ab-hook-tester
Generates two genuinely distinct hook variants for the same reel so you can post-test which opening actually wins. Use when the user says "give me two hooks to…
Use when an approved social campaign needs a media-ready brief for paid distribution, creative testing, and measurement. Trigger phrases include "brief paid social", "plan this ad test", "turn this campaign into paid", "what should we test in ads?", and "make a Meta or LinkedIn
$ npx -y skills add Ootto-AI/claude-content-skills --skill paid-social-brief --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/paid-social-briefContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when an approved social campaign needs a media-ready brief for paid distribution, creative testing, and measurement. Trigger phrases include "brief paid social", "plan this ad test", "turn this campaign into paid", "what should we test in ads?", and "make a Meta or LinkedIn
name: paid-social-brief description: Use when an approved social campaign needs a media-ready brief for paid distribution, creative testing, and measurement. Trigger phrases include "brief paid social", "plan this ad test", "turn this campaign into paid", "what should we test in ads?", and "make a Meta or LinkedIn ad brief". Do not use this to claim ad-account access, launch spend, bypass platform policy, or invent targeting capabilities; use campaign-brief for the source strategy, utm-campaign-plan for tracking conventions, and social-analytics-report for results interpretation.
Translate an approved campaign into testable paid-social decisions without pretending media execution or platform access exists.
Ask for the campaign objective, offer, claim boundary, landing destination, proof, audience evidence, budget range if supplied, policy constraints, and the owner who can actually configure the platform. If the offer or landing page is unapproved, do not write ads around it.
State the hypothesis, audience context, creative angle, desired action, measurement event, and what would count as useful learning. Separate audience hypotheses from targeting settings because platform availability and policy can change. Keep the number of simultaneous variables small enough to interpret.
List the approved message variants, proof assets, disclosures, format needs, destination expectation, exclusions, and prohibited claims. Tie each creative to a hypothesis. Note where a native platform review or legal approval is required rather than claiming it is complete.
Provide the budget and pacing decisions only when supplied by an authorised owner; otherwise mark them open. Define launch checks, reporting window, stop or revise conditions, and the exact data needed for a review. Ensure tracked links follow the agreed UTM plan.
| Failure | Do this instead | | --- | --- | | A media brief is only ad copy | Define the hypothesis, audience context, measurement, and decision threshold. | | Too many variables change at once | Limit the first test to the few variables needed to answer one question. | | Creative promises more than the destination delivers | Align every claim with the approved landing experience and proof. | | Results cannot be attributed | Create the UTM and measurement plan before launch. |
Use campaign-brief and positioning-audit before this skill. Use utm-campaign-plan to make link naming consistent and cross-platform-distribution to distinguish paid from owned work. Use social-analytics-report for operating decisions and launch-retrospective for the full review.
Free, copy-paste Claude skills that run your content growth factory — turn ideas (and your Obsidian memory) into scroll-stopping Instagram reels: hooks, scripts, repurposing, captions, and a 2-week posting calendar.
Repo: Ootto-AI/claude-content-skills
Generates two genuinely distinct hook variants for the same reel so you can post-test which opening actually wins. Use when the user says "give me two hooks to…
MUST USE when user wants to 调研/research/搜索/search/查/找/look up anything on the internet — e.g. 全网调研 X / 帮我调研一下 X / 查一下 X / 搜搜 X / 看看大家怎么评价 X / X 上有什么讨论 /…
Give Claude a permanent, searchable long-term memory using an Obsidian vault as the store. At the end of a session, summarize what mattered and save it as a…
Reads your reel insights and explains in plain English what to make more of and what to stop — no jargon. Use when the user says "explain my analytics", "what…
Build evidence-led social audience personas from customer interviews, comments, reviews, or CRM notes.
Turns a script into a shoot-ready shot list — every clip, angle and visual you need to film, in order. Use when the user says "what do I need to film", "shot…