← Back to Skills Marketplace
Truthcheck
by
Xiaobing Li
· GitHub ↗
· v0.4.4
· MIT-0
757
Downloads
0
Stars
2
Active Installs
5
Versions
Install in OpenClaw
/install truthcheck
Description
Verify claims, fact-check content, check URL trustworthiness, and trace claims to their origin using the TruthCheck CLI. Use when: (1) user asks to fact-chec...
Usage Guidance
This skill is an instruction-only wrapper that calls an external truthcheck CLI. Before installing or running it: 1) Confirm the origin of the 'truthcheck' package (inspect the pip package or source repository) — the skill bundle contains no code to review. 2) Understand that providing LLM/search API keys grants the CLI access to those services and could incur charges; prefer local models (e.g., --llm ollama) if you want to avoid sending data to third parties. 3) Treat the SKILL.md statement that keys are 'never sent to any external service' as unverifiable here — if this matters, audit the truthcheck package source or monitor network calls. 4) Note a minor metadata inconsistency: bundled _meta.json reports version 0.4.0 while registry metadata lists 0.4.4 — consider confirming you have the intended release.
Capability Analysis
Type: OpenClaw Skill
Name: truthcheck
Version: 0.4.4
The 'truthcheck' skill bundle provides metadata and instructions for a fact-checking CLI tool. The SKILL.md file contains clear, functional instructions for an AI agent to verify claims, check URL trustworthiness, and trace misinformation sources using standard CLI commands. There is no evidence of malicious intent, prompt injection, or unauthorized data access; the mention of API keys is consistent with the tool's stated requirement for LLM and search engine integration.
Capability Assessment
Purpose & Capability
Name/description align with requirements: the skill simply wraps a truthcheck CLI. It requires the 'truthcheck' binary and optionally LLM/search API keys, all of which are coherent with fact-checking functionality.
Instruction Scope
SKILL.md confines runtime behavior to invoking the truthcheck CLI and using files/URLs provided by the user. It does not instruct reading unrelated system files. One claim — that API keys are 'never sent to any external service' — is a statement about behavior that cannot be confirmed from these instructions and could be misleading depending on how the CLI implements provider calls.
Install Mechanism
No install spec in the skill bundle (instruction-only). Installation instructions point to pip (pip install truthcheck) or an npx-based installer; these are standard package installation methods and not inherently suspicious.
Credentials
Declared env vars (GEMINI_API_KEY, OPENAI_API_KEY, ANTHROPIC_API_KEY, BRAVE_API_KEY) are directly relevant to optional LLM or search integrations. No unrelated credentials or system config paths are requested.
Persistence & Privilege
Skill does not request persistent/system-wide privileges, always:false, no config paths, and is user-invocable. It does not instruct modifying other skills or global agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install truthcheck - After installation, invoke the skill by name or use
/truthcheck - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.4.4
Add installation guide to SKILL.md
v0.4.3
Fix: --llm is optional
v0.4.2
Clarify LLM is optional, add ollama support docs, add privacy note about API keys
v0.4.1
Document required environment variables for LLM and search providers
v0.4.0
- Added detailed usage instructions and command examples for verifying claims, checking URLs, tracing claim origins, publisher lookups, and syncing the database.
- Introduced explanation of the TruthScore, including a scoring table and interpretation guide.
- Highlighted the requirement to use `--llm gemini` for higher accuracy in claim verification.
- Provided practical tips for better results, batch processing, and using alternative search methods.
- Updated metadata for improved integration and clarity on requirements.
Metadata
Frequently Asked Questions
What is Truthcheck?
Verify claims, fact-check content, check URL trustworthiness, and trace claims to their origin using the TruthCheck CLI. Use when: (1) user asks to fact-chec... It is an AI Agent Skill for Claude Code / OpenClaw, with 757 downloads so far.
How do I install Truthcheck?
Run "/install truthcheck" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Truthcheck free?
Yes, Truthcheck is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Truthcheck support?
Truthcheck is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Truthcheck?
It is built and maintained by Xiaobing Li (@baiyishr); the current version is v0.4.4.
More Skills