Tt Content Planner

Community

sergebulaev

tt-content-planner

Build a weekly TikTok posting plan from a niche, audience, and content pillars. Produces per-day picks (hook formula, angle, sound, video length, goal, posting time), a hook-batching schedule so you film several openers in one session, a sound shortlist with the trend window, and a completion-rate goal check. Use for a repeatable posting rhythm instead of ad-hoc videos. Not for scripting one hook (use tt-hook-scripter) or one caption (use tt-caption-writer).

Overview

Publisher	sergebulaev
Repository	`tiktok-skills`
Skill name	`tt-content-planner`
Stars	101
Forks	22
Bundled files	2
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by sergebulaev on GitHub. Read the source before you install it.

Installation

Install the Tt Content Planner AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/sergebulaev/tiktok-skills/tree/main/skills/tt-content-planner
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/sergebulaev/tiktok-skills.git /tmp/tiktok-skills
mkdir -p .claude/skills
cp -r /tmp/tiktok-skills/skills/tt-content-planner .claude/skills/tt-content-planner

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tt Content Planner in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Tt Content Planner on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Tt Content Planner is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

TikTok Content Planner

Produce a weekly TikTok plan built around a pillar discipline, a completion-rate target, and the batching workflow that makes consistent posting survivable. TikTok rewards frequency and a clear niche, so the plan locks in a rhythm, shortlists sounds while they are still early, and batches hooks so filming does not eat the whole week.

When to use

User asks "plan my week on TikTok" or "what should I post this week"
User wants to escape ad-hoc posting and build a rhythm
User wants to batch-film several videos in one session
Before a launch week (the plan aligns a product pillar)

Input

Niche (required): e.g. "backend engineering tips for junior devs"
Audience description: e.g. "self-taught devs, bootcamp grads, early-career"
Pillar mix (optional): defaults to 40% Teach / 30% Story / 20% Trend / 10% Promotion
Posting cadence (optional): defaults to 1 video/day, 5-7 days
Completion-rate target (optional): defaults to "beat your trailing 30-day average"
Voice samples (optional): past scripts for voice calibration

Output

A markdown plan with:

7-day calendar

Day	Pillar	Formula	1-line angle	Sound	Length	Goal	Time
Mon	Teach	T9 Tutorial Cold Start	"the git command that saved my job"	original VO	22s	saves	8:00 AM
Tue	Story	T8 Story In Medias Res	"the 11pm prod outage"	trending (early)	34s	completion	7:30 PM
Wed	Teach	T3 Number Reveal	"97% of bugs are in 3 files"	original VO	15s	saves	12:00 PM
Thu	Trend	T10 Trend-Ride	"{trend} but for backend devs"	trending sound	12s	shares	7:00 PM
Fri	Story	T5 Relatable Call-Out	"pov: the standup that should've been a slack"	trending	18s	shares	8:00 AM
Sat	Teach	T7 Listicle Promise	"5 vs code settings i never turn off"	original VO	28s	saves	11:00 AM
Sun	Promotion	T1 Cold-Open Result	"what i built that got me hired"	original VO	30s	completion	6:00 PM

(The skill fills real angles from the niche. Weekends skew to story and relatable.)

Hook-batching schedule

Filming one video at a time burns out creators. The plan groups the week's hooks into one or two batch sessions:

Batch the hooks first. Film all the 1-3 second openers in one sitting (same lighting, same outfit if you want them undated). Strong hooks are the scarce resource; batch them while you are warm.
Group by setup. Videos that share a location, prop, or framing film together. The plan tags each day with its setup so you can cluster them.
Leave trend slots flexible. Trend rides (T10) are filmed close to posting because the sound window moves. The plan marks them "film day-of".

Sound-selection shortlist

For the week:

2 to 3 trending sounds to watch, with a note on where each sits in the trend lifecycle (emerging / peaking / saturated). Ride only the early ones.
Original audio for the evergreen Teach posts (builds a niche sound asset).
A reminder: catch a sound in its first 1-3 days of climbing or skip it.

Completion-rate goal check

Every video has one idea and a length that fully delivers it (no padding)
Every hook puts a result, number, or tension in frame one
At least 3 of 7 are designed for saves (the underrated lever)
At least 1 designed for shares (a niche-specific relatable or trend ride)
No two days use the same formula back to back
Trend rides are 1-2 of the week, not the whole plan
Each video has a loop-close so a rewatch feels natural

Goal mix (balance the week)

Every formula earns a primary signal. A week that is all saves-bait or all trend rides reads as engineered. Spread the goals:

Goal	Formulas	Weekly target
Completion	T1, T2, T8	every video (the floor)
Saves	T3, T7, T9	at least 3 (saves are the underrated lever)
Comments	T4, T6	at least 1
Shares	T5, T10	at least 1
Follows	any framed as a series	at least 1 series hook

Rules

1 video/day is a sustainable floor; 1-3 is fine on TikTok. It rewards frequency without the cannibalization penalty other platforms impose. Quality still gates: do not pad to hit a count.
Completion rate is the goal, not views. Plan the shortest length that fully delivers each idea.
Batch hooks, film bodies around them. The hook is the scarce resource.
Trend rides are seasoning, not the meal. 1-2 a week. Over-relying on trends means you never build a niche of your own.
One formula per day, varied across the week. Do not stack three T7 lists.
Promotion pillar max 1-2 posts/week. Overuse kills trust.

Formula -> pillar mapping

Pillar	Preferred formulas
Teach	T9 Tutorial Cold Start, T3 Number Reveal, T7 Listicle Promise
Story	T8 Story In Medias Res, T5 Relatable Call-Out
Trend	T10 Trend-Ride, T2 Pattern Interrupt
Promotion	T1 Cold-Open Result (a result that implies the product)

Steps

Gather inputs. Ask for niche, audience, pillar preferences if not provided.
Validate the pillar mix sums to 100%; warn if any pillar is over 60%.
For each day, pick: pillar, formula (do not over-repeat), angle, sound (trending-early or original), length, posting time (audience timezone), goal.
Build the hook-batching schedule by grouping shared setups.
Build the sound shortlist with lifecycle notes (hand specifics to tt-trend-mapper).
Run the completion-rate goal check and the goal-mix check; flag gaps.
Return as markdown, plus optional JSON for import.

Example

See references/example-week.md for a filled-in 7-day plan.

Files

SKILL.md - this file
references/example-week.md - worked 7-day plan with batching
references/pillars-framework.md - the TikTok pillar discipline explained

Related skills

tt-hook-scripter - script each day's hook from the plan
tt-caption-writer - caption and schedule each video
tt-trend-mapper - vet the week's trend slots before filming
tt-humanizer - scrub each script before the batch shoot

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Tt Content Planner AI skill do?

Why use Tt Content Planner on TypingMind?

Because you install it once and use it with any model. Tt Content Planner is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Tt Content Planner in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sergebulaev/tiktok-skills/tree/main/skills/tt-content-planner. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Tt Content Planner?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Tt Content Planner?

As many as you like. As long as a model supports skills, you can use Tt Content Planner with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tt Content Planner AI skill free?

Yes. It is published on GitHub by sergebulaev under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Clawhub

openclaw

OrganizationPopular

Search ClawHub for skills when a requested capability is not already available; install, verify, update, uninstall, publish, or sync skills.

Diagnosing Superpowers

obra

CommunityPopular

Use 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…

Brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Executing Plans

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

TikTok Content Planner

When to use

Input

Output

7-day calendar

Hook-batching schedule

Sound-selection shortlist

Completion-rate goal check

Goal mix (balance the week)

Rules

Formula -> pillar mapping

Steps

Example

Files

Related skills

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now