polloaiofficial/pollo-skills / skills/pollo-ai-video-generator
pollo-ai-video-generator
UnverifiedGenerate AI videos using the Pollo AI API. Supports 13 leading models (Kling, Sora, Runway, Veo, Pixverse, Hailuo, Vidu, Luma, Pika, Wan, Seedance, Hunyuan, Pollo) with 50+ versions. It also supports task polling, credit cost estimation, and credit balance checks. Use this skill whenever the user wants to generate an AI video from text or image, use any AI video model, check Pollo credits, or mentions Pollo AI, pollo.ai, or any of the supported model names. Even if the user just says "generate a video" or "make me a short clip" without mentioning Pollo, this skill should be used.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.5 KB |
| agents/openai.yaml | config | 310 B |
| references/brands/bytedance.md | markdown | 6.7 KB |
| references/brands/google.md | markdown | 9.1 KB |
| references/brands/hunyuan.md | markdown | 1.2 KB |
| references/brands/kling-ai.md | markdown | 13.4 KB |
| references/brands/luma.md | markdown | 4.2 KB |
| references/brands/minimax.md | markdown | 4.4 KB |
| references/brands/pika.md | markdown | 2.8 KB |
| references/brands/pixverse.md | markdown | 10.8 KB |
| references/brands/pollo.md | markdown | 4.2 KB |
| references/brands/runway.md | markdown | 1.8 KB |
| references/brands/sora.md | markdown | 2.4 KB |
| references/brands/vidu.md | markdown | 8.1 KB |
| references/brands/wanx.md | markdown | 7.4 KB |
| references/common.md | markdown | 3.1 KB |
| references/models-index.md | markdown | 4.8 KB |
| scripts/poll_task.py | script | 5.7 KB |
| scripts/pollo_api.py | script | 3.8 KB |
| scripts/pollo_config.py | script | 3.0 KB |
| scripts/pollo_setup.py | script | 4.1 KB |
scripts/pollo_api.py
View on GitHub#!/usr/bin/env python3
"""
Unified API wrapper for Pollo AI. Keeps API key out of LLM context.
Usage:
python3 pollo_api.py <METHOD> <endpoint> [--data JSON] [--upload FILE]
Examples:
python3 pollo_api.py GET /credit/balance
python3 pollo_api.py POST /generation/pollo/pollo-v2-0 --data '{"input":{...}}'
python3 pollo_api.py POST /file/sign --data '{"action":"putObject","filename":"photo.jpg","type":"image/jpeg"}'
python3 pollo_api.py PUT <signed-url> --upload /path/to/file.jpg --content-type image/jpeg
Exit codes: 0 = success, 1 = API error, 2 = config error
"""
import argparse
import json
import sys
import urllib.request
import urllib.error
from pathlib import Path
from typing import Optional, Tuple, Union
# Import config from same directory
sys.path.insert(0, str(Path(__file__).resolve().parent))
from pollo_config import load_config
def api_request(method: str, url: str, headers: dict, data: Optional[bytes] = None) -> Tuple[int, Union[dict, str]]:
"""Make HTTP request, return (status_code, parsed_response)."""
req = urllib.request.Request(url, data=data, headers=headers, method=method)
try:
with urllib.request.urlopen(req, timeout=60) as resp:
body = resp.read().decode()
try:
return resp.status, json.loads(body)
except json.JSONDecodeError:
return resp.status, body
except urllib.error.HTTPError as e:
body = ""
try:
body = e.read().decode()
except Exception:
pass
try:
return e.code, json.loads(body)
except json.JSONDecodeError:
return e.code, {"error": body, "status_code": e.code}
def main():
parser = argparse.ArgumentParser(description="Pollo AI API wrapper")
parser.add_argument("method", choices=["GET", "POST", "PUT"], help="HTTP method")
parser.add_argument("endpoint", help="API endpoint (e.g. /credit/balance) or full URL for PUT uploads")
parser.add_argument("--data", help="JSON request body")
parser.add_argument("--upload", help="File path to upload (binary PUT)")
parser.add_argument("--content-type", default="application/octet-stream", help="Content-Type for file upload")
args = parser.parse_args()
# For PUT uploads to signed URLs (external), skip config loading
is_external_url = args.endpoint.startswith("http://") or args.endpoint.startswith("https://")
if is_external_url and args.upload:
# Direct file upload to signed URL — no API key needed
file_path = Path(args.upload)
if not file_path.exists():
print(json.dumps({"error": f"File not found: {args.upload}"}))
sys.exit(1)
file_data = file_path.read_bytes()
headers = {"Content-Type": args.content_type}
status, response = api_request(args.method, args.endpoint, headers, file_data)
else:
# Normal API call — load config for key
try:
config = load_config()
except (FileNotFoundError, ValueError) as e:
print(json.dumps({"error": str(e)}))
sys.exit(2)
url = config["base_url"].rstrip("/") + args.endpoint if not is_external_url else args.endpoint
headers = {
"X-API-KEY": config["api_key"],
"Content-Type": "application/json",
"User-Agent": "Pollo-AI-Skill/1.0",
}
body = args.data.encode() if args.data else None
status, response = api_request(args.method, url, headers, body)
# Output result
if isinstance(response, dict):
print(json.dumps(response, indent=2, ensure_ascii=False))
else:
print(response)
# Exit code based on HTTP status
if 200 <= status < 300:
sys.exit(0)
else:
sys.exit(1)
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |