SC

scepticagent-prompts

Reference and tuning tool for the ScepticAgent analysis prompts.

Install

mkdir -p .claude/skills/scepticagent-prompts && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13284" && unzip -o skill.zip -d .claude/skills/scepticagent-prompts && rm skill.zip

Installs to .claude/skills/scepticagent-prompts

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

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.
287 charsno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Provide access to full page analysis system prompt
  • Allow modification of analysis behavior
  • Adjust highlight categories and scoring
  • Understand instructions sent to the AI
  • Tune the output format of analysis or highlights
  • Access chat follow-up system prompt

How it works

The skill provides a reference to the ScepticAgent's AI prompts located in `background.js`, detailing their purpose, required output sections, and constraints. It allows users to understand and modify how the AI analyzes pages and generates highlights.

Inputs & outputs

You give it
User query about prompts, analysis behavior, or output format
You get back
Details of system prompts, JSON schema for highlights, constraints, and modification guidance

When to use scepticagent-prompts

  • Changing analysis behavior
  • Modifying highlight categories
  • Adjusting output scoring

About this skill

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.

When not to use it

  • When the user wants to perform web searches directly
  • When the user wants to extract information not related to page analysis or chat
  • When the user wants to modify the core `background.js` logic beyond prompt adjustments

Limitations

  • Page content is truncated to 10000 characters for analysis.
  • Highlights are limited to a maximum of 25.
  • Phrases for highlights must appear verbatim on the page.

How it compares

This skill offers direct insight into and control over the AI's underlying prompts and output schemas, enabling fine-grained customization of analysis behavior, unlike a black-box AI system.

Compared to similar skills

scepticagent-prompts side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
scepticagent-prompts (this skill)04moNo flagsIntermediate
ai-prompting17moNo flagsBeginner
sales-coach04moNo flagsAdvanced
literature-review5592moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

ai-prompting

jasonkneen

Effective communication strategies for AI-assisted development. Learn context-first prompting, phased interactions, iterative refinement, and validation techniques to get better results from Claude and other AI coding assistants.

111

sales-coach

daphatpharm4

Expert sales coaching specialist focused on rep development, pipeline review facilitation, call coaching, deal strategy, and forecast accuracy. Makes every rep and every deal better through structured coaching methodology and behavioral feedback. Use when Codex needs this specialist perspective, wor

00

literature-review

K-Dense-AI

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).

5591,298

markitdown

K-Dense-AI

Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.

177310

openalex-database

davila7

Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.

48202

market-sizing-analysis

wshobson

This skill should be used when the user asks to "calculate TAM", "determine SAM", "estimate SOM", "size the market", "calculate market opportunity", "what's the total addressable market", or requests market sizing analysis for a startup or business opportunity.

73142

Search skills

Search the agent skills registry