All authors
Claude Skills by VectorSpaceLab
github.com/VectorSpaceLab6,028 skills74 installs15,373 views
- Bridge Recovery HarnessRun a bounded BridgeStan score-model proxy recovery that invokes generated module scripts, logs command evidence, and writes validator-ready recovery artifacts.Votes: 0GitHub stars: 247
- Parameter Transform AdapterApply scalar Stan-style constrained and unconstrained transforms with support checks and log-Jacobian values for bounded real parameters.Votes: 0GitHub stars: 247
- Score Function EvaluatorEvaluate log density, gradient, Hessian, and finite-difference checks for a Bernoulli-Beta Stan score-model proxy in unconstrained coordinates.Votes: 0GitHub stars: 247
- Stan Model ContractExtract a structured contract from simple Stan programs so score-model workflows can identify data, constrained parameters, transforms, model terms, and generated quantities.Votes: 0GitHub stars: 247
- Diffusion DesignSelect and validate scalar diffusion factors for robust or heavy-tailed minimum Stein discrepancy estimators.Votes: 0GitHub stars: 247
- Minimum Sd OptimizerMinimise empirical Stein discrepancy objectives with bounded searches and auditable loss traces for recovery experiments.Votes: 0GitHub stars: 247
- Msd Recovery ProtocolAssemble executable soft-mode recovery evidence for Minimum Stein Discrepancy Estimator proxy experiments.Votes: 0GitHub stars: 247
- Stein Kernel LossCompute one-dimensional kernel Stein and diffusion kernel Stein losses for unnormalized model recovery experiments.Votes: 0GitHub stars: 247
- Particle Mirror Descent Density MetricsUse this skill to score Particle Mirror Descent density approximations against reduced posterior targets with total variation, cross entropy, and symmetric mode coverage diagnostics.Votes: 0GitHub stars: 247
- Particle Mirror Descent Kde UpdateUse this skill to run the weighted kernel-density Particle Mirror Descent prox update loop with stochastic likelihood factors, normalized weights, Gaussian kernels, and trace logging.Votes: 0GitHub stars: 247
- Particle Mirror Descent Mixture ProtocolUse this skill to construct the synthetic tied Gaussian mixture posterior target from the Particle Mirror Descent paper, including data generation, log prior/likelihood functions, and grid posterior evaluation.Votes: 0GitHub stars: 247
- Particle Mirror Descent Recovery HarnessUse this skill to compose PMD mixture protocol, KDE update, and density metrics modules into an executable bounded soft-mode recovery experiment with auditable evidence.Votes: 0GitHub stars: 247
- Benchmark Recovery HarnessAssemble executable posteriordb reduced benchmark recovery runs with provenance, metric, and mechanism evidence.Votes: 0GitHub stars: 247
- Posterior Accuracy MetricsCompute posterior moment accuracy metrics for approximate draws against reference posterior summaries.Votes: 0GitHub stars: 247
- Posterior Object ContractsValidate and normalize posteriordb posterior, model, data, and reference object contracts for benchmarking workflows.Votes: 0GitHub stars: 247
- Reference Summary ChecksLoad posteriordb reference posterior summaries and validate numeric quality fields for benchmark targets.Votes: 0GitHub stars: 247
- Gaussian Mixture RecoveryRun a bounded 1D Gaussian-mixture KSD-U recovery experiment for the Kernelized Stein Discrepancy paper.Votes: 0GitHub stars: 247
- Ksd Bootstrap GofCalibrate a KSD U-statistic goodness-of-fit test with the centered multinomial bootstrap for degenerate U-statistics.Votes: 0GitHub stars: 247
- Stein Kernel ScoringCompute Kernelized Stein Discrepancy pairwise Stein kernels and U/V-statistic estimates from samples, model scores, and an RBF kernel.Votes: 0GitHub stars: 247
- Iterate Averaging McseGenerated robust stochastic VI module skill for arXiv 2009.00666 recovery.Votes: 0GitHub stars: 247
- Recovery Diagnostics HarnessGenerated robust stochastic VI module skill for arXiv 2009.00666 recovery.Votes: 0GitHub stars: 247
- Rhat StationarityGenerated robust stochastic VI module skill for arXiv 2009.00666 recovery.Votes: 0GitHub stars: 247
- Stochastic Vi ChainRun bounded constant-step noisy stochastic optimization chains that model stochastic VI iterates as a Markov process around an optimum.Votes: 0GitHub stars: 247
- Aevb Vae CoreRun a compact AEVB/VAE training step with encoder statistics, reparameterization, decoder reconstruction, analytic KL, and optimizer evidence.Votes: 0GitHub stars: 247
- Vae Image Proxy BatchCreate deterministic tiny image batches for bounded VAE/AEVB recovery experiments when full image datasets are unavailable or too expensive.Votes: 0GitHub stars: 247
- Vae Recovery EvaluationConvert VAE/AEVB proxy training traces into auditable recovery_result.json artifacts with target matching and mechanism checks.Votes: 0GitHub stars: 247
- Cot Answer ExtractionExtract and normalize final answers from chain-of-thought outputs without scoring intermediate reasoning text.Votes: 0GitHub stars: 247
- Cot Equation CalculatorSafely check and repair simple arithmetic equations inside chain-of-thought reasoning traces.Votes: 0GitHub stars: 247
- Cot Prompt TemplatesBuild standard, chain-of-thought, and ablation few-shot prompts with auditable prompt structure metadata.Votes: 0GitHub stars: 247
- Cot Recovery HarnessRun a bounded standard-versus-chain-of-thought proxy recovery experiment and emit auditable recovery artifacts.Votes: 0GitHub stars: 247
- Binary Nce EstimatorCompute binary conditional NCE objectives and diagnose self-normalization failures in finite protocols.Votes: 0GitHub stars: 247
- Conditional Nce ProtocolBuild finite conditional NCE protocols with noise distributions, adjusted scores, and paper counterexample fixtures.Votes: 0GitHub stars: 247
- Nce Recovery EvaluationEvaluate conditional NCE recovery with ratio errors, KL metrics, and explicit mechanism checks for proxy runs.Votes: 0GitHub stars: 247
- Ranking Nce EstimatorOptimize finite ranking NCE objectives and recover conditional distributions when partition functions vary by input.Votes: 0GitHub stars: 247
- Deberta Disentangled AttentionCompute and test DeBERTa style disentangled relative attention terms for bounded recovery experiments without relying on the original repository.Votes: 0GitHub stars: 247
- Deberta Enhanced Mask DecoderApply DeBERTa enhanced mask decoder scoring that injects absolute position evidence only at candidate decoding time.Votes: 0GitHub stars: 247
- Deberta Race Multiple Choice ProtocolBuild and evaluate RACE style multiple choice candidate records for DeBERTa recovery experiments.Votes: 0GitHub stars: 247
- Deberta Recovery Experiment HarnessOrchestrate a source boundary clean DeBERTa reduced recovery harness that records executable evidence and mechanism checks.Votes: 0GitHub stars: 247
- Deberta Sift FinetuningRun deterministic SiFT style normalized perturbation and optimizer traces for DeBERTa reduced recovery evidence.Votes: 0GitHub stars: 247
- Gsm8k Answer ToolsExtract GSM8K final answers, validate calculator annotations, and label candidate solutions by answer correctness.Votes: 0GitHub stars: 247
- Gsm8k Candidate GenerationBuild diverse GSM8K candidate solution records and label them by final-answer agreement for verifier training.Votes: 0GitHub stars: 247
- Gsm8k Recovery EvaluationRun a bounded GSM8K verifier recovery harness with source provenance, generated-skill invocation logs, and solve-rate metrics.Votes: 0GitHub stars: 247
- Gsm8k Verifier SearchSelect GSM8K answers by ranking verifier-scored candidate solutions or voting among top-ranked answers.Votes: 0GitHub stars: 247
- Gsm8k Verifier TrainingTrain a deterministic lightweight verifier on correctness-labeled GSM8K candidate solutions and record loss traces.Votes: 0GitHub stars: 247
- Conditional Nce TrainingTrain a tiny residual sequence-energy model with the paper's conditional NCE objective on positive and fixed-LM negative continuations.Votes: 0GitHub stars: 247
- Importance Sampling GenerationEstimate residual EBM partition terms and select text continuations by importance reweighting fixed-LM proposal samples.Votes: 0GitHub stars: 247
- Reduced Recovery ProtocolBuild and validate soft-mode reduced recovery artifacts for residual EBM text generation without reading the original repository.Votes: 0GitHub stars: 247
- Residual Joint ModelCompute residual EBM sequence scores and normalized importance weights from fixed LM proposal log probabilities and scalar energies.Votes: 0GitHub stars: 247
- Direct Rlaif RewardingCompute direct-RLAIF rewards from one-to-ten score-token logits without training a separate reward model.Votes: 0GitHub stars: 247
- Reinforce Policy UpdateRun a bounded REINFORCE-style policy update with terminal RLAIF rewards, a value baseline, and KL regularization evidence.Votes: 0GitHub stars: 247