cnhkmcp 2.1.7__tar.gz → 2.1.9__tar.gz

{cnhkmcp-2.1.7/cnhkmcp.egg-info → cnhkmcp-2.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cnhkmcp
-Version: 2.1.7
+Version: 2.1.9
 Summary: A comprehensive Model Context Protocol (MCP) server for quantitative trading platform integration
 Home-page: https://github.com/cnhk/cnhkmcp
 Author: CNHK

{cnhkmcp-2.1.7 → cnhkmcp-2.1.9}/cnhkmcp/__init__.py

@@ -50,7 +50,7 @@ from .untracked.forum_functions import (
     read_full_forum_post
 )
 
-__version__ = "2.1.7"
+__version__ = "2.1.9"
 __author__ = "CNHK"
 __email__ = "cnhk@example.com"
 

{cnhkmcp-2.1.7 → cnhkmcp-2.1.9}/cnhkmcp/untracked/AI/346/241/214/351/235/242/346/217/222/344/273/266/config.json

@@ -1,5 +1,5 @@
 {
-    "api_key": "sk-lCfgrezCmn15J4VNkQb4n7pHYH2lKDQ82lj5Ehu6tOWoecPc",
+    "api_key": "sk-xxxxxxx",
     "base_url": "https://api.moonshot.cn/v1",
     "model": "kimi-latest",
     "system_prompt": "You are a WorldQuant BRAIN platform expert and Consultant. Your goal is to assist users with Alpha development, BRAIN API usage, and maximizing consultant income.\n\nYour expertise includes:\n- Deep knowledge of the BRAIN API (authentication, data, simulation, analysis).\n- Alpha development best practices (stable PnL, economic sense, avoiding pitfalls).\n- Consultant income structure (daily pay, Genius Program, increasing earnings).\n\nGuidelines:\n- Always refer to the BRAIN_Consultant_Starter_Handbook.md for guidance.\n- Emphasize the importance of stable PnL and economic sense when discussing Alphas.\n- Follow the handbook's workflow for API usage.\n- Explain income components clearly when asked.\n- IMPORTANT: You cannot directly interact with the platform. You must guide the user step-by-step on what actions to take (e.g., 'Copy this code', 'Go to the Simulation page').\n- Always suggest the specific next operation the user should perform.\n\nKey Concepts:\n1. Pyramid:\n   - Definition: Combination of Region + Delay + Data Category. 'Lit' when 3+ Alphas are submitted in that combo.\n   - Purpose: Measures diversity; affects promotions and QualityFactor.\n   - Tips: Target underfilled pyramids; use grouping fields; track via MCP.\n\n2. Simulation Settings:\n   - Key fields: instrument_type, region, delay (D0/D1), universe, neutralization, decay, truncation, etc.\n   - Best Practices: Preprocess (winsorize -> zscore) -> Neutralize. Validate exposures.\n   - Neutralization: Use regression_neut or group_neutralize. Consider CROWDING or RAM options.\n   - Universes: Choose based on investability (e.g., TOP3000, TOPSP500).\n\nIf the user provides a screenshot, analyze it in the context of the BRAIN platform (e.g., Alpha code, simulation results, error messages). Answer in Chinese."

cnhkmcp-2.1.9/cnhkmcp/untracked/skills/brain-calculate-alpha-selfcorrQuick/SKILL.md

@@ -0,0 +1,25 @@
+---
+name: brain-Calculate-alpha-selfcorrQuick
+description: >-
+  Calculates self-correlation and PPAC (Power Pool Alpha Correlation) for WorldQuant BRAIN alphas Locally, this can be very fast than query the platform via mcp.
+  Use this when the user calculates alpha correlations, checks PPAC.
+---
+
+# Alpha Self and PPAC Correlation Calculator
+
+This skill helps calculate self-correlation and PPAC for alphas.
+For usage instructions and parameter details, see [reference.md](reference.md).
+
+## Why you would use this skill
+- Quickly assess alpha self-correlation and PowerPool Alpha Correlation (PPAC) without platform delays.
+- If the self-corr is higher than 0.7, you do not even need to query the production correlation from the platform since it will also be higher than 0.7 and fail the submission test.
+
+## Utility Scripts
+To perform the calculation, run the `skill.py` script located in the `scripts` directory.
+
+Example:
+```bash
+python .claude/skills/brain-calculate-alpha-selfcorrQuick/scripts/skill.py --start-date 01-10 --end-date 01-11 --region IND
+```
+
+Ensure dependencies from `.claude/skills/brain-calculate-alpha-selfcorrQuick/scripts/requirements.txt` are installed.

cnhkmcp-2.1.9/cnhkmcp/untracked/skills/brain-calculate-alpha-selfcorrQuick/reference.md

@@ -0,0 +1,59 @@
+# Alpha Self and PPAC Correlation Calculator
+
+Calculates self-correlation and PPAC (Power Pool Alpha Correlation) for WorldQuant BRAIN alphas. This skill combines two local self-correlation calculation codes into a unified, easy-to-use solution for RA (Research Associates).
+
+## Why you would use this skill
+- Quickly assess alpha self-correlation and PowerPool Alpha Correlation (PPAC) without platform delays.
+- If the self-corr is higher than 0.7, you do not even need to query the production correlation from the platform since it will also be higher than 0.7 and fail the submission test.
+
+
+## Parameters
+
+- `--start-date`: Start date in MM-DD format (e.g., "01-10"), this defines the beginning of the date range for alpha retrieval, The year is automatically set to the current year. The retrival alphas will be from submitted alphas by yourself and we will calculate self-correlation and PPAC correlation with each of them to check if the new alpha you are testing is highly correlated with any of your existing alphas.
+- `--end-date`: End date in MM-DD format (e.g., "01-11"), this defines the end of the date range for alpha retrieval. The year is automatically set to the current year. The retrival alphas will be from submitted alphas by yourself and we will calculate self-correlation and PPAC correlation with each of them to check if the new alpha you are testing is highly correlated with any of your existing alphas.
+- `--region`: Market region (e.g., "IND", "USA", "EUR")
+- `--sharpe-threshold`: Sharpe ratio threshold (default: -1.0)
+- `--fitness-threshold`: Fitness threshold (default: -1.0)
+- `--alpha-num`: Number of alphas to retrieve (default: 100)
+- `--username`: BRAIN platform email (optional, uses stored credentials if available)
+- `--password`: BRAIN platform password (optional, uses stored credentials if available)
+- `--output`: Output Excel file name (default: auto-generated)
+
+## Examples
+
+Example:
+```bash
+python .claude/skills/brain-calculate-alpha-selfcorrQuick/scripts/skill.py --start-date 01-10 --end-date 01-11 --region IND
+```
+
+## Implementation Details
+
+This skill performs the following steps:
+1. Authenticates with WorldQuant BRAIN API
+2. Retrieves eligible alphas based on date range, region, and threshold filters
+3. Calculates self-correlation for each alpha
+4. Calculates PPAC correlation for each alpha
+5. Saves results to an Excel file with comprehensive alpha metrics
+
+The skill outputs:
+- Alpha ID and expression
+- Check status (Check OK/FAIL)
+- Rank based on Sharpe ratio
+- Self-correlation and PPAC correlation values
+- Turnover, fitness, margin, and other metrics
+- Neutralization settings and other configuration details
+
+## Dependencies
+
+- requests
+- pandas
+- numpy
+- tqdm
+
+## Notes
+
+1. Date format is MM-DD, and the year is automatically set to the current year
+2. The skill uses stored credentials from BRAIN MCP configuration if available
+3. Results are saved as Excel files in the current directory
+4. The skill includes progress bars for long-running calculations
+5. Both self-correlation and PPAC correlation are calculated for comprehensive analysis

cnhkmcp-2.1.9/cnhkmcp/untracked/skills/brain-calculate-alpha-selfcorrQuick/scripts/requirements.txt

@@ -0,0 +1,4 @@
+requests>=2.32.0
+pandas>=2.0.0
+numpy>=1.24.0
+tqdm>=4.65.0