Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsCrypto Multi-Timeframe Scoring Desk
Read-only 0–100 score for a crypto pair across 1D, 4H, and 15m. Transparent technical, confluence, and optional macro breakdown. No orders, no exchange account, no financial advice.
$15
Crypto Multi-Timeframe Scoring Desk
Example session with this skill installed
Score BTC/USD and ETH/USD across 1D, 4H and 15m and give me the report in Spanish.
- Read your context and instructions
- Compiled the crypto multi-timeframe scoring
Here is a live local demo from 10 November 2026, 22:53 Europe/Madrid, using public Binance USDT klines labeled BTC/USD and ETH/USD (not Twelve Data). Each pair used 249 closed candles on 1D, 4H, and 15m. Indicators were computed on the last closed 15-minute bar (22:30 Europe/Madrid). Macro inputs were omitted, so their weight was redistributed between Technical and confluence.
BTC/USD scored 52.6 / 100, bias MIXED. Last close 73,870. Technical 0.586 (weight 0.556) and MTF confluence 0.45 (weight 0.444). Confluence was PULLBACK: 1D BULL, 4H BEAR, 15m BEAR, with a BULLISH_RSI divergence on 4H. Context style MEAN_REVERSION (descriptive only). 15m RSI 56.6, ADX 19.9, ATR 0.35% of price.
ETH/USD scored 48.2 / 100, also MIXED. Last close 2,059.05. Technical 0.511 (weight 0.528) and confluence 0.45 (weight 0.472), same PULLBACK structure (1D BULL / 4H BEAR / 15m BEAR).
The report lists sources, as-of time, closed-bar counts, and missing macro fields. It does not recommend buying or selling. You decide what to do.
Connects securely to your tools. The creator never sees your data.
About this skill
Crypto Multi-Timeframe Scoring Desk gives your agent a structured, rules-based snapshot of a crypto pair — not a trade signal.
The agent collects closed OHLCV for 1D, 4H, and 15m (on Agensi, typically through Twelve Data after you approve the tool quote). A standard-library Python scorer then runs offline: no network, no API keys, no exchange login. You can also pass your own candles.json.
You get:
- A 0–100 score and a bias band (CONSTRUCTIVE, UPSIDE_LEAN, MIXED, CAUTION, or DEFENSIVE). These names describe the snapshot. They are not an instruction to act.
- Component scores for Technical (trend, RSI, ADX, volume, momentum) and multi-timeframe confluence (ALIGNED_UP, PULLBACK, COUNTER, or ALIGNED_DOWN), plus Macro when Bitcoin dominance and market-cap change are actually available.
- Dynamic weights by market regime. If Macro is missing, its weight is redistributed between Technical and confluence. Trade-history and adaptive-edge legs are not used.
- Per-timeframe trend, RSI, ADX, ATR (volatility context only), MACD, Bollinger, and StochRSI on the last closed bar (anti-repaint).
- A filled report in the user’s language, with sources, as-of time, missing fields, and a clear disclaimer.
Requirements: Python 3.10+ (standard library only). At least 200 closed candles on 1D and 4H; 15m is recommended. This skill does not place or change orders and is not financial advice.
Analysis only, no orders. Needs 200+ closed candles on 1D and 4H. Macro leg only when BTC dominance and market-cap change are supplied. Not financial advice.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today
- Software
Python