Build this tool: Clickbait Ethics Title Checker Product folder name: Clickbait Ethics Title Checker PRODUCT BRIEF General title ethics checker for any creator niche (YouTube, TikTok, Shorts, blogs). Paste a draft title → flag risky / controversial / advertiser-unfriendly phrasing → suggest softer high-CTR alternatives that keep curiosity without platform risk. Not gaming-only. Covers exclusion bait, shock/harm sensationalism, crude or sexualized hooks, tragedy bait, scam money, health fearmongering, fake urgency, classic misleading clickbait, and related patterns. Gaming tropes (girls-only tournament, etc.) still work as one category among many. CONTEXT Difficulty: Medium Category: Creator tools / SEO + channel safety TREND HOOK "This title style might be getting creators demonetized" — works for gaming, lifestyle, commentary, health, drama, and more. VIDEO ANGLE Short: paste a risky title → show flags + softer rewrites. Long: run several real trending titles across niches through the checker. WHY THIS TOOL SEO + channel-safety angle; useful beyond one game community. STACK (standalone desktop app) - Python 3 + tkinter GUI — standalone desktop tool (not a website). - Even if the brief says "web app" / "site", ship a Python desktop GUI for v1. - Include: main .py, requirements.txt, run_*.bat, build_exe.bat (PyInstaller), and an exports/ folder for saved output. - Smoke-test core logic offline without requiring live API keys when possible. GUI RULES - Clean, readable dark or light UI — pick one consistent palette (no brand lock-in required). - Clear app title / hero name derived from the product folder name. - Short muted "How to use: …" line under the title (one sentence: what to enter → what button → what you get). - Prefer real inputs (paste URL / fields / text) over fake demos. - No sample dropdowns or canned demo datasets unless explicitly requested. - Dropdowns: NEVER ttk.Combobox (unreadable on Windows dark UI). Use DarkSelect (preferred, no grab_set) OR dark-styled tk.OptionMenu (BG_ELEVATED / TEXT / active #243056 / BORDER+TEAL highlight; style the popup menu the same way). Never use grab_set (breaks close behavior on Windows). - Handle window close with WM_DELETE_WINDOW. - One job per tool; working copy/export; avoid overbuilt dashboards. APIs & KEYS - Never hardcode API keys or secrets into source or the packaged EXE. - Store keys in a local user settings JSON under %LOCALAPPDATA%\\ (or a single shared settings file if multiple tools share a key). - Label each key field clearly in the UI (e.g. YouTube API key vs Gemini API key). - Local/offline logic must work first; APIs are optional enhancements where possible. - Call network APIs in a background thread; update the UI with after(...). On failure, keep local results and show a clear error. Gemini API (optional copy / polish) - Add Gemini (AI-first for paste-ready copy) when the tool WRITES language creators will paste online (titles, captions, descriptions, pinned comments, end-cards, disclaimers, SEO templates). - UI: API key field + Model text field + checkbox like "Use Gemini" / "Polish with Gemini". - Default model: gemini-2.5-flash-lite. Also accept typed model ids (e.g. gemini-3.1-flash-lite). - Do not hardcode the model URL/path; pass the Model field value into the generate call. - Pattern: Local pattern library decides verdict/score first. Gemini only adds softer title alternatives that match the original niche (do not force gaming lobby language on non-gaming titles). - On Gemini failure: keep local output, show error, do not wipe results. - Flash Lite is enough for short creative jobs — do not default to Pro. Other APIs (only if the product brief needs them) - None required for v1. IMPLEMENTATION NOTES - Match the product brief closely; keep v1 focused on one job. - Support Copy and/or Export of results where useful (TXT/CSV/JSON as fits the tool). - Validate inputs; show empty/error states clearly. - If scoring/grading: show score + short explanation of what failed/passed. - If generating copy: show multiple variants when the brief asks for them. - Local library must catch crude/explicit titles (not only gaming tropes). DEMO INPUT → OUTPUT (from live scan) - Field Title To Check: "Girls Only Restricted Tournament" - Primary button name: Check title - Example result lines: RESULT 1. MEDIUM | Why: "Restricted tournament" style titles read as social gatekeeping. Keeps CTR if reframed as private-lobby / invite-bracket challenge. RESULT 2. MEDIUM | Why: Gender-gate framing can look exclusionary in feeds and may attract comment drama / advertiser caution even when the video is wholesome. RESULT 3. HIGH | Why: "Illegal / forbidden / they banned it" framing looks like policy evasion or shock bait. OUTPUT - Runnable standalone Python app - requirements.txt + run bat + optional EXE build script - In-app how-to line - Example of typical input → output (in README or comments, not fake UI samples)