compliance_review
Filters text content for sensitive topics and NSFW keywords before content generation.
Install
mkdir -p .claude/skills/compliance-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16317" && unzip -o skill.zip -d .claude/skills/compliance-review && rm skill.zipInstalls to .claude/skills/compliance-review
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
内容安全与合规审核工具。在生成任何视觉内容前，必须确保不触碰平台红线。Key capabilities
- →Check text content against a sensitive keyword list
- →Provide feedback on blocked content
- →Weakening descriptions of extreme violence
- →Filtering political or contraband sensitive metaphors
- →Updating shot status in a database upon compliance pass
How it works
The skill checks provided text content against a list of sensitive keywords. If keywords are found, it blocks the content and provides feedback. If safe, it updates the shot's status in a SQLite database.
Inputs & outputs
When to use compliance_review
- →Screening scripts for sensitive content
- →Automating safety checks in visual storytelling
- →Updating project status after content moderation
About this skill
平台合规审查
你不仅是导演，也是发行制片。必须过滤：
极度血腥暴露
- 将"斩首"弱化为"致命一击"
- 将"血肉模糊"弱化为"激烈战斗"
- 过度血腥暴露的描写都需要弱化
政治违禁品敏感隐喻
- 政治、违禁品等敏感隐喻必须过滤
- 敏感内容都需要进行适当处理
NSFW 关键词库
["血肉模糊", "斩首", "断肢", "色情", "裸露", "血腥", "残忍", "恐怖", "虐杀"
def execute(params):
import sqlite3
import os
content = params.get("text_content", "")
shot_id = params.get("shot_id", "")
# 实际项目中，这里通常会调用阿里云/腾讯云的内容安全 API (Text Moderation)
# 这里做简单的本地敏感词拦截作为示例
nsfw_keywords = ["血肉模糊", "斩首", "断肢", "色情", "裸露", "血腥", "残忍", "恐怖", "虐杀"]
found_keywords = []
for word in nsfw_keywords:
if word in content:
found_keywords.append(word)
if found_keywords:
return {
"status": "blocked",
"feedback": f"触发合规风控：包含敏感描写：{', '.join(found_keywords)}。请修改表达方式（如使用剪影或隐晦镜头替代）。"
}
# 如果有 shot_id，更新 shot 的状态
if shot_id:
# 数据库路径
db_path = os.path.join(os.path.dirname(__file__), "../../project/evolution_log.db")
conn = sqlite3.connect(db_path)
cursor = conn.cursor()
cursor.execute('UPDATE shots SET status = ? WHERE shot_id = ?', ('compliance_passed', shot_id))
conn.commit()
conn.close()
return {
"status": "safe",
"message": "内容安全风控通过。"
}
When not to use it
- →When generating visual content before compliance review
- →When sensitive content is not properly handled
Limitations
- →Uses a simple local sensitive word interception as an example.
- →Relies on a predefined list of NSFW keywords.
- →Does not call external content moderation APIs.
How it compares
This skill automates content safety and compliance review by checking text against a keyword list and providing immediate feedback, unlike manual content moderation processes.
Compared to similar skills
compliance_review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| compliance_review (this skill) | 0 | 3mo | No flags | Beginner |
| solidity-security | 15 | 2mo | No flags | Intermediate |
| supabase-rls-policy-generator | 11 | 9mo | No flags | Advanced |
| backend-security-coder | 24 | 4mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
solidity-security
wshobson
Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.
supabase-rls-policy-generator
hopeoverture
This skill should be used when the user requests to generate, create, or add Row-Level Security (RLS) policies for Supabase databases in multi-tenant or role-based applications. It generates comprehensive RLS policies using auth.uid(), auth.jwt() claims, and role-based access patterns. Trigger terms include RLS, row level security, supabase security, generate policies, auth policies, multi-tenant security, role-based access, database security policies, supabase permissions, tenant isolation.
backend-security-coder
sickn33
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
sqlmap-database-penetration-testing
davila7
This skill should be used when the user asks to "automate SQL injection testing," "enumerate database structure," "extract database credentials using sqlmap," "dump tables and columns from a vulnerable database," or "perform automated database penetration testing." It provides comprehensive guidance for using SQLMap to detect and exploit SQL injection vulnerabilities.
agent-security-manager
ruvnet
Agent skill for security-manager - invoke with $agent-security-manager
secure-workflow-guide
trailofbits
Guides through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features (upgradeability/ERC conformance/token integration), generates visual security diagrams, helps document security properties for fuzzing/verification, and reviews manual security areas.