build-in-public-youtube

--- name: build-in-public-youtube description: Use when Dhruv shares a long-form (1-3 hour) team meeting recording or transcript and wants to publish it on YouTube as build-in-public content. Produces title, description, thumbnail prompt, tags, chapters, and pinned comment. Works from RTF, TXT, MD transcripts or audio files (with transcribe.py). ---

# Build-in-Public YouTube — Long-Form Team Meeting → YouTube Episode

## What this skill does

Turns Dhruv's long Saturday/Sunday team sync recordings (Afeefa, Shailendra, Vishal, Navpreet + Dhruv) into a complete YouTube upload pack:

- **Title** (clickable, honest, build-in-public framed) - **Description** (chapter timestamps, what's covered, links, team credits, hashtags) - **Thumbnail prompt** (Gemini-paste-ready, brand palette: deep dark + neon cyan #18D1E0 + metallic grey) - **Tags** (25-30 YouTube tags) - **Chapters** (with timestamps if known, otherwise structural placeholders) - **Pinned comment** (CTA + community + product links)

This is the canonical format for the AIwithDhruv "Build-in-Public Diaries" series.

---

## When to invoke

Trigger phrases from Dhruv: - "Here's the Sunday team recording, write a YouTube post" - "Make a YouTube title for this transcript" - "We did 2 hours yesterday, can we upload it" - "Build-in-public episode from this" - Or just shares a `.rtf` / `.txt` / `.md` transcript inside `Library/Mobile Documents/com~apple~TextEdit/Documents/` or `inbox/recordings/`

---

## Series identity (locked)

| Field | Value | |------|------| | Channel | AIwithDhruv (main) | | Series name | **Build-in-Public Diaries** | | Episode prefix | `Build-in-Public Diaries — Ep N` | | Cadence | 1-2 long-form episodes per week (weekend syncs + Wednesday mid-week sync if any) | | Duration | 1-3 hours unedited (NO heavy editing — raw is the brand) | | Voice | First-person from Dhruv ("we built", "I shipped", "we lost", never "the team did") | | Brand palette | Deep dark `#0A0E1A` + neon cyan `#18D1E0` + metallic grey. NO orange / red / teal-mint. (See `brand_palette.md`) | | Format | 16:9, 1080p min, thumbnails 1280x720 |

---

## Inputs you need before generating

If any of these are missing, ASK Dhruv before drafting:

1. **Episode number** (default to next sequential: check the channel or ask) 2. **Recording date** (e.g., "Apr 26, 2026") — used in title + filename 3. **Recording length** in HH:MM (estimate from word count if no audio: ~150 words/min) 4. **Path to transcript** (`.rtf` / `.txt` / `.md`) 5. **Public revenue claim allowed?** (default: NO. Don't drop ₹/$ numbers without explicit approval) 6. **Specific milestone to lead with?** (e.g., "Vishal joined", "AutoBOQ shipped", "first paid client")

If you have the transcript path but no metadata, run `wc -w <file>` to estimate length and propose Episode N + date + suggested headline angle. Then wait for confirmation.

---

## Step-by-step process

### Step 1 — Read the transcript fully

Convert RTF if needed: `textutil -convert txt -stdout "input.rtf" > /tmp/transcript.txt`

Read end-to-end. Don't skim. Look for: - **Strategic decisions** (pivots, hires, product calls) - **Real numbers** (only use them if Dhruv approved public-revenue mode) - **Tools/stack mentioned** (Claude, Antigravity IDE, Blotato, Plivo, Flow, Vercel, etc.) - **Honest losses / blockers** (these make the best build-in-public hooks) - **Personal moments** (team onboarding, philosophy, framework calls)

### Step 2 — Extract the 5 anchor points

Every episode pack is built on these 5 anchor points pulled from the transcript:

1. **The headline decision** — the one thing this meeting will be remembered for 2. **The week's score** — wins shipped, losses absorbed 3. **The team motion** — who did what, who joined, who graduated 4. **The technical reveal** — one stack/tool/pattern that was tested or chosen 5. **The next-7-days commit** — public commitment so viewers can hold us accountable

Write these 5 lines first. Title and description flow from them.

### Step 3 — Generate the upload pack

Apply the templates in **Reference Templates** below. Always show the full pack to Dhruv for approval before suggesting upload. Never auto-publish (see `feedback_never_auto_publish.md`).

### Step 4 — Save the pack

Write the final pack to `/tmp/<recording-filename>_episode_pack.md` so Dhruv can copy-paste into YouTube directly. Print location at end.

---

## Reference Templates

### Title formulas (pick one, A/B is fine)

**Formula 0 — Setup / Foundation video (use ONCE, for the genesis "operating manual" video):** ``` {$0 MRR / honest current state}, {$tool spend}, {N products}: How {brand} Actually Works ({Setup / Operating Manual / Day 0}) ``` Example: `$0 MRR, $400/mo Tools, 4 Products: How AIwithDhruv Actually Works (Build-in-Public Setup)` Use this only for the first/foundation video that explains how the team and stack are wired. NOT for ongoing weekly episodes.

**Formula A — Decision lead (best for big pivots/hires, ongoing episodes):** ``` Build-in-Public Diaries — Ep {N}: {THE ONE DECISION} | Day {X} of the 45-Day Sprint ``` Example: `Build-in-Public Diaries — Ep 3: We Hired 4 People in One Weekend | Day 12 of the 45-Day Sprint`

**Formula B — Stakes lead (best for weeks with money/risk on the line):** ``` {X Hours} of Real Strategy: How We're Trying to Hit ₹{Y} in {Z} Days (Build-in-Public Diaries Ep {N}) ``` Use only if revenue mode = approved.

**Formula C — Team lead (best when a meeting introduces team):** ``` Meet the Team Building 4 AI Products in Public — Sunday Sync Ep {N} ```

**Formula D — Stack lead (best when one tool/tech is the star):** ``` We Replaced {Old Tool} With {New Tool} — Live Decision in Sunday Sync (Build-in-Public Ep {N}) ```

**Formula E — Honesty hook (use anytime real numbers are public):** ``` {$honest current state}: Here's the {N-Day} Plan to Change That ({Build-in-Public Ep N}) ``` Example: `We're at $0 MRR. Here's the 45-Day Plan to Land Our First Client (Build-in-Public Ep 4)`

**Title rules:** - 60-70 chars max for full visibility - No emoji in title (looks unserious for B2B audience) - Number → real number (no clickbait inflation) - Episode number always present - "Build-in-Public Diaries Ep N" recognized somewhere in the title

### Description template

``` {ONE-LINE HOOK — what this episode is actually about, 200 chars max}

This is the unfiltered {duration} Sunday sync from {date}. No edits. Real strategy, real arguments, real pivots.

━━━━━━━━━━━━━━━━━━━━ 👥 WHO'S IN THE ROOM ━━━━━━━━━━━━━━━━━━━━ Dhruv Tomar — AI Architect & Founder, AIwithDhruv {LIST EACH TEAM MEMBER PRESENT WITH 1-LINE ROLE}

━━━━━━━━━━━━━━━━━━━━ 📋 WHAT WE COVER ━━━━━━━━━━━━━━━━━━━━ {5 ANCHOR POINTS as bullet list — 1 line each}

━━━━━━━━━━━━━━━━━━━━ ⏱️ CHAPTERS ━━━━━━━━━━━━━━━━━━━━ {TIMESTAMPS — see Chapter Generation below}

━━━━━━━━━━━━━━━━━━━━ 🛠️ TOOLS & STACK MENTIONED ━━━━━━━━━━━━━━━━━━━━ {LIST OF TOOLS WITH PURPOSE — 1 line each, no affiliate links unless explicitly approved}

━━━━━━━━━━━━━━━━━━━━ 🚀 PRODUCTS WE'RE BUILDING ━━━━━━━━━━━━━━━━━━━━ QuotaHit — AI Inbound Revenue OS (CRM + AI calling) | quotahit.com (when live) AutoBOQ — AI construction estimation for SMB contractors | github.com/aiagentwithdhruv/autoboq IndianWhisper — Hindi/Hinglish/Indian-English voice-to-text | indianwhisper.com Angelina-OS — Personal AI OS, 30+ tools

━━━━━━━━━━━━━━━━━━━━ 📌 LINKS ━━━━━━━━━━━━━━━━━━━━ 🌐 Site: https://aiwithdhruv.com 💼 LinkedIn: https://www.linkedin.com/in/aiwithdhruv/ 🐦 X: https://x.com/aiwithdhruv 📸 Instagram: https://instagram.com/aiwithdhruv 🐙 GitHub: https://github.com/aiagentwithdhruv {PRODUCT-SPECIFIC LINKS RELEVANT TO THIS EPISODE}

━━━━━━━━━━━━━━━━━━━━ 👋 ABOUT ━━━━━━━━━━━━━━━━━━━━ We're building 4 AI products in public — QuotaHit, AutoBOQ, IndianWhisper, Angelina-OS — using Claude Code as a workflow engine. This channel is the unfiltered process. If you're building, hiring, or learning AI for real production work — subscribe.

#BuildInPublic #AIwithDhruv #ClaudeCode #AIAgents #SaaS #Founder #Indian{Optional product hashtags — pick 2-3 max}

{TEAM CREDIT BLOCK — only when team appears on camera or is named. ALWAYS check team_linkedin_profiles.md NO-PUBLIC-CREDIT list before adding anyone:} Team: - Afeefa Albeena Sheikh — AI Architect | https://www.linkedin.com/in/afeefa-albeena-sheikh-298857192/ - Shailendra Gour — Developer | https://www.linkedin.com/in/shailendra-gour-01922b22b/ - Navpreet Kaur — AI GrowthLead | https://www.linkedin.com/in/navpreet-kaur-b22521305/ ```

**CRITICAL: NO-PUBLIC-CREDIT enforcement.** Some team members have explicitly opted out of public promotion (currently: Vishal). NEVER name them in descriptions, NEVER link them, NEVER include them in credit blocks — even if they appear on camera or are mentioned by other speakers in the recording. Refer to "the team" or "an internal teammate" if needed. The full NO-PUBLIC-CREDIT list lives in `team_linkedin_profiles.md`.

**Description rules:** - First 150 chars are the hook (these show in search snippet) - Always include chapters — long-form needs them for completion rate - Always credit team using canonical LinkedIn URLs from `team_linkedin_profiles.md` - Hashtag count: 6-9 max (YouTube cap = 15, but quality > quantity) - Never mention source creators (per `feedback_content_voice.md`) - Don't drop revenue numbers unless Dhruv explicitly opts in for this episode

### Chapter generation

If timestamps aren't provided, build chapters from the transcript's structural sections. For long-form team meetings, default outline:

``` 00:00 Cold open / context {XX:XX} Strategy block — the week's plan {XX:XX} {PRODUCT 1} update {XX:XX} {PRODUCT 2} update {XX:XX} {PRODUCT 3} update {XX:XX} Team motion (hires, role changes, dispatch) {XX:XX} Tools / stack discussion {XX:XX} Content + social media plan {XX:XX} Open questions and pending decisions {XX:XX} Action items + commits for next 7 days {XX:XX} Wrap ```

Mark unknown times with `[XX:XX]` so Dhruv can fill in from YouTube Studio later.

**Min 8 chapters, max 14.** YouTube algorithm rewards 8+ chapters on long-form.

### Thumbnail prompt formula (Gemini-paste-ready)

Always 16:9, 1280×720 minimum. Brand palette: deep dark + neon cyan + metallic grey ONLY.

Template (paste this into Google Gemini, free):

``` Create a 16:9 cinematic YouTube thumbnail (1280x720, sharp print-ready).

SCENE: {ONE LINE — the scene that anchors the episode. Examples: - "A founder at a desk surrounded by 4 floating product UIs (CRM, voice app, design tool, dashboard) with team members visible behind glass walls" - "A whiteboard packed with sticky notes labelled QuotaHit / AutoBOQ / IndianWhisper / Angelina, with a calendar showing 45 DAYS in glowing cyan" - "A war-room table with 5 laptops open, neon city skyline behind, stack of business cards labelled with the 4 product names"}

STYLE: - Cinematic photography, shallow depth of field, dramatic lighting - Color palette STRICTLY: deep dark navy/black background (#0A0E1A) + neon cyan accents (#18D1E0) + metallic grey/silver highlights - NO orange, NO red, NO teal-mint — these are off-brand - Slight glow / volumetric light from cyan elements - Photorealistic, NOT illustrated, NOT cartoon

TYPOGRAPHY OVERLAY: - Top-left or bottom-right: bold sans-serif "{HEADLINE TEXT — 3-6 words MAX, ALL CAPS}" in cyan or white - Tiny brand badge bottom-left: "AIwithDhruv • Build-in-Public • Ep {N}" - TEXT MUST BE SHARP, READABLE, NO BLUR, NO OVERLAP WITH FACES

COMPOSITION: - Subject(s) in left third, headline text in right two-thirds (or flip) - Generous safe margin (5% around all edges) - Mobile preview rule: must read at 200px wide

NEGATIVE PROMPT: no orange, no red, no warm yellow, no teal mint, no cluttered backgrounds, no stock-photo people, no clipart, no low resolution, no text overlap, no face cutoff, no distorted text ```

**Thumbnail rules:** - Always 16:9 - Always brand palette (no exceptions) - Headline text always 3-6 words max -