← all repositories
SynaLinks/synalinks-skills

Teaching Claude to stop writing Keras when you asked for Synalinks

Eleven Claude Skills that keep an LLM coding assistant from hallucinating the wrong framework syntax into your neuro-symbolic project.

synalinks-skills
Velocity · 7d
+0.8
★ / day
Trend
steady
star history

What it does

This repo ships 11 “Claude Skills” — structured prompt bundles that slot into Claude Code, Claude Desktop, or the web UI. Each skill covers one slice of the Synalinks framework (core data models, program graphs, agents, training loops, optimizers, etc.). Claude auto-activates the relevant skill based on what you’re asking about, so it supposedly stops generating plausible-looking but broken mashups of Keras, LangChain, and DSPy syntax.

The interesting bit

The real value isn’t the prompts themselves; it’s the recognition that framework-specific LLM assistance decays fast without guardrails. Synalinks is deliberately Keras-inspired, which turns out to be a trap — the surface similarity makes LLMs confident and wrong. These skills are essentially a syntax firewall with 11 narrow gates.

Key highlights

  • 11 scoped skills from synalinks-core (JSON operators, DataModel basics) to synalinks-datasets (built-in benchmarks, visualization helpers)
  • synalinks-control-flow covers unusual neuro-symbolic primitives: XOR guards, branch merging, self-consistency voting
  • synalinks-optimizers includes quality-diversity methods (OMEGA, Dominated Novelty Search) — not your usual Adam/SGD territory
  • synalinks-knowledge has DuckDB-backed RAG/KAG with hybrid search and entity/relation graphs
  • Each skill bundles SKILL.md (scannable guide), references/ (deep docs), and scripts/ (runnable examples)
  • Install via copy, symlink, or .skill zip archive depending on your Claude flavor

Caveats

  • The README notes Claude “auto-activates” skills based on SKILL.md frontmatter, but doesn’t explain how reliably this works in practice or what happens with ambiguous queries spanning multiple skills
  • No benchmarks or user feedback on whether the skills actually reduce hallucination rates — the claim is plausible but unverified in the sources

Verdict

Worth a look if you’re actively building with Synalinks and tired of debugging LLM-generated framework soup. Skip it if you aren’t using Synalinks; the skills are tightly coupled to its specific APIs and won’t transfer.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.