Individual skill
synalinks
Use for anything involving the Synalinks neuro-symbolic LM framework (Keras-inspired): DataModel/Field/Input, JSON operators (+ & | ^ ~), synalinks.ops; LanguageModel/EmbeddingModel and provider prefixes; DecisionModel (TypeSafe jev decision models, decision_model=, min_confidence/threshold); the Program class and its four APIs, save/load; modules (Generator, ChainOfThought, SelfCritique, PythonSynthesis, custom Module); control flow (Decision, MultiDecision, Branch, And/Or/Xor, guards); agents (FunctionCallingAgent, RLM, DeepAgent, Tool, MCP); KnowledgeBase/RAG; training (compile/fit/evaluate/predict, callbacks, KerasTuner tuners); rewards (ExactMatch, CosineSimilarity, LMAsJudge, ProgramAsJudge, RubricsAsJudge and presets like Faithfulness/Toxicity, AgentAsJudge, DeepAgentAsJudge, RLMAsJudge, ComposableReward, BatchReward) and metrics; optimizers (RandomFewShot, OMEGA); datasets, visualization. Synalinks is Keras-shaped: without guidance LMs mix Keras/LangChain/DSPy syntax.
skills/synalinks/SKILL.md
Source commit 092970a578e53590f3b87597887952a4cfa98a4e
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 10, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 909
- Repository last updated
- Sep 28, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- artificial-intelligence Repository topic
- large-language-models Repository topic
- neuro-symbolic Repository topic
- neurosymbolic Repository topic
- neuro-symbolic-ai Repository topic
- data Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 19,456 bytesSKILL.mdcore · 19,456 bytesreferences/agents-tools.mddoc · 16,479 bytesreferences/api-reference.mddoc · 12,584 bytesreferences/chain_of_thought.logasset · 8,732 bytesreferences/conditional_branches.logasset · 33,051 bytesreferences/control-flow.mddoc · 10,199 bytesreferences/custom_dataset.logasset · 477 bytesreferences/custom_module.logasset · 36,856 bytesreferences/custom_reward.logasset · 10,005 bytesreferences/data-models.mddoc · 6,985 bytesreferences/decision-models.mddoc · 9,632 bytesreferences/deep_agent.logasset · 112,142 bytesreferences/four_apis.logasset · 13,747 bytesreferences/guard_patterns.logasset · 54,751 bytesreferences/knowledge-base.mddoc · 10,105 bytesreferences/lmstudio_setup.logasset · 24 bytesreferences/modules-catalog.mddoc · 14,714 bytesreferences/omega_example.logasset · 1,572 bytesreferences/optimizers.mddoc · 6,984 bytesreferences/programs.mddoc · 10,421 bytesreferences/rag_example.logasset · 281,844 bytesreferences/rewards-metrics.mddoc · 16,629 bytesreferences/rlm_agent.logasset · 53,560 bytesreferences/simple_qa.logasset · 3,136 bytesreferences/subclassing_modules.logasset · 3,448 bytesreferences/tool_agent.logasset · 117,971 bytesreferences/training-guide.mddoc · 18,229 bytesreferences/training_example.logasset · 2,184 bytesreferences/visualization.logasset · 2,650 bytesscripts/chain_of_thought.pyruns · 1,500 bytesscripts/conditional_branches.pyruns · 2,493 bytesscripts/custom_dataset.pyruns · 4,400 bytesscripts/custom_module.pyruns · 5,084 bytesscripts/custom_reward.pyruns · 2,533 bytesscripts/decision_model.pyruns · 4,173 bytesscripts/deep_agent.pyruns · 2,332 bytesscripts/four_apis.pyruns · 5,493 bytesscripts/guard_patterns.pyruns · 6,775 bytesscripts/lmstudio_setup.pyruns · 3,168 bytesscripts/omega_example.pyruns · 3,812 bytesscripts/rag_example.pyruns · 2,577 bytesscripts/rlm_agent.pyruns · 1,784 bytesscripts/simple_qa.pyruns · 1,509 bytesscripts/subclassing_modules.pyruns · 5,470 bytesscripts/tool_agent.pyruns · 4,089 bytesscripts/training_example.pyruns · 3,877 bytesscripts/visualization.pyruns · 2,499 bytes
Read excerpt
# Synalinks
Synalinks is an open-source, Keras-inspired framework for building neuro-symbolic
LM applications (RAGs, agents, self-evolving reasoning) with in-context
reinforcement learning. This skill is the single entry point: each section below
is a scannable overview that points to a **runnable script + its captured run log**
and a **deep-dive reference doc** under `references/`.
## Core abstractions
- **DataModel** — Pydantic-style schema for structured I/O (replaces tensors).
- **Module** — async computational unit processing JSON data (replaces layers).
- **Program** — DAG of modules with conditional logic (replaces models).
- **Reward / Optimizer** — guide training by *maximizing reward* (no gradients;