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 fatfingererr/macro-skills --skill lithium-supply-demand-gap-radargit clone --depth 1 https://github.com/fatfingererr/macro-skillsWrote 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/lithium-supply-demand-gap-radar)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/lithium-supply-demand-gap-radar"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/lithium-supply-demand-gap-radar/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/lithium-supply-demand-gap-radar"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/lithium-supply-demand-gap-radar.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 | $0.00088 | $0.03630 |
| Opus 5 | $0.00044 | $0.01815 |
| Sonnet 5 | $0.00018 | $0.00726 |
| Haiku 4.5 | $0.00009 | $0.00363 |
Grade A, and why
lithium-supply-demand-gap-radar 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles> 鋰產業鏈供需雷達 核心原則
鋰產業鏈必須分層分析，不可混為一談：
Mining → Processing → Battery
(礦端) (化學品) (終端需求)
| 層級 | 代表數據 | 典型延遲 |
|---|---|---|
| Upstream (礦端) | 鋰礦產量、出口量 | 年度/季度 |
| Midstream (化學品) | 碳酸鋰/氫氧化鋰價格 | 週度/日度 |
| Downstream (電池/EV) | EV 銷量、電池裝機量(GWh) | 月度 |
強制規則：
- 供給分析需指定層級（礦端 vs 精煉端）
- 需求 proxy 需明確轉換假設（kWh → kg Li）
- 價格分析需區分碳酸鋰 vs 氫氧化鋰
根據 data_level 參數自動選擇數據源：
| data_level | 價格數據 | 供需數據 | 可靠度 |
|---|---|---|---|
free_nolimit |
CME 期貨/Proxy 指數 | USGS/IEA/澳洲政府 | 中 |
free_limit |
SMM/Fastmarkets 頁面 | + 公司財報 | 中高 |
paid_low |
SMM 完整序列 | + Benchmark 基本 | 高 |
paid_high |
Fastmarkets API | + S&P/BNEF/WoodMac | 最高 |
強制規則：
- 價格數據不足時，使用 CME 合約或相關股籃子作為 proxy
- 需在輸出中標註實際使用的數據等級
電池需求到鋰需求的轉換必須明確假設：
| 假設場景 | kg Li / kWh | 備註 |
|---|---|---|
| 保守估計 | 0.12 | 含 LFP 佔比上升假設 |
| 中性估計 | 0.15 | 混合 NMC/LFP |
| 積極估計 | 0.18 | 高鎳 NMC 主導 |
li_demand_kt = battery_gwh * kg_per_kwh * 1000 # 單位: kt LCE
強制規則：
- 需求估計必須輸出三個情境（保守/中性/積極）
- 輸出需包含
kg_per_kwh_assumption欄位
鋰價週期分為四個階段：
| Regime | 特徵 | 交易含義 |
|---|---|---|
downtrend |
12-26 週動能 < 0, 斜率 < 0 | 空頭主導，避免做多 |
bottoming |
動能收斂，波動下降，均值回歸 | 觀望，等待確認 |
uptrend |
動能 > 0, 斜率 > 0 | 做多視窗開啟 |
overheat |
動能極端正值，波動放大 | 獲利了結風險 |
指標組合：
- 12 週 / 26 週動能（ROC）
- 趨勢斜率（線性回歸）
- 波動率（ATR / 標準差）
- 均值回歸強度（距 MA 偏離度）
ETF 對鋰價的敏感度受持股結構影響：
| 持股類型 | 對鋰價 Beta | 波動特性 |
|---|---|---|
| Upstream (礦業) | 1.5 - 2.5 | 高槓桿、高波動 |
| Midstream (精煉) | 0.8 - 1.2 | 跟隨但有加工費緩衝 |
| Downstream (電池) | 0.3 - 0.8 | 受競爭/技術路線影響 |
計算公式：
ETF_beta_li = Σ(weight_i * beta_i_to_lithium)
強制規則：
- 需計算 rolling beta（建議 52 週滾動）
- 傳導斷裂判斷：beta < 0.3 且持續 > 8 週
</essential_principles>
- Full Analysis - 完整供需×價格×傳導整合分析（生成完整報告）
- Balance Nowcast - 僅計算供需平衡即時估計（缺口擴大/縮小）
- Price Regime - 僅分析價格型態與週期位置
- ETF Exposure - 僅分析 ETF 持股結構與鋰價敏感度
- Ingest Data - 從各數據源擷取並標準化數據
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 |
|---|---|
| data-sources.md | 所有數據來源詳細說明與 URL |
| unit-conversion.md | 單位轉換規則（LCE/Li/GWh） |
| price-methodology.md | 價格數據方法學（Fastmarkets/SMM） |
| etf-holdings-structure.md | LIT 持股結構與產業鏈分段 |
| supply-chain-mapping.md | 鋰供應鏈完整映射（礦→化學品→電池） |
| failure-modes.md | 失敗模式與緩解策略 |
| </reference_index> |
What ships with it
25 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.
- manifest.json 4.6 KB
- methodology.md 3.2 KB
- references/data-sources.md 7.0 KB
- references/etf-holdings-structure.md 8.9 KB
- references/failure-modes.md 9.0 KB
- references/price-methodology.md 7.1 KB
- references/supply-chain-mapping.md 11 KB
- references/unit-conversion.md 6.4 KB
- scripts/classify_regime.py 11 KB runs code
- scripts/compute_balance.py 8.4 KB runs code
- scripts/compute_etf_beta.py 14 KB runs code
- scripts/inflection_point_chart.py 13 KB runs code
- scripts/ingest_sources.py 8.9 KB runs code
- scripts/lithium_pipeline.py 25 KB runs code
- scripts/visualize_analysis.py 21 KB runs code
- skill.yaml 22 KB
- templates/config.yaml 4.0 KB
- templates/data-schema.yaml 8.4 KB
- templates/output-json.md 10 KB
- templates/output-markdown.md 13 KB
- workflows/balance-nowcast.md 8.6 KB
- workflows/etf-exposure.md 9.6 KB
- workflows/full-analysis.md 8.7 KB
- workflows/ingest.md 11 KB
- workflows/price-regime.md 9.0 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.
- 12d ago First seen · 334 lines · 88 tokens per session scan A 942754b5e82a
lithium-supply-demand-gap-radar is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 88 tokens to every session and 3,630 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
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.
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.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.