ScepticAgent Prompts Reference

VerifiedSafe

Complete reference of prompts used by ScepticAgent to analyze web pages, verify sources, and detect bias and misinformation.

Sby Skills Guide Bot
Data & AIIntermediate
007/23/2026
Claude Code
#scepticagent#ai-prompts#misinformation-analysis#bias-detection#content-verification

Recommended for

Our review

Reference for ScepticAgent AI prompts, enabling customization of web page analysis to detect misinformation, bias, and emotional language.

Strengths

  • Structured misinformation detection with categories and scoring
  • Leverages web search to verify claims in real-time
  • JSON output easily parseable for highlights and analysis
  • Fine-grained control over analysis categories and behavior

Limitations

  • Limited to 10,000 characters of page content
  • Relies on web search function (may fail if unavailable)
  • Highlights must be verbatim from the page, which can be restrictive
When to use it

When you need to instruct the AI to objectively analyze a web page with source verification and bias highlighting.

When not to use it

For creative or subjective analyses where factual verification is not relevant.

Security analysis

Safe
Quality score90/100

This skill is a static reference document describing AI prompt locations, formats, and constraints for a browser extension. It contains no executable instructions, no tool declarations, and no dangerous operations. It poses no execution risk.

No concerns found

Examples

Change analysis categories
Modify the buildAnalysisSystem prompt to include a new category 'Logical Fallacies' with its own output section.
Adjust highlight format
Update the highlights prompt to increase the maximum number of highlights from 25 to 40.
Tune scoring behavior
Add a numerical score (0-10) for each highlight category in the JSON output of the highlights prompt.

name: scepticagent-prompts description: ScepticAgent AI prompt reference. Use whenever the user asks about the prompts, wants to change analysis behaviour, modify what the AI looks for, adjust highlight categories or scoring, understand what instructions are sent to the AI, or tune the output format of analysis or highlights.

Prompt locations — all in background.js

buildAnalysisSystem(url, title, content) — lines 658–705

Full page analysis system prompt. Instructs Claude to use web_search to verify claims, check source credibility, find supporting/opposing evidence, identify bias and emotional language. Page content truncated to 10000 chars.

Required output sections (renderer depends on these exact headings):

## Key Claims
## References & Sources
## Supporting Evidence
## Opposing Perspectives
## Bias & Framing
## Emotional Language
## Misinformation Risks
## Overall Assessment

Sources must be cited as inline markdown links e.g. [Reuters](https://reuters.com/...).


buildChatSystem(url, title, content) — lines 707–720

Chat follow-up system prompt. Instructs the agent to answer questions about the page using web search and cite sources as inline markdown links. Page content truncated to 10000 chars.


buildHighlightsPrompt(withSearch) — lines 108–140

Extracts verbatim phrases from the page. Two modes:

  • withSearch: true — includes STEP 1 (web_search for real URLs) / STEP 2 (output JSON). Used in manual "Highlight Page" after analysis is complete.
  • withSearch: false — JSON output only, source_url left empty. Used in the auto fast scan on page open.

Output JSON schema:

{
  "summary": "two sentences — what the article is about, then how emotional/factual/biased it is",
  "category_summaries": {
    "misinformation": "one sentence",
    "emotional": "one sentence",
    "bias": "one sentence",
    "supported": "one sentence",
    "logical": "one sentence"
  },
  "highlights": [
    {
      "phrase": "verbatim text from page (8–180 chars, no quote characters)",
      "category": "misinformation|emotional|bias|supported|logical",
      "note": "max 90 chars explanation",
      "source": "publication name or empty string",
      "source_url": "full URL or empty string"
    }
  ]
}

Constraints: max 25 highlights, phrases must appear verbatim on the page, no markdown code fences in output, no typographic quote characters in phrases.

Related skills