菜单
Configure webhook callbacks for Kling AI task completion. Use when building event-driven pipelines or replacing polling. Trigger with phrases like 'klingai webhook', 'kling ai callback', 'klingai notifications', 'video completion webhook'.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/jeremylongshore/claude-code-plugins-plus-skills --skill klingai-webhook-config命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Implement user sign-up and sign-in flows with Clerk. Use when building authentication UI, customizing sign-in experience, or implementing OAuth social login. Trigger with phrases like "clerk sign-in", "clerk sign-up", "clerk login flow", "clerk OAuth", "clerk social login".
Implement session management and middleware with Clerk. Use when managing user sessions, configuring route protection, or implementing token refresh and custom JWT templates. Trigger with phrases like "clerk session", "clerk middleware", "clerk route protection", "clerk token", "clerk JWT".
Configure enterprise SSO, role-based access control, and organization management. Use when implementing SSO integration, configuring role-based permissions, or setting up organization-level controls. Trigger with phrases like "clerk SSO", "clerk RBAC", "clerk enterprise", "clerk roles", "clerk permissions", "clerk organizations".
正在显示 SKILL.md
基于 SOC 职业分类
| name | klingai-webhook-config |
| description | Configure webhook callbacks for Kling AI task completion. Use when building event-driven pipelines or replacing polling. Trigger with phrases like 'klingai webhook', 'kling ai callback', 'klingai notifications', 'video completion webhook'. |
| allowed-tools | Read, Write, Edit, Bash(npm:*), Grep |
| version | 1.18.0 |
| license | MIT |
| author | Jeremy Longshore <jeremy@intentsolutions.io> |
| tags | ["saas","kling-ai","webhooks","callbacks"] |
| compatibility | Designed for Claude Code, also compatible with Codex and OpenClaw |
Instead of polling task status, pass a callback_url when creating a task. Kling AI will POST the completed task result to your URL when generation finishes. This eliminates polling overhead and reduces API calls.
Supported on: All video generation endpoints (text2video, image2video, video-extend, lip-sync, effects)
callback_url in your task creation requestsucceed or failed), Kling POSTs the full result to your URLimport jwt, time, os, requests
BASE = "https://api.klingai.com/v1"
def get_headers():
ak, sk = os.environ["KLING_ACCESS_KEY"], os.environ["KLING_SECRET_KEY"]
token = jwt.encode(
{"iss": ak, "exp": int(time.time()) + 1800, "nbf": int(time.time()) - 5},
sk, algorithm="HS256", headers={"alg": "HS256", "typ": "JWT"}
)
return {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}
# Create task with callback
response = requests.post(f"{BASE}/videos/text2video", headers=get_headers(), json={
"model_name": "kling-v2-master",
"prompt": ,
: ,
: ,
: ,
})
task_id = response.json()[][]
()
from flask import Flask, request, jsonify
import hmac
import hashlib
import json
app = Flask(__name__)
@app.route("/webhooks/kling", methods=["POST"])
def kling_webhook():
payload = request.get_json()
task_id = payload["data"]["task_id"]
status = payload["data"]["task_status"]
if status == "succeed":
video_url = payload["data"]["task_result"]["videos"][0]["url"]
print(f"Task {task_id} complete: {video_url}")
# Download video, store to S3, notify user, etc.
process_completed_video(task_id, video_url)
elif status == "failed":
error = payload["data"].get("task_status_msg", "Unknown error")
print(f"Task {task_id} failed: {error}")
handle_failure(task_id, error)
return jsonify({"received": True}), 200
import express from "express";
const app = express();
app.use(express.json());
app.post("/webhooks/kling", (req, res) => {
const { data } = req.body;
const { task_id, task_status } = data;
if (task_status === "succeed") {
const videoUrl = data.task_result.videos[0].url;
console.log(`Task ${task_id} complete: ${videoUrl}`);
processVideo(task_id, videoUrl);
} else if (task_status === "failed") {
console.error(`Task ${task_id} failed: ${data.task_status_msg}`);
}
res.json({ received: true });
});
app.listen(3000);
{
"code": 0,
"message": "success",
"data": {
"task_id": "abc123...",
"task_status": "succeed",
"task_status_msg": "",
"task_result": {
"videos": [{
"id": "vid_001",
"url": "https://cdn.klingai.com/...",
"duration": "5.0"
}]
}
}
}
import time
from collections import defaultdict
class WebhookManager:
"""Track webhook delivery and fall back to polling on failure."""
def __init__(self, poll_fallback_sec: int = 300):
self.pending = {} # task_id -> submission_time
self.poll_fallback_sec = poll_fallback_sec
def register(self, task_id: str):
self.pending[task_id] = time.time()
def mark_received(self, task_id: str):
self.pending.pop(task_id, None)
def get_stale_tasks(self) -> list:
"""Tasks that haven't received a callback within threshold."""
now = time.time()
return [tid for tid, submitted in self.pending.items()
if now - submitted > self.poll_fallback_sec]
def fallback_poll(self, client):
"""Poll stale tasks that missed their callback."""
for task_id in self.get_stale_tasks():
try:
result = client._get(f"/videos/text2video/{task_id}")
status = result["data"]["task_status"]
if status in ("succeed", "failed"):
self.mark_received(task_id)
return result
except Exception:
pass
| Requirement | Detail |
|---|---|
| Protocol | HTTPS only |
| Response | Return 2xx within 5 seconds |
| Availability | Must be publicly reachable |
| Idempotency | Handle duplicate deliveries gracefully |
| Timeout | Kling retries on timeout, so process async |