Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fatfingererr/macro-skillsnpx agentmods add skills/fatfingererr/macro-skills/google-trends-ath-detectorWrote 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/fatfingererr/macro-skills/google-trends-ath-detector)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/google-trends-ath-detector"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/google-trends-ath-detector/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/fatfingererr/macro-skills/google-trends-ath-detector"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/google-trends-ath-detector.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 | $0.00084 | $0.02297 |
| Opus 5 | $0.00042 | $0.01149 |
| Sonnet 5 | $0.00017 | $0.00459 |
| Haiku 4.5 | $0.00008 | $0.00230 |
Grade A, and why
google-trends-ath-detector 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 11d 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.
<essential_principles> Google Trends ATH Detector 核心原則
1. 模擬真人瀏覽器行為抓取 Google Trends
本技能使用 Selenium 模擬真人瀏覽器:
- 移除
navigator.webdriver自動化標記 - 隨機輪換 User-Agent(Chrome/Firefox/Safari)
- 請求間隨機延遲(0.5-2 秒)
- 先訪問首頁建立 session,再抓取數據
2. 訊號分型(Signal Typing)
搜尋趨勢飆升分為三種類型:
| 類型 | 特徵 | 解讀 |
|---|---|---|
| Seasonal spike | 每年固定月份重複 | 制度性週期(投保季、報稅季) |
| Event-driven shock | 短期尖峰、z-score 高 | 新聞/政策/突發事件 |
| Regime shift | 趨勢線上移、持續高位 | 結構性關注上升 |
3. 分析公式
ATH 判定:latest_value >= max(history) * 0.98
異常判定:zscore >= threshold (default: 2.5)
訊號分型:based on (is_ath, is_anomaly, trend_direction)
4. 描述性分析優先
本技能提供客觀的數學分析結果:
- 輸出訊號類型、異常分數等量化指標
- 提取 related queries 作為驅動因素參考
- 由用戶根據專業知識自行解讀 </essential_principles>
- Detect - 快速偵測是否創下 ATH 或出現異常
- Analyze - 深度分析訊號類型與驅動因素
- Compare - 比較多個主題的趨勢共振
等待回應後再繼續。
讀取工作流程後,請完全遵循其步驟。
<reference_index>
參考文件 (references/)
| 文件 | 內容 |
|---|---|
| input-schema.md | 完整輸入參數定義與預設值 |
| data-sources.md | Google Trends 數據來源與 Selenium 爬取指南 |
| signal-types.md | 訊號分型定義與判定邏輯 |
| seasonality-guide.md | 季節性分解方法與解讀 |
| </reference_index> |
<workflows_index>
| Workflow | Purpose |
|---|---|
| detect.md | 快速偵測 ATH 與異常分數 |
| analyze.md | 深度分析、訊號分型、驅動詞彙 |
| compare.md | 多主題趨勢共振分析 |
| </workflows_index> |
<templates_index>
| Template | Purpose |
|---|---|
| output-schema.yaml | 標準輸出 JSON schema |
| </templates_index> |
<scripts_index>
| Script | Purpose |
|---|---|
| trend_fetcher.py | 核心爬蟲與分析邏輯(Selenium 版) |
| </scripts_index> |
<examples_index>
範例輸出 (examples/)
| 文件 | 內容 |
|---|---|
| health_insurance_ath.json | Health Insurance ATH 偵測範例 |
| seasonal_vs_anomaly.json | 季節性 vs 異常判定範例 |
| multi_topic_comparison.json | 多主題比較範例 |
| </examples_index> |
<quick_start> 快速開始:安裝依賴
pip install selenium webdriver-manager beautifulsoup4 lxml loguru
Python API:
from scripts.trend_fetcher import fetch_trends, analyze_ath
# 抓取數據(使用 Selenium 模擬瀏覽器)
data = fetch_trends(
topic="Health Insurance",
geo="US",
timeframe="2004-01-01 2025-12-31"
)
# ATH 分析
result = analyze_ath(data, threshold=2.5)
print(f"Is ATH: {result['analysis']['is_all_time_high']}")
print(f"Signal Type: {result['analysis']['signal_type']}")
print(f"Z-Score: {result['analysis']['zscore']}")
CLI 快速開始:
# 基本分析
python scripts/trend_fetcher.py \
--topic "Health Insurance" \
--geo US \
--output ./output/health_insurance.json
# 比較多個主題
python scripts/trend_fetcher.py \
--topic "Health Insurance" \
--compare "Unemployment,Inflation" \
--geo US \
--output ./output/comparison.json
# 跳過 related queries(更快、更少請求)
python scripts/trend_fetcher.py \
--topic "Health Insurance" \
--no-related \
--output ./output/health_insurance.json
# Debug 模式(顯示瀏覽器、保存 HTML)
python scripts/trend_fetcher.py \
--topic "Health Insurance" \
--debug \
--no-headless
# 登入模式(預設等待 120 秒供 2FA 驗證)
python scripts/trend_fetcher.py \
--topic "Health Insurance" \
--output ./output/health_insurance.json
# 跳過登入等待(不需要登入時)
python scripts/trend_fetcher.py \
--topic "Health Insurance" \
--login-wait 0 \
--output ./output/health_insurance.json
# 從已下載的 CSV 檔案分析(跳過瀏覽器抓取)
python scripts/trend_fetcher.py \
--topic "Health Insurance" \
--csv ./downloads/multiTimeline.csv \
--output ./output/health_insurance.json
# 自動從 Downloads 目錄找最新 CSV
python scripts/trend_fetcher.py \
--topic "Health Insurance" \
--csv auto \
--output ./output/health_insurance.json
What ships with it
14 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.
- examples/health_insurance_ath.json 1.6 KB
- examples/multi_topic_comparison.json 3.1 KB
- examples/seasonal_vs_anomaly.json 4.2 KB
- manifest.json 2.2 KB
- references/data-sources.md 10 KB
- references/input-schema.md 6.2 KB
- references/seasonality-guide.md 8.5 KB
- references/signal-types.md 7.7 KB
- scripts/trend_fetcher.py 43 KB runs code
- skill.yaml 7.0 KB
- templates/output-schema.yaml 3.3 KB
- workflows/analyze.md 6.3 KB
- workflows/compare.md 6.4 KB
- workflows/detect.md 3.7 KB
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.
- 11d ago First seen · 232 lines · 84 tokens per session scan A 9395411d2543
google-trends-ath-detector is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 84 tokens to every session and 2,297 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…