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.
npx agentmods add skills/futurefuzzy/topic-tracker/skill-workbuddynpx skills add FutureFuzzy/topic-tracker --skill skill-workbuddygit clone --depth 1 https://github.com/FutureFuzzy/topic-trackerWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00097 | $0.01873 |
| Opus 5 | $0.00048 | $0.00937 |
| Sonnet 5 | $0.00019 | $0.00375 |
| Haiku 4.5 | $0.00010 | $0.00187 |
Grade A, and why
topic-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 2d 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.
This is a copy
91% identical to bilibili-helper — 236 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
选题追踪 Skill
概述
帮助自媒体创作者基于领域方向和热点时间范围，生成各平台适配的爆款选题建议及标题优化方案。核心是多维评分体系 + 分平台差异化输出。
核心评分体系
爆款指数计算公式
爆款指数 = 热度分×30% + 平台适配分×25% + 竞争度分×20% + 情绪共鸣分×15% + 变现潜力分×10%
各维度定义（0-10分）
| 维度 | 权重 | 说明 | 评分标准 |
|---|---|---|---|
| 热度分 | 30% | 当前搜索/讨论量 | 参考微博热搜、知乎热榜、抖音热点等实时数据 |
| 平台适配分 | 25% | 与目标平台用户偏好契合度 | 根据平台特性打分 |
| 竞争度分 | 20% | 内容饱和度（越低越好） | 低饱和→高分，高竞争→低分 |
| 情绪共鸣分 | 15% | 能引发讨论/共情的能力 | 强共鸣→高分 |
| 变现潜力分 | 10% | 商业价值潜力 | 直接变现/引流价值 |
时间范围对应的数据策略
| 时间范围 | 数据采集策略 |
|---|---|
| 今天 | 微博热搜实时榜、知乎热榜、抖音热点飙升榜、今日头条热榜 |
| 近一周 | 平台热搜聚合 + 行业媒体RSS摘要 |
| 近一月 | 百度指数/微信指数关键词趋势 |
| 近三月/半年 | 爆款内容反查（新榜、蝉妈妈等） |
| 近一年 | 长期趋势分析（Google Trends） |
注：若无实时数据接口，优先使用联网搜索获取近期热点信息。
各平台适配规则
小红书
核心用户画像：18-30岁女性为主，追求实用、颜值、情绪价值
爆款规律：
- 封面吸睛 + 首图文字冲击
- 关键词密度高（利于搜索流量）
- 痛点共鸣 + 解决方案
- 种草属性强
标题特征：
- 数字量化：「3个技巧」「7天见效」「月入XX」
- 情绪词：「必看」「绝了」「救命」「哭死」
- 身份标签：「打工人」「学生党」「新手」
- 悬念钩子：「竟然」「没想到」「揭秘」
B站
核心用户画像：18-35岁，追求知识增量、娱乐性、专业深度
爆款规律：
- 标题悬念感强，吸引点击
- 内容密度大，干货满满
- 知识增量明显
- 系列化内容易爆
标题特征：
- 悬念式：「全网最全XX教程」「XX的正确姿势」
- 挑战式：「挑战30天XX」「我尝试了XX，结果...」
- 盘点式：「TOP10 XX」「XX合集」
- 科普式：「XX原理解析」「一文读懂XX」
公众号
核心用户画像：25-40岁，追求深度内容、观点、干货
爆款规律：
- 大标题情绪张力强
- 深度叙事+独特视角
- 传播钩子设计（引发转发）
- 私域传播为主
标题特征：
- 情绪烈：「刚刚」「重磅」「突发」
- 身份代入：「XX人必看」「XX的都看看」
- 数字冲击：「XX个XX」「XX的秘密」
- 反差式：「不是XX，而是XX」「XX的真相」
抖音
核心用户画像：全年龄段，娱乐/猎奇/情绪共鸣
爆款规律：
- 前3秒必须有钩子
- 冲突感/反转设计
- 完播率优先
- 情绪调动（感动/震惊/好笑）
标题特征：
- 悬念：「最后结局太意外...」「结果你猜怎么着」
- 情绪：「泪目」「破防」「笑喷」
- 数字钩子：「第3个动作最关键」
- 反常识：「XX不要再XX了」「XX原来一直做错了」
输出结构模板
基础结构
## 📌 领域：[用户输入领域] | 时间范围：[用户选择范围]
### 🔥 热点事件摘要
基于联网搜索获取的近期热点事件，列出3-5个核心热点
### 💡 选题池（按爆款指数排序）
---
#### 选题[N]：[选题标题]
- **爆款指数**：X.X/10
- **维度评分**：热度⭐⭐⭐⭐⭐ | 竞争度：中 | 情绪共鸣：高
- **适合平台**：[平台1]、[平台2]
- **核心角度**：[切入角度描述]
**📕 小红书标题**：
1. [标题1]
2. [标题2]
**📺 B站标题**：
1. [标题1]
2. [标题2]
**📰 公众号标题**：
1. [标题1]
2. [标题2]
**🎵 抖音标题**：
1. [标题1]
2. [标题2]
标题数量建议
| 平台 | 标题数量 | 风格侧重 |
|---|---|---|
| 小红书 | 3-5个 | 实用型+情绪型组合 |
| B站 | 2-3个 | 悬念型+知识型组合 |
| 公众号 | 2-3个 | 情绪型+观点型组合 |
| 抖音 | 3-4个 | 钩子型+反转型组合 |
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.
- 2d ago First seen · 189 lines · 97 tokens per session scan A 433fbcd118fe
topic-tracker is a skill published in the GitHub repository FutureFuzzy/topic-tracker (5 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 1,873 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to bilibili-helper, differing in 236 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…