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 skills add asoiso/trend-radar --skill viral-forgegit clone --depth 1 https://github.com/asoiso/trend-radarWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/asoiso/trend-radar/viral-forge)<a href="https://agentmods.dev/skills/asoiso/trend-radar/viral-forge"><img src="https://agentmods.dev/badge/skills/asoiso/trend-radar/viral-forge/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/asoiso/trend-radar/viral-forge"><img src="https://agentmods.dev/badge/skills/asoiso/trend-radar/viral-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00111 | $0.03880 |
| Opus 5 | $0.00056 | $0.01940 |
| Sonnet 5 | $0.00022 | $0.00776 |
| Haiku 4.5 | $0.00011 | $0.00388 |
Grade A, and why
viral-forge 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
viral-forge — 爆款内容生产器
把一个真实热点（来自 trendradar）转成平台原生的爆款内容，覆盖标题变体、开篇 hook、正文骨架、hashtag、CTA。
When to activate
触发词（任一即可）：
- 中文：
爆款标题/写一条小红书笔记/抖音脚本/微博热搜文案/B站标题/知乎回答开头/公众号开头/借势XX 写文案/蹭热点写一篇/给我写个爆款 - English：
viral title/hook for X/write a viral post about X/xiaohongshu note/douyin script
平台关键词（出现任一时进入对应平台分支）：小红书 / xhs / 抖音 / douyin / tiktok-cn / B站 / bilibili / 微博 / weibo / 知乎 / zhihu / 公众号 / wechat / gzh.
Workflow
按顺序执行，每一步都要明确输出。
-
锚定真实热点（grounding）
- 如果用户给了具体新闻 / 事件 / 标题：直接进入第 2 步。
- 如果用户只给了一个模糊话题（"写一条关于 AI 的小红书"）：先调用
mcp__trendradar__get_latest_news(limit=30)获取近期真实角度；如果用户提到了某个参考事件，调用mcp__trendradar__find_related_news(reference_title="...")找关联角度。 - 必须挑选 1-3 条真实新闻作为事实锚点，记录每条的 platform + 标题 + 时间，后续输出中要可追溯。
-
（可选）情绪基调判断
- 当事件属于争议 / 社会 / 民生 / 娱乐塌房等敏感类，调用
mcp__trendradar__analyze_sentiment判断 正向 / 负向 / 中性 哪个占主导。 - 平台与情绪适配：
- 负向主导 → 公众号 / 知乎 适合理性复盘；小红书 / 抖音 不要硬蹭，可换"避坑 / 观察"角度。
- 正向主导 → 小红书 / 抖音 / B站 庆祝、玩梗、种草模式都可以。
- 中性 → 走"信息差 / 干货 / 揭秘"路线最稳。
- 当事件属于争议 / 社会 / 民生 / 娱乐塌房等敏感类，调用
-
加载平台规则
- 阅读
references/platform-playbook.md获取目标平台的字符上限、hook 模板、互动钩子。 - 如果用户没指定平台，默认输出 小红书 + 抖音 + 微博 三套（覆盖度最高的组合）。
- 阅读
-
加载标题模板
- 阅读
references/title-patterns.md，挑选 3-5 个与本次事件 / 平台最匹配的模板。 - 不同平台优先模板不同：
- 小红书：痛点式 / 清单式 / 第二人称式 / 损失厌恶式
- 抖音：悬念式 / 反转式 / 数字反差式 / 提问式
- B站：对比式 / 反共识式 / 揭秘式 / 故事钩子式
- 微博：情绪标签式 / 时代符号式 / 角色代入式
- 知乎：反共识式 / 权威背书式 / 揭秘式
- 公众号：共情式 / 警示式 / 时代符号式 / 解决方案式
- 阅读
-
生成内容
- 3-5 条标题变体，每条要标注用了哪个模板（如
[反转式][数字反差式]）。 - 1 套正文骨架（开篇 hook + 中段 3-5 个要点 + 收尾 CTA）。
- 1 个开篇 hook（视频前 3 秒 / 文字首句必须勾住人）。
- hashtag / 话题标签清单（数量符合平台规范）。
- 1 个 CTA（评论 / 收藏 / 转发 / 三连 / 关注）。
- 3-5 条标题变体，每条要标注用了哪个模板（如
-
过 guardrail 自检（见下方 "Anti-clickbait + 合规 guardrails" 与 "Quality checklist"）
-
返回给用户：按"每平台一个 block"的格式输出。
Per-platform output blocks
按平台输出，每个 block 都要有 字符上限标注 + 标题变体 + 开篇 hook + 正文骨架 + hashtag + CTA + 来源标注。
小红书
- 字符限制：标题 ≤ 20 字最佳（系统上限 20，超出会被截断），正文 ≤ 1000 字（实际 600-800 字阅读体验最好）。
- emoji：适度使用 2-5 个，集中在标题首尾、段首；过量会被识别为"营销号"。
- 结构模板：
标题（≤20 字 + 1-2 个 emoji） 首段 hook（1-2 句，制造痛点 / 反转 / 共鸣，让人想滑下去） 痛点 1 / 亮点 1（小标题加粗或 emoji 引导） 痛点 2 / 亮点 2 痛点 3 / 亮点 3 （建议 3-5 段，每段 2-4 行） 收尾互动钩子（提问 / 求评论 / 抛话题） #话题1# #话题2# #话题3#（3-8 个） - hashtag：3-8 个，混合大词（百万级）+ 中词（十万级）+ 长尾词。
- CTA：
你也遇到过吗？评论区告诉我/点赞收藏 下次不迷路/蹲一个同款。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 232 lines · 111 tokens per session scan A 9fb773a2664f
viral-forge is a skill published in the GitHub repository asoiso/trend-radar (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 111 tokens to every session and 3,880 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ops-demo
CocoOps demo mode activator — populates .cocoplus/ops/demo/ with realistic mock data and sets cocoplus.toml [demo] enabled = true. Invoked via $ops demo.
add-analytics
Add Google Analytics 4 tracking to any project. Detects framework, adds tracking code, sets up events, and configures privacy settings.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
agent-team-orchestration
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4)…
rank-monitor
Set up and run keyword ranking monitoring — baseline capture, scheduled position checks against GSC and connected rank-tracker MCPs, and severity-tiered alerts (minor/major/critical) on drops; --features adds a query-by-SERP-feature ownership matrix including AI Overview citation presence. Triggers on…
agent-bom-enforce
Enforce security policies on MCP tool calls and block dangerous operations at runtime. Use when: "block risky calls", "apply policy", "proxy", "runtime protection", "policy enforcement", "intercept MCP calls".