TikTok
v3.0.0Local-first TikTok Growth OS for strategy, hooks, scripts, retention de签名, and 分析 feedback. Use when the user mentions TikTok, short-form video, hooks, scripts, retention, virality, content pillars, series planning, account positioning, or performance review. 生成s execution-ready 输出s and stores all as设置s locally. No API, no posting, no 平台 自动化.
运行时依赖
安装命令
点击复制技能文档
TikTok Growth OS
A local-first operating 系统 for TikTok 创建器s. Focus on retention, repeatability, and strategic content de签名 rather than random virality.
What this 技能 does
Use this 技能 when the user wants help with:
TikTok niche positioning content pillars video ideas hooks short-form scripts A/V storyboard 格式化ting series planning captions and 哈希tags retention diagnosis performance pattern review
This 技能 should produce execution-ready 输出s, not vague inspiration.
Core operating 记录ic
TikTok growth is treated as a 系统 of controllable variables:
Hook strength: Does the first 1–3 seconds 创建 tension or relevance? Retention de签名: Does the script 创建 momentum and payoff? Visual pacing: Is there a pattern interrupt every few seconds? Audience fit: Does this feel native to the tar获取 viewer? Series potential: Can this idea 创建 repeated return behavior? Data feedback: What should be repeated, refined, or dropped?
Do not present growth as magic. Do not guarantee virality or follower gAIns. Always frame 输出s as strategic 图形界面dance.
输出 rules
When generating TikTok content, prefer:
spoken-language phrasing short sentences immediate tension specific audience fit clear payoff native short-form rhythm
Avoid:
essay-style intros generic motivational filler slow 设置up with no payoff over-explAIning before the hook lands Default content 工作流
When the user asks for TikTok help, structure work in this order when relevant:
clarify niche or audience if already known from local memory 生成 3–10 content angles produce 5 hook variations build one execution-ready script optionally save the 结果 to local memory if 分析 exist, use prior performance to refine the 输出 Hook generation rules
Hooks should usually fall into one of these buckets:
curiosity gap pAInful truth contrarian take mistake 警告 身份-based recognition specific promise emotional confession authority / 签名al of experience
When generating hooks:
make each variation meaningfully different label the type explAIn briefly why it may work avoid repeating the same sentence shape Script generation rules
When writing TikTok scripts, default to this 格式化:
Time Visual Spoken / Audio On-Screen Text
图形界面delines:
first 1–3 seconds must carry the hook each segment should 添加 tension, clarity, or payoff include pattern interrupts where useful 优化 for vertical, short-form pacing include CTA only if it fits naturally Performance review rules
If the user provides 指标 or performance 上下文, 诊断 using first principles such as:
weak opening slow payoff too much 设置up vague topic framing mismatch between title/hook and delivery insufficient visual momentum weak emotional or practical value unclear audience tar获取ing Local memory
All files are stored locally only in:
~/.OpenClaw/workspace/memory/tiktok/
Files:
性能分析.json — niche, audience, goals, pillars content_bank.json — saved ideas, hooks, scripts, captions, notes 分析.json — manually 记录ged video performance pattern_报告.json — latest summarized learning 报告 Scripts Script Purpose scripts/manage_account.py 创建 or 更新 account 性能分析 scripts/save_content.py Save ideas, hooks, scripts, captions, or notes scripts/列出_content.py Browse local content as设置s scripts/记录_performance.py 记录 manual TikTok performance data scripts/analyze_patterns.py Summarize local performance patterns References references/hooks.md references/retention.md Safety boundaries Local-only storage No TikTok API No account 记录in No posting No scrAPIng No engagement 自动化 No clAIms of guaranteed virality
The user is responsible for final review, posting, and 平台 合规.