tiktok-learning-phase-tracker

tiktok-learning-phase-tracker is a skill for Claude Code from Ad-Superpowers/ad-superpowers-plugin. It costs 115 tokens per session (5,280 once invoked), scanned A, original, MIT.

A guide for managing the learning phase of TikTok ad groups. The learning phase is the period when TikTok gathers data to decide which users, bids, placements, and creatives are most likely to produce conversions.

In plain words
What is it for?
Use it to decide when to edit campaigns, estimate the budget needed for learning, and diagnose ad groups that are stuck learning or not delivering.
Why use it?
It helps explain statuses such as Learning and Learning Limited and reduces the risk of changing campaigns before enough data is available. It also relates edits and budget to the platform's conversion requirements.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ad-superpowers plugin — 120 skills, 35 commands, 5 agents, 1 MCP server shipped together

Good fit Use it to decide when to edit campaigns, estimate the budget needed for learning, and diagnose ad groups that are stuck learning or not delivering.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ad-superpowers/ad-superpowers-plugin/tiktok-learning-phase-tracker
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Ad-Superpowers/ad-superpowers-plugin --skill tiktok-learning-phase-tracker
Clone the repo
git clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-plugin

Made for: Claude Code.

Or install ad-superpowers, the plugin that ships this one along with the rest of its 120 skills, 35 commands, 5 agents, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tiktok-learning-phase-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/tiktok-learning-phase-tracker/github.svg)](https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/tiktok-learning-phase-tracker)
Your own site
<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/tiktok-learning-phase-tracker"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/tiktok-learning-phase-tracker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tiktok-learning-phase-tracker

Your own site · 80×15
<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/tiktok-learning-phase-tracker"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/tiktok-learning-phase-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,280 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00115 $0.05280
Opus 5.5 $0.00046 $0.02112
Sonnet 5.5 $0.00023 $0.01056
Haiku 4.5 $0.00012 $0.00528

Measured 1mo ago against content hash eddd5fa05a71, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tiktok-learning-phase-tracker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/tiktok-learning-phase-tracker/SKILL.md · 740 lines

How it starts

The opening of the file, as written. The whole thing — 740 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TikTok Learning Phase Tracker

Analyzer for TikTok Ads learning phase management. Predicts edit impact and advises on optimal timing for changes.

Learning Phase Basics

What Is TikTok's Learning Phase?

TIKTOK LEARNING PHASE EXPLAINED
================================

Period during which TikTok's algorithm collects data about:
+-- Which users are most relevant
+-- Optimal bid prices per auction
+-- Best times and placements
+-- Creative performance patterns

STATUS INDICATORS:
+-- "Learning": Algorithm is collecting data
+-- "Active": Exited, stable optimization
+-- "Learning Limited": Not enough conversions
+-- "Not Delivering": Budget/bid issues

Exit Criteria

TIKTOK EXIT REQUIREMENTS
========================

MINIMUM REQUIREMENTS:
+-- 50 conversion events per week per ad group
+-- 72-hour initial learning window
+-- Sufficient budget for target CPA
+-- Stable creative performance

FORMULA FOR MINIMUM BUDGET:
Daily Budget = (Target CPA x 50) / 7

EXAMPLE:
+-- Target CPA: EUR20
+-- Minimum weekly: EUR20 x 50 = EUR1,000
+-- Minimum daily: EUR1,000 / 7 = EUR143/day
+-- With buffer (1.5x): EUR215/day recommended

72-HOUR RULE:
+-- First 72 hours: Make NO changes
+-- Algorithm learns fundamental patterns
+-- Edits during this period = reset learning
+-- Avoid even small changes

Learning Phase Statuses

STATUS INTERPRETATION
=====================

STATUS: Learning (Normal)
+-- Duration: 0-7 days
+-- Meaning: Algorithm is actively learning
+-- Action: WAIT, do not change
+-- Expectation: CPA fluctuates 30-50%
+-- Exit: After 50+ conversions/week

STATUS: Learning Limited
+-- Duration: >7 days without exit
+-- Causes:
|   +-- Budget too low
|   +-- Audience too small (<100k)
|   +-- Bid too low
|   +-- Event too rare
+-- Action: Intervene (see Exit Strategies)
+-- Urgency: High

STATUS: Active
+-- Meaning: Learning complete
+-- CPA: Stabilized
+-- Action: Optimize, scale
+-- Edits: Careful, can re-trigger

STATUS: Not Delivering
+-- Causes:
|   +-- Budget exhausted
|   +-- Bid too low for auction
|   +-- Creative rejected
|   +-- Audience exhausted
+-- Action: Diagnose and fix
+-- Urgency: Critical

Read the full file on GitHub · 740 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 740 lines · 115 tokens per session scan A eddd5fa05a71

Subscribe to this mod's changes

tiktok-learning-phase-tracker is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 29d ago), licensed MIT. It adds 115 tokens to every session and 5,280 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.

Related

Other skills, from other repositories

analytics

Growth analytics authority — GA4 event tracking, conversion funnels, attribution models, cohort analysis, A/B testing, Supabase analytics queries, and revenue reporting patterns.

LuuOW/meridian-mcp · 33 tokens

creative-generate

A workflow for creating advertising images and banners from a strategy brief. It separates the main visual artwork from the accurately typeset text and produces variants for display or social formats.

logly/mureo · 131 tokens

cro-optimizer

CRO specialist that pulls live analytics data via the Humblytics MCP, analyzes conversion funnels, identifies drop-off points, and generates prioritized A/B test hypotheses. Use when analyzing conversion rates, diagnosing funnel leaks, optimizing signup flows, or creating test roadmaps. Triggers: CRO, conversion rate…

Humblytics/humblytics-marketing-skills · 76 tokens

learn

Save a marketing diagnosis insight to the pro-diagnosis knowledge base so it is applied in future operations across all platforms. Use when the user runs /learn, explicitly teaches the agent a marketing insight, corrects the agent's analysis, or asks to remember/record an operational learning for next time. Also use…

logly/mureo · 98 tokens

lead-form-create

Create a Meta Instant Form (Lead Ad form) through a one-question-at-a-time interview. Use when the user asks to create a lead form, Instant Form, CV form, or similar. The agent collects required parameters via a guided dialogue, confirms, then calls metaadsleadformscreate. Also use when the user asks in Japanese…

logly/mureo · 93 tokens

ai-hive-simulate-dn-samuel

A research and content-planning workflow that studies DN-Samuel's public material and turns its general methods into original work using your own facts and experience. It can also organise authorised documents into a source-linked reference library.

wubin1836/ai-hive-agent-skills · 334 tokens