Real Skill packageSource verifiedClawHub registry

Liquid Neural Networks (LNN)

Build, train, and inspect Liquid Neural Networks (LNNs) — liquid time-constant (LTC) and closed-form continuous-time (CfC) networks with Neural Circuit Policy (NCP) sparse wirings, using the ncps library on PyTorch. Activate when the user asks to build/train a liquid neural network, LNN, LTC, CfC, o

Identity and source

Publisher attributionpromiseyukiregistry owner unverified by skillvetai
Functional categoryEnterprise Functionsautomatically inferred · 56% rule confidence
Package forminstruction with code9 recorded files
Canonical sourceClawHub registryclawhub:promiseyuki:lnn
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/30/2026.claude/skills/liquid-neural-network

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/30/2026.agents/skills/liquid-neural-network

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/30/2026skills/liquid-neural-network

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @promiseyuki/lnn
clawhub inspect @promiseyuki/lnn --version 1.0.0

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
9 / 9 inspected as text
Checked
8/30/2026, 4:44:55 PM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highDynamic code or shell execution is presentscripts/train_lnn.py:243 · confidence 78%eval(
1 High/Critical review queue entry
STATIC_DYNAMIC_CODE_EXECUTIONpending
Open human review queue →
2 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
7 dependency and API indicators
  • pypi: ncps >=1.0.1
  • pypi: torch >=2.0.0
  • pypi: numpy >=1.24.0
  • pypi: pandas >=2.0.0
  • pypi: matplotlib >=3.7.0
  • api: clawhub.ai
  • api: ncps.readthedocs.io
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/30/2026, 6:03:08 AM
Release binding
Matches this record
  • vt: clean
  • skillspector: clean
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:0645250a7d1975110242df8096762c824ad01a9742495b022906b4d53fd8ce2c
Show up to 9 recorded paths
  • LICENSE
  • README.md
  • references/api_cheatsheet.md
  • references/lnn_theory.md
  • scripts/inspect_wiring.py
  • scripts/requirements.txt
  • scripts/train_lnn.py
  • skill-card.md
  • SKILL.md

Source changelog

liquid-neural-network Skill v1.0.0 – initial release - Build, train, and inspect Liquid Neural Networks (LNNs), including liquid time-constant (LTC) and closed-form continuous-time (CfC) models with NCP wiring via the ncps library on PyTorch. - Provides `scripts/train_lnn.py` for training on synthetic or CSV time-series data, with options for network type, wiring, and model saving. - Includes support for neural circuit policy (NCP) sparse wirings, model theory and API references. - Activation triggers on user requests for LNN, LTC, CfC, or NCP models; continuous-time or ODE-based sequence modeling; or fitting robust recurrent models for time-series prediction. - Offers quick-start commands, environment setup guidance, and details on outputs and usage scenarios.