Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.
Scaffold Zig-native database routes using pg.zig + TurboPG. Use when adding database-backed CRUD endpoints, custom SQL queries (pgvector, JSONB, full-text search, JOINs, CTEs), or standalone TurboPG usage.
Build neuro-symbolic LLM applications with Synalinks framework. Use when working with DataModel, Program, Generator, Module, training LLM pipelines, in-context learning, structured output, JSON operators, Branch/Decision control flow, FunctionCallingAgent, RAG/KAG, or Keras-like LLM workflows.
Parse table definition to extract module name, model name, table name, and field definitions. First step of CRUD generation.
Quantitative statistical methods: ADF unit-root / cointegration tests, GARCH volatility modeling, regression diagnostics (heteroskedasticity / autocorrelation), Bootstrap, and hypothesis testing.
Core technical indicator collection (trend EMA/ADX + mean-reversion BB/RSI + volume-price OBV/volume ratio), generates a composite signal via three-dimensional voting. Pure pandas implementation for any OHLCV data.
Data source selection decision tree. Load this skill BEFORE any backtest or data-fetching task to choose the best available data source.
Candlestick pattern recognition engine, pure pandas vectorized implementation of 15 classic candlestick patterns (5 single-candle + 5 double-candle + 4 triple-candle + 1 trend confirmation), generating a composite signal from bullish/bearish pattern scores.
Elliott Wave Theory signal engine. Detects swing points through Zigzag, matches 5-wave impulse and 3-wave corrective structures, validates them with Fibonacci wave relationships, and generates trend-top / correction-complete signals. Pure in-house pandas implementation.
Machine-learning predictive strategy based on sklearn walk-forward training, feature engineering, and signal generation. Suitable for any OHLCV data.
Send messages to other agents on your server. Use when you need to communicate with, query, or delegate tasks to another agent.
Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update the model configuration. Covers models.json configuration, CI test matrix, and handle validation.
Find other agents on the same server. Use when the user asks about other agents, wants to migrate memory from another agent, or needs to find an agent by name or tags.
Search past messages to recall context. Use when you need to remember previous discussions, find specific topics mentioned before, pull up context from earlier in the conversation history, or find which agent discussed a topic.
Create data-driven charts with Vega-Lite (simple) and Vega (advanced). Best for bar, line, scatter, heatmap, area charts, and multi-series analytics. Use when you have numeric data arrays needing statistical visualization. Vega for radar charts and word clouds. NOT for process diagrams (use mermaid) or quick KPI cards (use infographic).
Design and run machine learning experiments with proper evaluation using jupyter_execute, including training, benchmarking, and ablation studies. Use when the user wants to train models, compare algorithms, run ablation studies, evaluate ML performance, or reproduce paper results.
Use as the routing skill for selecting the correct F8Framework layer skill chain across foundation, features, editor, tools, and build.
Use as the master index and router for the full F8Framework skill library. Trigger when selecting the correct skill or skill chain across foundation bootstrap, runtime features, editor tooling, utility tools, and build packaging workflows.When a feature needs to be implemented, priority should be given to using the skills of F8Framework.
