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 โ 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.
Standardmรครig ist der Prompt ausgewรคhlt, der zuerst die Quelle prรผft. Sie kรถnnen zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prรผfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich fรผr eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fรผgen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prรผfen und installieren.
Ein direkter Befehl รผberspringt den Prรผf-Prompt. Prรผfen Sie die Quelle, bevor Sie ihn ausfรผhren.
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 โ 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 โ both the AI consulting segment and the productized SMB offering.
Input Detection
Detect input type from $ARGUMENTS:
Starts with http/https โ URL
YouTube URL (youtube.com, youtu.be) โ see YouTube Extraction below
Any other URL โ WebFetch to extract article content
Starts with / or ~ โ file path โ Read tool
Flag: --refresh-context โ regenerate business context (see below)
Everything else โ 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 โ 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 โ 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 โ full structured report with competitive landscape, Danish market lens, implementation sketch
--save โ persist analysis as Obsidian note in business/idea-analysis/
--refresh-context โ 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):
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ IDEA: [Auto-extracted idea title]
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ Idea Viability [๐ข|๐ก|๐ด] [Verdict] โ [One-line rationale]
โ ๏ธ Hype/BS Score [๐ข|๐ก|๐ด] [Verdict] โ [One-line rationale]
๐ข dotslash.dev Fit [๐ข|๐ก|๐ด] [Verdict] โ [One-line rationale]
๐ฐ Effort vs Payoff [๐ข|๐ก|๐ด] [Verdict] โ [One-line rationale]
๐ฌ One-liner: "[Actionable summary โ what to do with this]"
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
For dotslash.dev Fit, specify WHICH segment(s) the idea applies to:
"๐ข Strong fit (Segment B)" or "๐ก Explore further (both segments)" etc.
Traffic light meanings:
๐ข = Strong / Low risk / Strong fit / High payoff
๐ก = Explore further / Medium risk / Partial fit / Medium payoff
๐ด = Skip / High risk / Poor fit / Low payoff
Verdict labels: "Strong fit", "Explore further", "Skip", "Hype trap", "Steal one piece", "Park for later"
