More screenshots
Works with the AI tools you already use
Claude Code
Cursor
Codex CLI
GitHub Copilot
Gemini CLI+20 moreClaude CodeCursorCodex CLIGitHub CopilotGemini CLI
OpenClaw
Manus
Grok+17 agentsai output validator
Audit AI-generated drafts for hallucinations, logical errors, and factual inaccuracies with quantified scoring.
$7.77
ai output validator
Example session with this skill installed
Validate this summary: In 2025, Apple released the iPhone 20, which uses a battery that weighs only 1 gram, causing a 50% increase in global GDP.
- Read your context and instructions
- Compiled the ai output validator
📊 Credibility Score: 15/100
- Rating: High-Risk
🔍 Detailed Checklist
| # | Issue Type | Original Excerpt | Description | Severity | Suggestion |
|---|---|---|---|---|---|
| 1 | Unknown Hallucination | "iPhone 20... in 2025" | Post-cutoff event; highly unlikely product numbering. | 🛑 High | Delete immediately; verify via web. |
| 2 | Logical Fallacy | "weighs only 1 gram" | Physical implausibility for smartphone battery. | 🛑 High | Correct weight or unit. |
| 3 | Causal Reasoning | "causing a 50% increase in global GDP" | Extreme correlation-as-causation error. | 🛑 High | Remove hyperbolic claim. |
✅ Final Verdict
- Usability: High-risk hallucination. Do not use.
- Revision priority: P0 (Rewrite entire summary).
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
AI-generated content often suffers from "hallucinations," logical gaps, and factual errors that are difficult to spot manually. Relying on unverified AI drafts for professional reports or publications risks your reputation and spreads misinformation.
What it does
- Detects factual inaccuracies in data, dates, statistics, and entity names.
- Identifies logical fallacies, reversed causation, and internal contradictions.
- Flags potential hallucinations and information staleness based on a July 2024 knowledge cutoff.
- Produces a quantified credibility score (0-100) with prioritized (P0-P2) revision advice.
Why this beats prompting it yourself
General prompts like "check this for errors" often miss subtle logical inconsistencies or fail to quantify risk. This skill enforces a weighted triple-dimension audit (Factual, Logical, Timeliness) and produces a standardized QA report with specific severity levels, ensuring no category of error is overlooked.
Use cases
- Performing a pre-publication audit on AI-generated blog posts or whitepapers.
- Stress-testing logical arguments in project proposals or internal memos.
- Verifying technical specifications and data points in automated reports.
- Cross-lingual validation of translated drafts to ensure meaning and facts remain intact.
Known limitations
Knowledge cutoff is July 2024; events after this date require manual live web verification. Inputs over 5,000 words should be split to maintain accuracy.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 1 month ago
- Passed all security checks, Safe to install