0 trl==0.4.7 scipy | |
| from dataclasses import dataclass, field | |
| from typing import Optional | |
| import torch | |
| from datasets import load_dataset | |
| from transformers import ( |
| #!/bin/bash | |
| ### steps #### | |
| # verify the system has a cuda-capable gpu | |
| # download and install the nvidia cuda toolkit and cudnn | |
| # setup environmental variables | |
| # verify the installation | |
| ### | |
| ### to verify your gpu is cuda enable check |
