Menu
Integrate GROQ LLM streaming into a project. Use when the user wants to add GROQ, set up GROQ streaming, or use a GROQ model in their app.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Scaffold, revise and manage custom ACF Gutenberg blocks for WordPress with Tailwind CSS. Use when the user wants to create a new block, revise/audit blocks, or set up a WordPress blocks project.
Scaffold one or more ACF Gutenberg blocks from GitHub issues, a markdown brief, or interactive prompts. Generates block.json, fields.json, render.php, and optional view.js.
Discuss a new block's purpose and requirements with the user, then create a GitHub issue with a structured breakdown ready for /wp-acf-blocks:add-block.
Deep AI audit of all blocks or specific blocks — runs structural checks first, then uses AI to review content quality, descriptions, grammar, admin render justification, wrapper usage, and empty-state messages.
Fast structural audit of all blocks or specific blocks — checks required files, wrapper attributes, fields.json timestamp, previewImage, viewScript. No AI, runs instantly via script.
Set up a new WordPress theme with the wp-acf-blocks block development workflow
| name | groq |
| description | Integrate GROQ LLM streaming into a project. Use when the user wants to add GROQ, set up GROQ streaming, or use a GROQ model in their app. |
| allowed-tools | Read Write Edit Bash |
Apply the pattern below to the current project's stack and existing code structure. Ask the user which model to use if not specified (default: llama-3.3-70b-versatile). Copy the .env block as a template — remind the user to fill in GROQ_API_KEY.
GROQ provides fast LLM inference via an OpenAI-compatible API — drop-in replacement for OpenAI, just swap the base URL and key.
POST https://api.groq.com/openai/v1/chat/completions
# Groq — enable by setting GROQ_API_KEY
GROQ_API_KEY=
GROQ_MODELS=llama-3.3-70b-versatile,llama-3.1-8b-instant
# LLM temperature (0 = deterministic, good for structured extraction)
LLM_TEMPERATURE=0
{
"model": "llama-3.3-70b-versatile",
"stream": true,
"temperature": 0,
"max_tokens": 16384,
"messages": [{ "role": "user", "content": "your prompt here" }]
}
Content-Type: application/json
Authorization: Bearer <GROQ_API_KEY>
Response is Server-Sent Events. For each line:
data: data: prefix[DONE]choices[0].delta.contentparseLine: line => {
if (!line.startsWith('data: ')) return null;
const data = line.slice(6).trim();
if (!data || data === '[DONE]') return null;
try {
const obj = JSON.parse(data);
return obj.choices?.[0]?.delta?.content || null;
} catch { return null; }
}
Check for non-2xx HTTP status before reading the stream. For stream errors, same SSE format applies — obj.error?.message on each parsed line.
Observed in phucbm/openwalletvn/api — admin/routes/extract.ts.
Part of a multi-provider LLM streaming abstraction (Ollama, Gemini, GROQ).