Skip to content

sergebulaev/youtube-skills / .codex-marketplace/youtube-skills/skills/yt-content-planner

yt-content-planner

Verified

Build a weekly YouTube upload plan: long-form vs YouTube Shorts mix, posting cadence, per-slot title and thumbnail pairing, hook angle, community-tab posts between uploads, and a goal balance across CTR, retention, and subscribes. Maps Shorts as top-of-funnel that points at long-form, and long-form as the loyalty and watch-time engine. Use to plan a week or a content calendar instead of shipping ad hoc. Not for writing a single title, description, or hook (use the dedicated yt skills).

FileKindSize
SKILL.mdskill md5.0 KB
references/example-week.mdmarkdown3.0 KB
references/pillars-framework.mdmarkdown3.0 KB

references/example-week.md

View on GitHub
# Example Week

A fully worked weekly grid for a growing solo build-in-public channel (around
3k subscribers, audience in US Eastern). The creator can make 1 long-form and
3 Shorts a week. This is an illustration, not a prescription.

## Inputs

- **Theme:** building an AI side project in public
- **Audience:** indie devs and early founders, US Eastern
- **Pillars:** Build logs, Tool teardowns, Mistakes and lessons, Quick tips
- **Capacity:** 1 long-form + 3 Shorts per week
- **Stage:** growing (1k to 50k)

## The grid

| Day | Slot | Format | Pillar | Title angle (formula) | Thumbnail angle | Hook (formula) | Goal | Window (ET) |
|---|---|---|---|---|---|---|---|---|
| Mon | Short | Quick tips | one setting that 2x'd a metric (Y4 Mistake) | the setting toggled, big arrow | 3-sec frame-one (Y10) | CTR / reach | 12:00 PM |
| Tue | Long-form | Build logs | "How I shipped X in 5 days" (Y3 How-I) | exhausted face + the live product | cold-open payoff (Y8) | retention | 4:00 PM |
| Wed | Community | - | poll: which feature next | - | - | engagement | 1:00 PM |
| Thu | Short | Tool teardowns | "this free tool beats the $200 one" (Y6 Versus) | two logos, one crossed out | 3-sec frame-one (Y10) | CTR / reach | 12:00 PM |
| Fri | Short | Mistakes | "I almost shipped this bug" (Y1 Curiosity) | the error on screen + face | 3-sec frame-one (Y10) | CTR / reach | 5:00 PM |
| Sat | Community | - | question: worst deploy story | - | - | engagement | 10:00 AM |
| Sun | (rest / batch) | - | - | - | - | - | - | - |

## Why this balances

- **Format mix:** 1 long-form (the watch-time engine) + 3 Shorts (top of funnel),
  matched to the creator's real capacity.
- **Through-line:** all three Shorts excerpt or tease the build-log long-form, so
  the reach they earn points at the library.
- **Goal spread:** the long-form is retention-first; the Shorts are CTR-first;
  the community posts drive engagement that seeds the next video. Not all one
  note.
- **Pillar variety:** four different pillars across the week, so the channel does
  not feel like one repeated topic.
- **Timing:** the long-form publishes Tuesday afternoon ET, a few hours before
  the indie-dev evening viewing peak, so the browse feed has data when it tests.

## How each slot gets built

The planner stops here. Each slot is then handed to the dedicated skill:

1. `yt-title-optimizer` writes 3 to 5 title variants for the slot's angle.
2. `yt-thumbnail-brief` writes 2 to 3 thumbnail concepts for the slot.
3. `yt-hook-scripter` scripts the first 30 seconds (or 3 for a Short).
4. `yt-description-writer` writes the description, chapters, and links.
5. `yt-community-post-writer` writes the Wednesday poll and the Saturday question.

## Holding the cadence

- Batch on Sunday: record the Shorts in one session, plan the long-form.
- If a week slips, drop a Short, never the long-form. The long-form is the engine.
- Re-evaluate the mix every 4 weeks against long-form watch-time and returning
  viewers, measured separately from Shorts views.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall