Results for “invariant-labs”

Analyzes type design for encapsulation, invariant expression, usefulness, and enforcement, providing scores and improvement suggestions.

Define owned inductive invariants and enforce them at parse, construct, API, DB, lock, or transaction boundaries, with counterexample-driven verification.

Test vector stores for embedding inversion, cross-tenant leakage, and poisoning.

Use `analysis-agent` to identify domain ownership, invariants, state transitions, and cross-context effects when rules change or ownership is unclear. Skip presentation-only or question-only work with no domain behavior.

KV cache compression for LLM inference — 4.4x compression, 2x context capacity, near-lossless quality. ICLR 2026 paper implementation with vLLM integration.

Stores immutable data on-chain using IQ Labs tech stack including IQDB, hanLock, and x402.

Conduct a design interview, generate 5 distinct UI variations in a temporary route, collect real click-to-comment feedback on the live rendered variants via human-review, and produce an implementation plan. Use when the user wants to explore UI design options, redesign an existing component/page, or create new UI with multiple genuinely different approaches to compare — before writing production code or committing to a direction. For a lighter, single-component variant picker with no interview, use `prototype` instead. For reviewing a UI that's already real (not exploring new directions), use `visual-review`. Source: adapted from github.com/0xdesign/design-plugin's design-lab skill (interview + 5-variant structure), with feedback collection replaced by this repo's own `visual-review` skill (human-review) instead of a bespoke overlay component.

Ingests case studies, past proposals, and boilerplate from library/inbox into structured indexes. Use when the user requests to 'index proposal library', 're-index case studies', 'ingest inbox docs', or 'validate library'.

proptest — property-based testing for Rust (Hypothesis-style). Generates thousands of random inputs to find counterexamples to invariants, with shrinking to minimal failing case. Critical for crypto, parsers, state machines, and finance code where edge cases matter. Includes strategies (gen functions), regression tracking, and integration with cargo test. Alternative: quickcheck (simpler API, less powerful). USE WHEN: user mentions "proptest", "property-based test", "proptest!", "Strategy", "Arbitrary", "shrink", "quickcheck", "regression file", "fuzz-light", "proptest-derive" DO NOT USE FOR: Generic Rust unit tests - use `testing/rust-testing` DO NOT USE FOR: Fuzzing with mutator (cargo-fuzz, AFL) - use bitcoin/testing/fuzz DO NOT USE FOR: KMP property testing - use `testing/kotest` (has built-in property)

Human-in-the-loop web studio to tune AI-generated output by eye. Stand up a local interactive studio (sliders, pickers, drag handles) or an inline edit/highlight/comment annotation studio for prose & media, instead of guessing values or shipping a static comparison grid.

Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.

Expert en inference llama.cpp avancé (GGUF, quantization, local models, HTTP server, hardware)

Spiral inductors, interdigital capacitors, baluns, resonators, phase shifters for impedance matching, DC blocking, and bias tees. TRIGGER: user asks to design or create a spiral inductor, interdigital capacitor, balun, resonator, phase shifter, or other passive RF component. Invoke BEFORE writing code — class names and property patterns are non-obvious. SKIP: filter design (use matlab-design-pcb-filter), coupler/splitter design (use matlab-design-pcb-coupler), transmission line design (use matlab-design-pcb-transmission-line), EM analysis (use matlab-analyze-em), material setup only (use matlab-manage-pcb-material).

Design and validate digital filters in MATLAB. Use when cleaning up noisy signals, removing interference, filtering signals, designing FIR/IIR filters (lowpass/highpass/bandpass/bandstop/notch), or comparing filters in Filter Analyzer.

Builds an interactive in-browser studio for tuning visual parameters (sliders, pickers, drag handles) or editing/annotating text and media, enabling real-time human-in-the-loop refinement instead of static comparisons or chat-based feedback.

Agent validation v4.3.0 — Make agents act effectively by disabling harmful actions, lowering gates, and injecting cross-run learning

SNLI-VE: Visual Entailment Dataset

Agent Vault — fetching secrets from Infisical at runtime

A complete tour of the intelli-verse-x 5-layer stack — Leantime/GitHub at the top, Beads/Bernstein/Claude-Squad in the middle, Gas Town as the multi-project fabric, and LiteLLM/Infisical/Langfuse/n8n/GH-Actions underneath. Use whenever the user asks "what does X service do", "where does Y data live", "how do I get to Z", or you need to understand which tool to reach for. This is the architecture map.

Defines a design system for ElevenLabs with colors, typography, layout, and component tokens for building brand-consistent interfaces.

Agent validation overhaul: reward weight overrides, fitness decline gate, pinned data, staged experiments

实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

Transform any voice into a different voice while preserving speech content and emotion using the inference.sh CLI and ElevenLabs models.

Hard Negative Mixing for Contrastive Learning

Design lean validation experiments — hypothesis, method, success criteria, sample size, timeline, and decision rules

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

Claim-driven 实验设计：界定目标 claims → 设计实验块（baseline/validation/ablation/robustness）→ 构建执行顺序 → 可选 Review LLM review → 写入 wiki

Plataforma de laboratório em nuvem para testes e validação automatizados de proteínas. Use ao projetar proteínas e precisar de validação experimental incluindo ensaios de ligação, testes de expressão, medições de estabilidade térmica, ensaios de atividade enzimática ou otimização de sequências de proteínas. Use também para submeter experimentos via API, rastrear status de experimentos, baixar resultados, otimizar sequências de proteínas para melhor expressão usando ferramentas computacionais (NetSolP, SoluProt, SolubleMPNN, ESM), ou gerenciar workflows de design de proteínas com validação em laboratório úmido.

Predict biomolecular complexes with Chai-1, an open AlphaFold3-style model that folds multi-entity assemblies (proteins, ligands, nucleic acids) from a single typed FASTA — strong on antibody–antigen and protein–ligand complexes, with optional MSA and restraint inputs. Use when predicting an antibody–antigen complex, folding a mixed protein/ligand/nucleic-acid assembly described in one FASTA, or generating a complex with experimental restraints. For binding-affinity prediction or a ligand-focused co-fold prefer alterlab-boltz; for protein-only or protein–protein folding prefer alterlab-alphafold; to dock into a fixed receptor prefer alterlab-diffdock. Part of the AlterLab Academic Skills suite.

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

VS-Enhanced Qualitative Design Consultant with Ethnography & Action Research Enhanced VS 3-Phase process: Avoids overused phenomenology, proposes context-optimal qualitative strategies Absorbed H1 (Ethnographic Research Advisor) and H2 (Action Research Facilitator) capabilities Use when: selecting qualitative research design, planning phenomenology/grounded theory/case study/ethnography/action research Triggers: phenomenology, 현상학, grounded theory, 근거이론, case study, 사례연구, narrative inquiry, ethnography, 민족지, action research, 실행연구, qualitative design

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

Applies medicinal-chemistry filters with the medchem library — drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, and molecular complexity metrics for compound prioritization and library cleanup. Use when filtering or triaging a compound library, flagging PAINS or reactive groups, or assessing drug-likeness of candidate molecules. Part of the AlterLab Academic Skills suite.

Type design analysis — encapsulation, invariant expression, usefulness, and enforcement.