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/evaluate-exponential-trend-deviation-regimesWrote 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/evaluate-exponential-trend-deviation-regimes)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/evaluate-exponential-trend-deviation-regimes"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/evaluate-exponential-trend-deviation-regimes/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/evaluate-exponential-trend-deviation-regimes"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/evaluate-exponential-trend-deviation-regimes.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 | $0.00068 | $0.01503 |
| Opus 5 | $0.00034 | $0.00751 |
| Sonnet 5 | $0.00014 | $0.00301 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
evaluate-exponential-trend-deviation-regimes 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 10d 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.
What it actually says
<essential_principles> 資產趨勢偏離度分析 核心原則
- 單資產偵測 - 計算單一資產的趨勢偏離度與歷史分位數
- 歷史對照分析 - 將當前偏離度與使用者指定的歷史日期或自動識別的極端值進行比較
- 宏觀因子分解 - 詳細拆解各宏觀代理指標對行情體質判定的貢獻（適用於支援的資產類別）
等待回應後再繼續。
讀取工作流程後，請完全遵循其步驟。
<quick_start> 快速開始
# 安裝依賴
pip install pandas numpy yfinance pandas-datareader statsmodels
# 快速偵測（範例：黃金期貨）
cd skills/evaluate-exponential-trend-deviation-regimes
python scripts/trend_deviation.py --symbol GC=F --quick
# 分析其他資產（範例：S&P 500）
python scripts/trend_deviation.py --symbol ^GSPC --start 1950-01-01
# 完整分析（含宏觀因子，目前支援黃金）
python scripts/trend_deviation.py --symbol GC=F --start 1970-01-01 --include-macro
# 指定歷史參考日期
python scripts/trend_deviation.py --symbol GC=F --compare-peaks "2011-09-06,2020-08-07"
# 生成視覺化圖表（輸出 PNG + JSON）
python scripts/generate_chart.py --output ./output/
</quick_start>
<reference_index>
參考文件 (references/)
| 文件 | 內容 |
|---|---|
| input-schema.md | 輸入參數詳細定義與驗證規則 |
| methodology.md | 指數趨勢擬合與偏離度計算方法論 |
| regime-rules.md | 1970s-like vs 2000s-like 體質判定規則 |
| data-sources.md | 數據來源與替代方案說明 |
| </reference_index> |
<workflows_index>
| Workflow | Purpose |
|---|---|
| detect.md | 單資產趨勢偏離度偵測與體質判定 |
| compare.md | 歷史峰值詳細對照分析 |
| macro.md | 宏觀因子分解與貢獻度分析 |
| </workflows_index> |
<templates_index>
| Template | Purpose |
|---|---|
| output-json.md | JSON 輸出結構定義 |
| output-markdown.md | Markdown 報告輸出模板 |
| </templates_index> |
<scripts_index>
| Script | Purpose |
|---|---|
| trend_deviation.py | 主要分析腳本：趨勢擬合、偏離度計算、體質判定 |
| generate_chart.py | 視覺化圖表生成：偏離度歷史圖表與峰值標註 |
| </scripts_index> |
<examples_index>
範例輸出 (examples/)
| 文件 | 內容 |
|---|---|
| gold-deviation-2026.json | 2026 年黃金趨勢偏離度分析範例 |
| </examples_index> |
<success_criteria> Skill 成功執行時：
- 成功擬合黃金價格的指數趨勢線
- 計算出當前偏離度百分比與歷史分位數
- 與 2011/1980 峰值進行有效比較
- 綜合宏觀代理指標得出 regime 判定（1970s-like / 2000s-like）
- 輸出完整的 JSON 或 Markdown 報告
- （選用）生成視覺化圖表（PNG）標註歷史峰值與當前位置 </success_criteria>
What ships with it
16 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/gold-deviation-2026.json 2.2 KB
- examples/gold-trend-deviation.md 3.7 KB
- manifest.json 2.3 KB
- methodology.md 4.5 KB
- references/data-sources.md 7.8 KB
- references/input-schema.md 6.0 KB
- references/methodology.md 936 B
- references/regime-rules.md 8.5 KB
- scripts/generate_chart.py 10 KB runs code
- scripts/trend_deviation.py 18 KB runs code
- skill.yaml 16 KB
- templates/output-json.md 5.3 KB
- templates/output-markdown.md 11 KB
- workflows/compare.md 4.4 KB
- workflows/detect.md 4.7 KB
- workflows/macro.md 6.4 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.
- 10d ago First seen · 125 lines · 68 tokens per session scan A d0674bd8f056
evaluate-exponential-trend-deviation-regimes is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 68 tokens to every session and 1,503 once invoked, about $0.0003 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.