菜单
Implement content policy compliance for Kling AI prompts and outputs. Use when filtering user prompts or handling moderation. Trigger with phrases like 'klingai content policy', 'kling ai moderation', 'safe video generation', 'klingai content filter'.
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-content-policy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。
基于 SOC 职业分类
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
| name | klingai-content-policy |
| description | Implement content policy compliance for Kling AI prompts and outputs. Use when filtering user prompts or handling moderation. Trigger with phrases like 'klingai content policy', 'kling ai moderation', 'safe video generation', 'klingai content filter'. |
| allowed-tools | Read, Write, Edit, Bash(npm:*), Grep |
| version | 1.18.0 |
| license | MIT |
| author | Jeremy Longshore <jeremy@intentsolutions.io> |
| tags | ["saas","kling-ai","content-policy","moderation"] |
| compatibility | Designed for Claude Code, also compatible with Codex and OpenClaw |
Kling AI enforces content policies server-side. Tasks with policy-violating prompts return task_status: "failed" with a content policy message. This skill covers pre-submission filtering to avoid wasted credits and API calls.
Kling AI prohibits prompts that generate:
| Category | Examples |
|---|---|
| Violence/gore | Graphic injuries, torture, weapons used violently |
| Adult/sexual | Explicit nudity, sexual acts, suggestive content |
| Hate/discrimination | Slurs, targeted harassment, supremacist imagery |
| Illegal activity | Drug manufacturing, terrorism, fraud instructions |
| Real people | Deepfakes of identifiable individuals without consent |
| Copyrighted characters | Trademarked characters (Mickey Mouse, Spider-Man) |
| Misinformation | Fake news, fabricated events presented as real |
| Self-harm | Suicide, eating disorders, self-injury instructions |
import re
class PromptFilter:
"""Filter prompts before sending to Kling AI to save credits."""
BLOCKED_PATTERNS = [
r"\b(nude|naked|explicit|nsfw|porn)\b",
r"\b(gore|dismember|torture|mutilat)\b",
r"\b(bomb|terroris|weapon|firearm)\b",
r"\b(suicide|self.harm|kill.yourself)\b",
r"\b(deepfake|impersonat)\b",
]
BLOCKED_TERMS = {
"blood splatter", "graphic violence", "child abuse",
"drug manufacturing", "hate speech",
}
def __init__(self):
self._patterns = [re.compile(p, re.IGNORECASE) p .BLOCKED_PATTERNS]
() -> [, ]:
lower = prompt.lower()
term .BLOCKED_TERMS:
term lower:
,
pattern ._patterns:
= pattern.search(prompt)
:
,
(prompt) > :
,
(prompt.strip()) < :
,
,
() -> :
pattern ._patterns:
prompt = pattern.sub(, prompt)
prompt.strip()
Always include safety-related negative prompts:
DEFAULT_NEGATIVE_PROMPT = (
"violence, gore, blood, nudity, sexual content, "
"weapons, drugs, hate symbols, distorted faces, "
"watermark, text overlay, low quality, blurry"
)
def safe_request(prompt: str, negative_prompt: str = ""):
"""Build request with safety defaults."""
combined_negative = f"{DEFAULT_NEGATIVE_PROMPT}, {negative_prompt}".strip(", ")
return {
"model_name": "kling-v2-master",
"prompt": prompt,
"negative_prompt": combined_negative,
"duration": "5",
"mode": "standard",
}
class SafeKlingClient:
"""Kling client with pre-submission content filtering."""
def __init__(self, base_client):
self.client = base_client
self.filter = PromptFilter()
def text_to_video(self, prompt: str, **kwargs):
is_safe, reason = self.filter.check(prompt)
if not is_safe:
raise ValueError(f"Content policy violation: {reason}")
# Add safety negative prompt
kwargs.setdefault("negative_prompt", "")
kwargs["negative_prompt"] = (
f"{DEFAULT_NEGATIVE_PROMPT}, {kwargs['negative_prompt']}".strip(", ")
)
return self.client.text_to_video(prompt, **kwargs)
def handle_policy_rejection(task_id: str, result: dict):
"""Handle content policy rejections gracefully."""
status_msg = result["data"].get("task_status_msg", "")
if "content policy" in status_msg.lower() or "policy violation" in status_msg.lower():
return {
"error": "content_policy_violation",
"message": "Your prompt was rejected by Kling AI's content policy. "
"Please revise to remove restricted content.",
"task_id": task_id,
"credits_consumed": False, # policy rejections typically don't consume credits
}
return {"error": "generation_failed", "message": status_msg, "task_id": task_id}
When building apps with user-submitted prompts: