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 team needs a deliberate, human-led plan for participating in comments, communities, or audience conversations around an approved topic. Trigger phrases include "plan community engagement", "how should we join this conversation?", "what should we reply to?", "make an
$ npx -y skills add Ootto-AI/claude-content-skills --skill community-engagement-plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/community-engagement-planContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when a team needs a deliberate, human-led plan for participating in comments, communities, or audience conversations around an approved topic. Trigger phrases include "plan community engagement", "how should we join this conversation?", "what should we reply to?", "make an
name: community-engagement-plan description: Use when a team needs a deliberate, human-led plan for participating in comments, communities, or audience conversations around an approved topic. Trigger phrases include "plan community engagement", "how should we join this conversation?", "what should we reply to?", "make an engagement playbook", and "how do we support this community?". Do not use this to automate unsolicited replies, manipulate conversations, impersonate people, or create comment copy at scale; use comment-responder for a specific approved reply and social-listening to analyse recurring themes.
Set a useful participation standard: where the team can add value, what it can truthfully say, and when it should not speak.
Ask which owned or external community is in scope, its rules, the team's legitimate role, the topic, and any moderator or brand constraints. Read supplied rules before proposing interaction. If the community does not welcome promotion or brand participation, do not design a workaround.
Use real questions, recurring friction, useful resources, corrections, and support needs as evidence. Classify participation as answer, clarification, acknowledgement, escalation, or observation. Give priority to helping people complete a task, not inserting the brand into every thread.
Define approved facts, prohibited claims, tone, disclosure, escalation owners, response windows, and cases that require silence or human review. Route product bugs, safety concerns, account-specific issues, legal questions, and hostile interactions to the appropriate owner rather than improvising publicly.
Set a small cadence to review unanswered questions, recurring themes, and useful contributions. Capture aggregate learning for social-listening. Measure quality through resolved questions, informed feedback, and community trust signals where available, not reply volume alone.
| Failure | Do this instead | | --- | --- | | The plan is "reply to everything" | Define situations where the team can add real value and where it should observe. | | A public reply attempts to solve a private account issue | Acknowledge the issue and route through the approved support path. | | Replies become repetitive promotion | Lead with the user's question, resource, or correction rather than the product. | | Community rules are discovered after posting | Review rules and obtain required permission before engaging. |
Use social-listening to identify recurring questions and comment-responder for a particular reply. Use campaign-brief only when a campaign has a legitimate community role. Feed patterns into audience-personas and positioning-audit; never treat a community plan as a mass-outreach mechanism.
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…