← Back to Skills Marketplace
Truth Check
by
Jack123255829
· GitHub ↗
· v1.0.0
· MIT-0
395
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install truth-check
Description
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
Usage Guidance
This skill appears coherent and low-footprint, but note it advises running generated code and verifying external operations — those activities can execute untrusted code or perform side effects. If you install it, ensure the agent runs code in a sandbox or test environment, restrict access to sensitive systems/credentials, and require human review for high-risk outputs. If you need stricter controls, disable autonomous invocation for this skill or limit it to read-only verification tasks.
Capability Analysis
Type: OpenClaw Skill
Name: truth-check
Version: 1.0.0
The 'truth-check' skill bundle is a set of meta-instructions designed to improve the reliability of an AI agent by implementing fact-checking and hallucination detection protocols. It outlines triggers for verification (e.g., technical content, statistics, code) and provides a structured checklist for the agent to validate its own output before finalizing tasks. No malicious code, data exfiltration, or suspicious behaviors were identified in SKILL.md or _meta.json.
Capability Assessment
Purpose & Capability
Name/description (truth-check / fact-checking) align with SKILL.md: the file lists triggers, verification checklist, confidence tags, and a verification workflow that directly implements the stated goal.
Instruction Scope
Instructions stay on-topic but explicitly recommend actions that can have side effects: 'run generated code to test it' and 'verify external operations (files/API/messages)'. These are valid for fact-checking but imply the agent may execute code or access external resources — operators should ensure those executions are sandboxed and appropriate for their environment.
Install Mechanism
No install spec (instruction-only). Nothing is written to disk or downloaded as part of installation, minimizing supply-chain risk.
Credentials
Skill declares no environment variables, credentials, or config paths and the instructions do not reference any secrets or unrelated credentials. The requested capabilities are proportional to fact-checking.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent presence or modify other skills/settings. Autonomous invocation is allowed (platform default) but not elevated by this skill.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install truth-check - After installation, invoke the skill by name or use
/truth-check - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of "truth-check" skill for fact-checking and hallucination detection.
- Outlines clear triggers for truth-check: technical content, statistics, quotations, code, and external actions.
- Provides a results-oriented verification protocol with an actionable checklist.
- Introduces confidence labeling: VERIFIED, LIKELY, UNCERTAIN.
- Emphasizes independent verification, especially for numbers, code, and external operations.
Metadata
Frequently Asked Questions
What is 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. It is an AI Agent Skill for Claude Code / OpenClaw, with 395 downloads so far.
How do I install Truth Check?
Run "/install truth-check" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Truth Check free?
Yes, Truth Check is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Truth Check support?
Truth Check is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Truth Check?
It is built and maintained by Jack123255829 (@jack123255829); the current version is v1.0.0.
More Skills