Critically analyzes business ideas from documents, YouTube transcripts, blog posts, URLs, or pasted text. Detects hype/affiliate marketing, assesses viability, and evaluates fit for dotslash.dev — an AI consultancy AND productized SMB agency targeting Copenhagen. Use when user mentions 'analyze this idea', 'is this worth pursuing', 'evaluate this', 'idea-analyzer', or pastes content asking if a business idea is good. Supports deep analysis with competitive research.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.
Instruções da origem · Visualização somente leitura
name
idea-analyzer
description
Critically analyzes business ideas from documents, YouTube transcripts, blog posts, URLs, or pasted text. Detects hype/affiliate marketing, assesses viability, and evaluates fit for dotslash.dev — an AI consultancy AND productized SMB agency targeting Copenhagen. Use when user mentions 'analyze this idea', 'is this worth pursuing', 'evaluate this', 'idea-analyzer', or pastes content asking if a business idea is good. Supports deep analysis with competitive research.
Critically evaluate business ideas from any media source. Filter hype from substance. Assess fit for dotslash.dev — both the AI consulting segment and the productized SMB offering.
Input Detection
Detect input type from $ARGUMENTS:
Starts with http/https → URL
YouTube URL (youtube.com, youtu.be) → see YouTube Extraction below
Any other URL → WebFetch to extract article content
Starts with / or ~ → file path → Read tool
Flag: --refresh-context → regenerate business context (see below)
Everything else → treat as pasted text content
YouTube Extraction
Extract the video ID from the URL (v= param, or path segment for youtu.be links).
Use nix-shell for ephemeral transcript fetching — no permanent installation:
nix-shell -p python3Packages.youtube-transcript-api --run "python3 -c \"
from youtube_transcript_api import YouTubeTranscriptApi
ytt = YouTubeTranscriptApi()
transcript = ytt.fetch('<VIDEO_ID>')
for entry in transcript:
print(entry.text)
\""
Filter out nix store download noise (lines starting with these, copying, /nix) from stdout before processing.
Fallback chain:
nix-shell + youtube-transcript-api (primary — works for any public video, no API key needed)
If nix is unavailable, try: yt-dlp --write-auto-sub --skip-download --sub-lang en -o "/tmp/%(id)s" <URL> then read the generated .vtt file
If both fail, ask the user to paste the transcript text directly
Never attempt to analyze placeholder/error text. If extraction fails, stop and ask for content.
Extraction Failure Handling
If content extraction fails for any reason (paywall, 403, empty content, broken URL, missing file):
Inform the user what failed and why
Ask them to paste the content directly
Do NOT attempt to analyze error messages or partial/placeholder content
Flags
--deep — full structured report with competitive landscape, Danish market lens, implementation sketch
--save — persist analysis as Obsidian note in business/idea-analysis/
--refresh-context — re-read vault business notes and regenerate references/business-context.md
Flags can appear anywhere in $ARGUMENTS. Strip them before processing content.
Analysis Process
Step 1: Extract Content
Based on detected input type, extract the raw content to analyze. Follow the extraction and failure handling rules above.
Important: When assessing dotslash.dev fit, evaluate against BOTH business segments:
Segment A: AI consulting (strategy, implementation, partnership for tech teams)
Segment B: Productized SMB offering (chatbots + websites for Copenhagen local businesses)
An idea can fit one, both, or neither. Cross-segment fit (serves both) scores highest.
Step 4: Output Results
Analyze in English regardless of input language. If input is in Danish, extract and translate key claims before scoring.
Default (quick verdict):
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📋 IDEA: [Auto-extracted idea title]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔍 Idea Viability [🟢|🟡|🔴] [Verdict] — [One-line rationale]
⚠️ Hype/BS Score [🟢|🟡|🔴] [Verdict] — [One-line rationale]
🏢 dotslash.dev Fit [🟢|🟡|🔴] [Verdict] — [One-line rationale]
💰 Effort vs Payoff [🟢|🟡|🔴] [Verdict] — [One-line rationale]
💬 One-liner: "[Actionable summary — what to do with this]"
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
For dotslash.dev Fit, specify WHICH segment(s) the idea applies to:
"🟢 Strong fit (Segment B)" or "🟡 Explore further (both segments)" etc.
Traffic light meanings:
🟢 = Strong / Low risk / Strong fit / High payoff
🟡 = Explore further / Medium risk / Partial fit / Medium payoff
🔴 = Skip / High risk / Poor fit / Low payoff
Verdict labels: "Strong fit", "Explore further", "Skip", "Hype trap", "Steal one piece", "Park for later"
