us-cpi-pce-comparator

用「庫存快速回補」作為短期警戒訊號，評估銅價是否接近短線高點，同時給出一個「長期是否偏便宜」的歷史分位數判讀。

1 skill

用跨資產訊號（全球股市韌性 + 中國利率環境）評估銅價能否突破關卡或進入「回補/回踩」到支撐的機率與路徑

1 skill

用公開資料量化「銅供應是否過度集中、主要產地是否結構性衰退、替代增量是否依賴少數國家」，並輸出可行的中期供應風險結論與情境推演。

1 skill

用天然氣與化肥價格的日頻數據，檢驗「天然氣暴漲→化肥供應受限/毀約→化肥飆價」敘事是否成立，輸出可標註到圖上的關鍵轉折點與領先落後分析。

1 skill

在「失業率走高／勞動市場轉弱」但「名目或實質 GDP 仍維持高位（或仍在成長）」的情境下，依據歷史關聯估算美國財政赤字占 GDP（Deficit/GDP）可能擴張的區間，並生成對長天期美債（長久期 UST）供給/利率風險的情境解讀。

1 skill

把「獲利成長 × 財務狀況（金融環境）」映射成「投資時鐘」，判斷目前落在哪個象限、近期是順時針還是逆時針旋轉、以及相對於上一輪循環的位置差異

1 skill

Chief AI Officer advisory for startups: model build-vs-buy calculator (API vs fine-tune vs build with 3-year TCO across 6 paths + breakeven that balances economics with practical feasibility), AI risk classifier (EU AI Act tier with 7 Article citations + US state patchwork: NYC LL 144, CO AI Act, IL HB 53, CA SB 1001, IL BIPA + industry overlays for FDA AI/ML, CFPB Circular 2023-03, NYDFS Reg 23, NAIC, ECOA, Fed SR 11-7), AI cost economics (API vs self-hosted breakeven with 2026 pricing across A100/H100, utilization reality, hidden costs). 4 in-depth references each citing 5+ authoritative sources. Standalone-installable; also bundled in c-level-skills. Strategic only — does not duplicate engineering AI/ML skills.

1 skill

Two stages: first a single-page sheet of numbered panels from an image model, then that sheet fed to Seedance as the reference. The sheet owns order, framing and timing, and the video prompt only has to connect the panels.

1 skill

Read-only Statistical Centre of Iran (amar.org.ir): CPI inflation, unemployment, census, any table.

1 skill · 1 MCP server

Convert JSON, CSV, YAML, and other structured data into TOON (Token-Oriented Object Notation) — a compact, lossless re-encoding that uses ~40% fewer tokens than JSON when fed to LLMs. Wraps @toon-format/toon and tracks the wider ecosystem (Python, Java, .NET, PHP, Rust ports).

6 skills

When the agent stops, a cheap model audits the whole conversation against ~/.agents/AGENTS.md. Rule violations are fed back to the agent on your next message.

hooks

When the agent stops, a cheap model audits the whole conversation against ~/.agents/AGENTS.md. Rule violations are fed back to the agent on your next message.

hooks