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 a campaign needs a consistent, approved way to label links so the team can distinguish sources and make later reporting possible. Trigger phrases include "plan our UTMs", "name campaign links", "make tracking links", "how should we tag creator links?", and "set up
$ npx -y skills add Ootto-AI/claude-content-skills --skill utm-campaign-plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/utm-campaign-planContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when a campaign needs a consistent, approved way to label links so the team can distinguish sources and make later reporting possible. Trigger phrases include "plan our UTMs", "name campaign links", "make tracking links", "how should we tag creator links?", and "set up
name: utm-campaign-plan description: Use when a campaign needs a consistent, approved way to label links so the team can distinguish sources and make later reporting possible. Trigger phrases include "plan our UTMs", "name campaign links", "make tracking links", "how should we tag creator links?", and "set up attribution for this launch". Do not use this to claim analytics access, create tracking without consent or policy review, or decide campaign strategy; use campaign-brief for the campaign source, paid-social-brief for media requirements, and social-analytics-report to interpret available data.
Create a small, consistent link taxonomy that answers real reporting questions without turning every URL into ungoverned tracking noise.
Ask what decision the data should support, which destinations are approved, which channels and partners are involved, what analytics system consumes the links, and what naming convention already exists. If no reporting owner or system is known, document that limitation before issuing links.
Set clear allowed values for source, medium, campaign, content, and term only when each has a decision use. Use human-readable, stable naming. Separate owned social, paid social, creators, partners, and experiments so later reporting does not blend unlike traffic.
For every link, provide the destination, intended placement, UTM values, owner, start and end context, and approval status. Include examples and invalid examples. Reserve a process for changes so a creator or operator does not silently alter the taxonomy.
Check that URLs resolve to the approved destination, parameters are encoded correctly, and the same source is not represented by several names. After the campaign, compare link usage against the register and record any taxonomy correction for the next brief.
| Failure | Do this instead | | --- | --- | | Every team member invents names | Publish one controlled vocabulary and a shared register. | | Parameters contain personal or sensitive data | Use a non-identifying campaign label and keep sensitive data out of URLs. | | A short link hides an unverified destination | Validate the final redirect and approved landing page before sharing. | | Reports blend creator and paid traffic | Assign separate medium/source values and preserve them in the register. |
Use campaign-brief to establish the campaign and paid-social-brief or influencer-partnerships to identify placements. Use this skill before cross-platform-distribution goes live. Use social-analytics-report and launch-retrospective to interpret the resulting labelled traffic honestly.
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…