Maros112358/scepticagent / .claude/skills/scepticagent-prompts
scepticagent-prompts
VerifiedScepticAgent 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_urlleft 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
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |