Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsHallucination Inspector — Find Unsupported AI Claims
Audit AI claims, citations, contradictions, precision and action statements against actual supporting evidence.
$9.99
Hallucination Inspector — Find Unsupported AI Claims
Example session with this skill installed
Fictional example: An AI report says Revenue grew 40%, customers love the product, and I emailed the report. Evidence only shows revenue rising from $100 to $120; no feedback or send log exists. Produce a complete first-pass deliverable, separate facts from assumptions and give practical next steps. Do not take external actions.
- Read your context and instructions
- Compiled the hallucination inspector
Hallucination Inspector: worked example
Scope: this fictional brief, using only supplied information.
An AI report says Revenue grew 40%, customers love the product, and I emailed the report. Evidence only shows revenue rising from $100 to $120; no feedback or send log exists.
Deliverable
| Workstream | Finding / decision | Recommended action |
|---|---|---|
| Revenue | Actual increase is 20%, not 40% | Correct to: Revenue increased from $100 to $120, a 20% rise, for the supplied period. |
| Sentiment | No customer feedback evidence | Remove customers love the product or label it an unverified hypothesis requiring actual feedback. |
| Action claim | No email-send evidence | Replace I emailed the report with Report prepared; sending remains unverified. Do not imply an action completed. |
Decision and next steps
Publish only the corrected evidence-supported version. Keep a claim register with source and verification status; missing evidence is not proof the claim is false, but it does block presenting it as verified.
Evidence boundaries
Conclusions apply to the supplied scenario. Missing facts remain unverified; recommendations are not completed actions. Validate source data and approvals before implementation. Track results against the objective and adjust only when new evidence supports change.
Connects securely to your tools. The creator never sees your data.
About this skill
Hallucination Inspector
Audit AI claims, citations, contradictions, precision and action statements against actual supporting evidence.
Workflow and deliverables
- Correct to: Revenue increased from $100 to $120, a 20% rise, for the supplied period.
- Remove customers love the product or label it an unverified hypothesis requiring actual feedback.
- Replace I emailed the report with Report prepared; sending remains unverified. Do not imply an action completed.
Getting started
Provide your goal, relevant source material, constraints and context for hallucination inspector. Include dates, existing decisions and any restrictions that must be preserved.
Receive a structured deliverable with source facts, explicit assumptions, priorities, open questions and next steps. Adapt the depth to your available evidence; the sample below demonstrates the workflow with fictional inputs.
Boundaries
Uses supplied evidence and explicit assumptions. No guaranteed outcomes or continuous monitoring. Live research and external actions require supported tools and authorization.
Reusable agent instructions, with optional tool use depending on your host. External actions require supported tools and explicit authorization.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
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
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scanned
Verified clean 6 days ago
- Passed all security checks, Safe to install