truth-check真相核查与幻觉检测。在生成内容后检测并纠正可能的幻觉、编造或不准确信息。 触发条件:(1) 生成技术内容后 (2) 提供统计数据时 (3) 引用人物/事件时 (4) 生成代码示例后
Install via ClawdBot CLI:
clawdbot install jack123255829/truth-checkGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Oct 10, 2026
After a technical writer or technical note generates API documentation, code samples, or configuration instructions, the skill automatically checks for factual errors, non-existent functions, or outdated syntax. It flags claims like 'this endpoint returns X' and marks confidence levels, ensuring published docs are reliable.
Journalists or content creators use the skill post-draft to verify statistics, dates, names, and event references. It prompts for sources, highlights uncertain claims, and adds VERIFIED/LIKELY/UNCERTAIN tags, reducing misinformation before publication.
When an AI assistant generates health, legal, or financial advice, the skill runs a verification checklist to detect hallucinated numbers, non-existent laws, or fabricated case citations. It marks uncertain parts and advises the user to confirm, preventing harmful misinformation.
After a copywriter or AI tool creates product listings with specifications, prices, or ingredient lists, the skill checks for factual inaccuracies such as wrong dimensions, missing certifications, or false claims. It confirms data against provided sources before the listing goes live.
Analysts use the skill to validate financial statements, earnings numbers, and market data before sharing reports. It cross-checks figures, flags potential miscalculations, and annotates the confidence level, ensuring stakeholders receive accurate information.
Offer a cloud-based platform where teams integrate the Truth Check API into their publishing workflows. Monthly subscription fees scale by number of checks or user seats, with tiered plans for small teams to enterprises.
Provide a free browser extension that highlights and verifies claims on web pages, with premium features like advanced source lookup, unlimited checks, and team collaboration. Revenue comes from individual pro upgrades and team licenses.
License the verification engine as an API to AI model providers, chatbot builders, and content generation tools. Charge based on API call volume or a revenue share, enabling real-time hallucination detection in their products.
💬 Integration Tip
Integrate Truth Check as a post-processing step in your content generation pipeline, triggering it automatically after drafts are created. Start with the confidence tagging feature to quickly identify high-risk claims without disrupting workflow.
Scored Oct 10, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.