Claude Skill
SynaLinks/synalinks-skills
Open-source collection of Claude skills by SynaLinks for neuro-symbolic AI integration, enhancing large language models with symbolic reasoning capabilities in Python.
Overview
Repository
Install this Skill
git clone https://github.com/SynaLinks/synalinks-skills.gitRegistry
Summary
A collection of Claude skills developed by SynaLinks for their open-source neuro-symbolic AI projects, focusing on integrating large language models with symbolic reasoning capabilities.
Synalinks的Claude技能
Key features
- Neuro-symbolic AI integration
- Claude skill implementations
- Python-based development
- Open-source project support
- Large language model enhancements
Use cases
- Extending Claude's capabilities with symbolic reasoning
- Neuro-symbolic AI research and development
- Open-source AI tool integration
- LLM enhancement projects
- AI skill library development
README excerpt
# Claude Skills for Synalinks --- This repository contains skills to use with Claude Code. ## What Are Claude Skills? Claude Skills are customizable workflows that teach Claude how to perform specific tasks according to your unique requirements. Skills enable Claude to execute tasks in a repeatable, standardized manner across all Claude platforms. ## What is the goal of Synalinks skills? The goal of Synalinks skills is to teach Claude to use the Synalinks framework correctly. Synalinks is Keras-inspired, so without guidance LMs tend to mix Keras / LangChain / DSPy syntax — producing plausible-looking but broken code. These skills constrain Claude to idiomatic Synalinks usage. ## The 11 Skills Each skill targets one slice of the framework. Claude auto-activates the relevant skill(s) based on what you're asking about. | Skill | When it activates | |-------|-------------------| | **synalinks-core** | DataModel, Field, Input, JSON operators (`+ & \| ^ ~`), `synalinks.ops`, configuration, LanguageModel/EmbeddingModel basics | | **synalinks-programs** | Program class, four building APIs (Functional / Sequential / Subclassing / Mixed), multi-input/output graphs, build/call lifecycle, save/load, `summary`, `get_module`, `plot_program`, custom serialization | | **synalinks-modules** | Generator, ChainOfThought, SelfCritique, Identity, PythonSynthesis, SequentialPlanSynthesis, custom modules via subclassing | | **synalinks-control-flow** | Decision, Branch, parallel branches, self-consistency, XOR input/output guards, And/Or modules, branch merging | | **synalinks-agents** | FunctionCallingAgent, ToolCalling, Tool definitions, MCP integration (MultiServerMCPClient), trajectories | | **synalinks-knowledge** | KnowledgeBase (DuckDB), EmbedKnowledge, UpdateKnowledge, Retrie