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 trend-reportgit 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/trend-report)<a href="https://agentmods.dev/skills/asoiso/trend-radar/trend-report"><img src="https://agentmods.dev/badge/skills/asoiso/trend-radar/trend-report/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/trend-report"><img src="https://agentmods.dev/badge/skills/asoiso/trend-radar/trend-report.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 | $0.00086 | $0.02321 |
| Opus 5.5 | $0.00034 | $0.00928 |
| Sonnet 5.5 | $0.00017 | $0.00464 |
| Haiku 4.5 | $0.00009 | $0.00232 |
Grade A, and why
trend-report 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 2mo 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
trend-report
按调度周期生成趋势简报:日报 / 周报 / 月报 / 月度对比 / 自定义对比。所有数据来自 trendradar MCP,禁止凭空编造指标。
When to activate
命中以下任一表达,立即激活:
- 中文:
出一份日报/周报/月报/趋势简报/对比上周/对比上月/给老板看的简报/今天的总结/本周总结/本月总结/近 7 天报告 - 英文:
summary report/digest/daily/weekly/monthly digest/period over period
如果用户的请求只是"看看现在最热的话题"而无报告意图,转交 trend-search / trending-now 类技能;本技能只负责"成型的、可分发的报告"。
Workflow
按编号顺序执行,不要跳步。
-
解析时间范围(必做) 调用
mcp__trendradar__resolve_date_range,把今天 / 昨天 / 本周 / 上周 / 本月 / 上月 / Q1 / 近 7 天 / 4 月 1 日到 4 月 15 日等自然语言转换为 ISOstart_date/end_date。跨年、跨月、跨季度边界一律走这一步,不要手算。 -
优先尝试一站式接口 如果用户要的是"标准日报/周报/月报",先尝试:
mcp__trendradar__generate_summary_report( date_range={"start_date": ..., "end_date": ...}, report_type="daily" | "weekly" | "monthly" )返回结构若已覆盖用户诉求,直接进入步骤 5(套模板)。
-
手动组合(fallback) 若
generate_summary_report输出不足(例如用户要"按行业拆分"或"附借势机会评分"),则组合调用:- 逐日数据:对范围内每个日期循环调用
mcp__trendradar__get_news_by_date(date=...) - 跨期洞察:
mcp__trendradar__analyze_data_insights(date_range=..., dimensions=[...])用于话题趋势、平台分布、情感倾向 - 高互动话题:
mcp__trendradar__get_trending_topics(date_range=..., limit=10)
- 逐日数据:对范围内每个日期循环调用
-
对比期处理 用户出现
对比 / vs / 环比 / 同比 / 较上周 / 比上月时:mcp__trendradar__compare_periods( period_a={"start_date": ..., "end_date": ...}, // 当期 period_b={"start_date": ..., "end_date": ...} // 对照期 )period_a永远是用户明确提到的"主期",period_b是被对比的参考期。 -
挑选输出模板(必须三选一,不要混搭) 按用户的受众线索匹配。无线索时默认用 执行摘要。
- 出现
老板 / CEO / 创始人 / 管理层 / 高管 / 董事会 / 一句话→ 执行摘要 - 出现
媒体 / 内容行业 / 平台 / IP / 政策 / 行业洞察→ 媒体行业 - 出现
投放 / 广告 / 借势 / 营销 / 品牌 / 限流 / 敏感词 / 流量→ 投放团队
- 出现
-
附 chart-friendly 数据块(必做) 报告末尾必须给一段可直接粘贴到飞书文档 / Notion / Lark Sheets 的 markdown 表格 + 一句"如何配图"提示(柱状图 / 折线图 / 饼图)。
Output Templates
模板 A — 执行摘要(C-suite,默认)
全文 ≤ 400 字。语气克制、结论先行。
# {周期标题,例:2026-04-22 ~ 2026-04-28 周报}
## TL;DR
{≤ 3 行,每行一个核心判断。先讲变化,再讲量级。}
## 关键事件
- {事件 1:发生了什么 + 量级}
- {事件 2:发生了什么 + 量级}
- {事件 3:发生了什么 + 量级}
## 关键指标
| 指标 | 本期 | 上期 | 变动 |
| --- | --- | --- | --- |
| 全网话题数 | … | … | ±x% |
| 头部话题峰值互动 | … | … | ±x% |
| 高情感强度事件数 | … | … | ±x% |
## 我们要做什么
1. {行动 1,可执行、有 owner 暗示}
2. {行动 2}
3. {行动 3}
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.
- 2mo ago First seen · 172 lines · 86 tokens per session scan A c93f2c8625a9
trend-report is a skill published in the GitHub repository asoiso/trend-radar (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 86 tokens to every session and 2,321 once invoked, about $0.0003 per session on Opus 5.5. 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.
trend-report compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trend-reportasoiso/trend-radar | Skill | 2 | 6mo ago | Apache-2.0 | A | 86 | Claude Code, Codex |
| ops-demoSnowflake-Labs/cocoplus | Skill | 727 | yesterday | MIT | A | 46 | Claude Code |
| ai-brainOotto-AI/claude-content-skills | Skill | 408 | yesterday | MIT | A | 95 | Claude Code |
| comment-responderOotto-AI/claude-content-skills | Skill | 408 | yesterday | MIT | A | 94 | Claude Code |
| hashtag-keyword-researchOotto-AI/claude-content-skills | Skill | 408 | yesterday | MIT | A | 56 | Claude Code |
| trend-spotterOotto-AI/claude-content-skills | Skill | 408 | yesterday | MIT | A | 74 | Claude Code |
| diarySnowflake-Labs/cocoplus | Skill | 727 | yesterday | MIT | A | 12 | Claude Code, Codex |