check-test基于FastAPI的文本错敏信息检测服务,支持敏感词、错别字及规范表述问题检测,提供RESTful API接口。
Install via ClawdBot CLI:
clawdbot install 1227323804/check-testGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:8080/api/safeguard/checkCalls external URL not in known-safe list
https://safeguard-pre.ucap.com.cn/...AI Analysis
The skill acts as a proxy to a documented upstream API (safeguard-pre.ucap.com.cn) for content moderation, which aligns with its stated purpose. While it sends user data externally, this is an expected function of the service, not hidden exfiltration. The primary risk is reliance on an undocumented third-party endpoint.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
This skill can be integrated into social media platforms to automatically scan user-generated posts and comments for sensitive content, spelling errors, and non-standard expressions. It helps maintain a safe and professional online environment by flagging inappropriate language and improving content quality before publication.
Publishers and news organizations can use this API to proofread articles, reports, and other written materials for typos, sensitive terms, and compliance with editorial standards. It ensures content is accurate, politically correct, and adheres to style guides, reducing manual review time and minimizing errors.
Enterprises can deploy this service to screen internal and external communications, such as emails, reports, and marketing materials, for sensitive information and regulatory compliance. It helps prevent data leaks, avoid legal issues, and maintain brand reputation by detecting problematic language and ensuring professional wording.
E-learning platforms can integrate this skill to analyze educational materials, quizzes, and student submissions for errors and inappropriate content. It assists educators in maintaining high-quality, safe learning resources and provides feedback to students on language usage and correctness.
Customer service centers can use this API to automatically filter and flag incoming support tickets or chat messages for sensitive language, typos, and non-standard phrases. It improves response accuracy, ensures respectful communication, and helps prioritize urgent or problematic cases for human agents.
Offer this detection service through a subscription-based API, charging users based on the number of API calls or volume of text processed. This model provides recurring revenue and scales easily with client usage, appealing to developers and businesses needing flexible integration.
License the technology to large organizations as a customizable, white-labeled tool that they can integrate into their internal systems. This includes providing support, customization, and maintenance services, generating revenue through licensing fees and ongoing service contracts.
Provide a free tier with basic detection capabilities and limited usage to attract individual users and small businesses. Upsell premium features such as advanced sensitivity categories, higher processing limits, and priority support, converting free users into paying customers over time.
💬 Integration Tip
Ensure the userKey is securely managed and the service is deployed behind a firewall for production use to protect sensitive data and API credentials.
Scored Apr 19, 2026
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Systematic code review patterns covering security, performance, maintainability, correctness, and testing — with severity levels, structured feedback guidance, review process, and anti-patterns to avoid. Use when reviewing PRs, establishing review standards, or improving review quality.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions