LLM & Model APIs AI agent skills & MCP servers

100 m5-onboard SkillLLM & Model APIs
End-to-end onboarding for a freshly-plugged-in M5Stack ESP32 device (Cardputer, Cardputer-Adv, Core, CoreS3, Stick) — detect on USB, flash UIFlow 2.0 firmware, and install the Clau

100 agentic-engineering SkillLLM & Model APIs
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

100 foundation-models-on-device SkillLLM & Model APIs
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.

100 few-shot-example-gen SkillLLM & Model APIs
Few-shot example generation and optimization for improved LLM performance

100 huggingface-classifier SkillLLM & Model APIs
Hugging Face transformer model fine-tuning and inference for intent classification

100 llm-classifier SkillLLM & Model APIs
LLM-based zero-shot and few-shot classification for flexible intent detection

100 opentelemetry-llm SkillLLM & Model APIs
OpenTelemetry instrumentation for LLM applications with distributed tracing

100 spacy-ner SkillLLM & Model APIs
spaCy NER model training and entity extraction for conversational AI

100 flow-network-builder SkillLLM & Model APIs
Model optimization problems as network flow problems

100 BI Semantic Layer Generator SkillLLM & Model APIs
Generates semantic layer definitions for BI tools from dimensional models

100 Dimensional Model Validator SkillLLM & Model APIs
Validates dimensional models against Kimball methodology best practices

100 aeja-robustness SkillLLM & Model APIs
Use when an American Economic Journal: Applied Economics (AEJ: Applied) manuscript's headline estimate must be shown to survive specification, sample, and inference choices before

100 aejmac-literature-positioning SkillLLM & Model APIs
Use when the contribution of an American Economic Journal: Macroeconomics (AEJ: Macro) manuscript relative to the macro frontier is fuzzy, contested, or undersold. Frames the margi

100 aejmac-robustness SkillLLM & Model APIs
Use when the headline result of an American Economic Journal: Macroeconomics (AEJ: Macro) manuscript must be shown stable across specification, sample, identification, and tuning c

100 aejmac-tables-figures SkillLLM & Model APIs
Use when building or revising exhibits for an American Economic Journal: Macroeconomics (AEJ: Macro) manuscript — impulse-response figures, fan charts, model-fit overlays, and regr

100 aejmic-robustness SkillLLM & Model APIs
Use when extensions, edge cases, or applied robustness checks are missing for an American Economic Journal: Microeconomics (AEJ: Micro) manuscript — covering theory extensions (rel

100 aejmic-tables-figures SkillLLM & Model APIs
Use when presenting results for an American Economic Journal: Microeconomics (AEJ: Micro) manuscript — propositions, numerical examples, schematic theory figures, and empirical/exp

100 atc-review-process SkillLLM & Model APIs
Use when reasoning about how an ATC (ACM SIGOPS Annual Technical Conference, formerly USENIX ATC) submission is evaluated — the two-round extended-abstract model, the round-one gat

100 amj-tables-figures SkillLLM & Model APIs
Use when building or cleaning the tables and figures for an Academy of Management Journal (AMJ) manuscript — correlation tables, regression/SEM/HLM result tables, the theoretical-m

100 amr-tables-figures SkillLLM & Model APIs
Use when building the conceptual exhibits of an Academy of Management Review (AMR) manuscript — process models, 2x2 typologies, multi-level frameworks, and propositions tables that

100 agsy-data-and-model-evaluation SkillLLM & Model APIs
Use when evaluating the model and analyzing results for an Agricultural Systems (AgSy) manuscript so it survives expert systems review — independent model evaluation (observed vs.

100 agsy-figures-and-tables SkillLLM & Model APIs
Use when building figures and tables for an Agricultural Systems (AgSy) manuscript so exhibits communicate interactions, dynamics, trade-offs, and model performance clearly. AgSy i

100 amanthro-data-analysis SkillLLM & Model APIs
Use when executing and reporting the analysis/interpretation for an American Anthropologist (AA) manuscript so it survives expert anonymous review — disciplined ethnographic/qualit

100 aria SkillLLM & Model APIs
Designs the data model, API contracts, and structural foundation of the system.

100 ai-inference-service-mesh SkillLLM & Model APIs
Use verified service mesh patterns for AI inference traffic management, mTLS,

100 ai-sre-incident-response SkillLLM & Model APIs
Build AI-focused SRE incident response practices for LLM outages, degraded

100 ai-wrapper-product SkillLLM & Model APIs
Expert in building products that wrap AI APIs (OpenAI, Anthropic,

100 atlas-cloud-media SkillLLM & Model APIs
Generate Atlas Cloud images and videos through its asynchronous media API with schema-first model selection and credential-safe polling.

100 cassette-model SkillLLM & Model APIs
Show or change the Cassette editing model and thinking level for the current media session. Invoke only when the user explicitly asks for the model picker, wants to inspect the cur

100 goal-convergence SkillLLM & Model APIs
Goal-oriented autonomous loop with external completion oracle. Keeps iterating until verifiable stopping conditions are met, checked by a separate model.

100 nanoclaw-repl SkillLLM & Model APIs
Operate and extend NanoClaw v2, ECC's zero-dependency session-aware REPL built on claude -p.

100 regex-vs-llm-structured-text SkillLLM & Model APIs
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.

97 convex-explain-app SkillLLM & Model APIs
Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function

95 projection-patterns SkillLLM & Model APIs
Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.

94 Apache Kafka Schema Extractor SkillLLM & Model APIs
Extracts and transforms Avro, Protobuf, and JSON Schema definitions from Confluent Schema Registry. Generates typed data models and validates schema compatibility using the Schema

94 gemini-vision SkillLLM & Model APIs
Analyze images using Google Gemini 2.0 Flash with proxy support, retry logic, and mock mode.

94 ai-inference-service-mesh SkillLLM & Model APIs
Use service mesh patterns for AI inference traffic management, mTLS,

94 ai-sre-incident-response SkillLLM & Model APIs
Build AI-focused SRE incident response practices for LLM outages, degraded

94 aria SkillLLM & Model APIs
Designs the data model, API contracts, and structural foundation of the system.

93 training-and-inference SkillLLM & Model APIs
Routes training, fine-tuning, validation, checkpoint, and

93 big-model-inference SkillLLM & Model APIs
Use Accelerate big-model inference utilities for meta

93 policy-training SkillLLM & Model APIs
Routes ACT, CNNMLP, Diffusion Policy, and latent-model training or

93 adelai-det SkillLLM & Model APIs
Routes AdelaiDet users through legacy-compatible setup, model

93 estimators-and-models SkillLLM & Model APIs
Choose and configure ART estimator wrappers for sklearn, PyTorch,

93 model-based-rl SkillLLM & Model APIs
Guides AI-Optimizer model-based RL baselines, world-model

93 aimet SkillLLM & Model APIs
Route AIMET install, PyTorch/ONNX quantization, GenAILab, model

93 genai-lab SkillLLM & Model APIs
Run and configure AIMET GenAILab LLM/VLM quantization scorecards

93 torch-quantization SkillLLM & Model APIs
Use AIMET Torch for model preparation, QuantizationSimModel

93 interpretable-models SkillLLM & Model APIs
Choose and operate AIX360's directly interpretable models, rule

93 remote-reward-models SkillLLM & Model APIs
Operate Align-Anything remote reward servers, payload checks, and

93 alpamayo-r1 SkillLLM & Model APIs
Router for Alpamayo R1 multimodal driving inference and trajectory sampling.

93 inference SkillLLM & Model APIs
End-to-end Alpamayo R1 multimodal driving inference, sample

93 alpha-gpt SkillLLM & Model APIs
Route AlphaGPT data ingestion, factor mining, live strategy, and

93 model-config-and-api SkillLLM & Model APIs
Inspect and modify AlphaFold model presets, RunModel

93 core-model SkillLLM & Model APIs
Guide construction and execution of the verified Alphafold2

93 embeddings SkillLLM & Model APIs
Guides ESM, MSA Transformer, ProtTrans/ProtBERT, and precomputed

93 model-inference SkillLLM & Model APIs
Construct bounded AlphaFold 3 models, choose forward loss or

93 anomalib SkillLLM & Model APIs
Use anomalib for anomaly-detection install, data/model selection,

93 data-and-models SkillLLM & Model APIs
Data modules, datasets, dataclasses, model registry, constructors,

93 anylabeling SkillLLM & Model APIs
Operate AnyLabeling desktop annotation, auto-labeling model,

93 auto-labeling-models SkillLLM & Model APIs
Operate AnyLabeling model-backed auto-labeling: catalogs, custom

93 services-cli-operations SkillLLM & Model APIs
Operate AReaL 2.0 service CLIs, service lifecycles, model

93 acoustic-models SkillLLM & Model APIs
Route ASRT acoustic model work for Keras/CTC training, evaluation,

93 language-model SkillLLM & Model APIs
Route ASRT pinyin sequences through its statistical

93 conditioning SkillLLM & Model APIs
Use diffusion wrapper models conditioned on lower-rate waveforms,

93 cli-and-model-registry SkillLLM & Model APIs
Guides Autodistill CLI runs, model registry inspection, plugin

93 ontologies-and-model-interfaces SkillLLM & Model APIs
Guides custom Autodistill ontologies, base/target model

92 general-knowledge-reasoning SkillLLM & Model APIs
Apply general knowledge reasoning across diverse domains — trivia, commonsense inference, analogy, and factual question answering.

92 visual-pattern-induction SkillLLM & Model APIs
Induce visual patterns from examples — few-shot visual reasoning, grid-based pattern recognition, and ARC-style inductive inference.

92 bubble-tea-scaffolder SkillLLM & Model APIs
Generate Bubble Tea (Go) TUI application structure with models, commands, and views using the Elm architecture.

92 domain-model-extractor SkillLLM & Model APIs
Extract domain models from monolithic codebases using DDD principles for microservices decomposition

92 openapi-generator SkillLLM & Model APIs
Generate OpenAPI specifications from code or legacy APIs with schema inference and documentation

92 vision-extraction SkillLLM & Model APIs
Extract structured data from images and documents using vision models — OCR, layout analysis, table extraction, and visual document parsing.

92 validating-ai-ethics-and-fairness SkillLLM & Model APIs
Validate AI/ML models and datasets for bias, fairness, and ethical concerns.

92 cost-aware-llm-pipeline SkillLLM & Model APIs

92 cross-model-review SkillLLM & Model APIs

91 kb-arbitration-difc-lcia-sboghossian SkillLLM & Model APIs
Use when dealing with arbitration clauses or proceedings under the former DIFC-LCIA Arbitration Centre, which operated from 2008 until its dissolution under Dubai Decree 34/2021. C

91 add-top-openrouter-models SkillLLM & Model APIs
Sync OpenRouter models used by OpenClaw into this installation's config. Fetches the OpenClaw app leaderboard from OpenRouter, verifies model IDs against the API catalog, and adds

91 chip-seq-read-alignment-filtering SkillLLM & Model APIs
Use when when beginning peak calling on ChIP-Seq data: you have raw single-end or paired-end BED/BEDPE alignment files for both ChIP and control samples and need to remove duplicat

91 cross-modality-embedding-integration SkillLLM & Model APIs
Use when you have paired scATAC-seq peak matrices and scRNA-seq gene expression matrices from the same cells (multiome data) and need to perform joint clustering, visualization, or

91 large-scale-single-cell-matrix-loading SkillLLM & Model APIs
Use when you have a single-cell count matrix with 10 million or more cells that must be processed through dimension reduction, clustering, or integration pipelines. Use it specific

91 local-background-estimation-multiple-scales SkillLLM & Model APIs
Use when when performing ChIP-Seq peak calling with MACS3, after duplicate filtering and fragment length prediction (d), to construct the background model that will be compared aga

91 monocle3-trajectory-embedding SkillLLM & Model APIs
Use when you have an ArchR project object with dimensionality reduction results (LSI or combined dimensions from scATAC-seq ± scRNA-seq) and want to infer pseudotime trajectories a

91 multiome-data-ingestion-paired-modalities SkillLLM & Model APIs
Use when you have independently generated or received both scATAC-seq peak count matrices and scRNA-seq gene expression matrices from the same set of cells (multiome experiment), a

91 single-cell-atac-fragment-import-processing SkillLLM & Model APIs
Use when you have aligned single-cell ATAC-seq data as BAM files or fragment files (TSV format with genomic coordinates) and need to prepare it for spectral embedding, clustering,

91 single-cell-atac-seq-dimensionality-reduction SkillLLM & Model APIs
Use when after loading and preprocessing raw scATAC-seq data into an ArchR project object when you need to compute low-dimensional embeddings for clustering, UMAP/tSNE visualizatio

91 single-cell-epigenomics-peak-analysis SkillLLM & Model APIs
Use when you have preprocessed single-cell ATAC-seq fragment files or count matrices and need to identify open chromatin regions (peaks) to support downstream differential accessib

91 spectral-embedding-dimension-reduction-parameters SkillLLM & Model APIs
Use when after generating a tile matrix or feature count matrix from single-cell ATAC-seq, RNA-seq, Hi-C, or methylation data, before clustering or UMAP visualization, when you nee

91 stream-trajectory-data-formatting SkillLLM & Model APIs
Use when you have completed peak calling and cell annotation in ArchR and want to perform trajectory inference or visualization in STREAM. Apply it specifically when your analysis

91 tile-matrix-generation-counting-strategy-selection SkillLLM & Model APIs
Use when after importing fragment files into AnnData using pp.import_fragments and before performing spectral embedding (tl.spectral) or other dimension reduction.

91 trajectory-inference-method-selection SkillLLM & Model APIs
Use when when you have an ArchR project object with processed single-cell ATAC-seq data and want to infer developmental or cell-state trajectories.

91 accuracy-metric-computation SkillLLM & Model APIs
Use when after running inference on a trained structure prediction model with one or more input modalities (1H NMR, 13C NMR, or combined), you have generated predicted molecular fo

91 adduct-assignment-accuracy-assessment SkillLLM & Model APIs
Use when you have a trained formula ranking model (such as MIST-CF) and want to measure the specific performance gain from incorporating multiple positive-mode adduct types (e.g.,

91 adduct-specific-model-fine-tuning SkillLLM & Model APIs
Use when when you have access to annotated MS/MS spectra from a specific ionization mode (e.g., negative ESI) or adduct class (e.

91 api-contract-validation SkillLLM & Model APIs
Use when integrating with an external API (such as TensorFlow Serving) where changes to the response schema could break dependent code, or when model metadata must be extracted and

91 atom-bond-feature-importance-ranking SkillLLM & Model APIs
Use when you have a trained GNN model for molecular property prediction (such as CCS) and need to understand which atomic and bond features are most influential in driving predicti

91 background-distribution-threshold-calibration SkillLLM & Model APIs
Use when when you have trained a predictive model (e.g., neural network or regression model) that outputs continuous scores (such as Spearman correlation coefficients) for individu

91 batch-normalization-implementation SkillLLM & Model APIs
Use when apply batch normalization after dense hidden layers (but not the final embedding layer) in a deep neural network trained on MS/MS spectral data, particularly when the netw

91 aria SkillLLM & Model APIs
Designs the data model, API contracts, and structural foundation of the system.

91 economics-concept-lesson SkillLLM & Model APIs
Teach an economics concept using incentives, constraints, models, assumptions, graphs or equations, examples, and policy relevance when appropriate.

91 model-and-graph-analysis SkillLLM & Model APIs
Teach how to construct, read, shift, and interpret economic models and graphs while keeping causal assumptions explicit.

91 engineering-mastery-check SkillLLM & Model APIs
Check engineering understanding through model selection, estimation, analysis, tradeoff reasoning, and recognition of unsafe assumptions.

91 scientific-reasoning SkillLLM & Model APIs
Teach hypothesis formation, experimental logic, variables, controls, measurement, uncertainty, causal inference, and interpretation of scientific evidence.

91 model-and-diagram-reasoning SkillLLM & Model APIs
Build and interpret free-body diagrams, field diagrams, energy representations, graphs, and simplified physical models.

91 physics-concept-lesson SkillLLM & Model APIs
Teach a physics concept using physical intuition, governing relationships, units, diagrams-in-words, examples, and model limits.

91 physics-problem-solving SkillLLM & Model APIs
Teach quantitative physics problem solving through representation, knowns and unknowns, model selection, calculation, units, and plausibility checks.

91 model-selection SkillLLM & Model APIs
Select an AI model for a real workload using representative evaluations, current official capability and pricing data, latency and cost measurements, operational constraints, and e

91 license-review SkillLLM & Model APIs
Review source code, dependencies, assets, data, models, fonts, media, and other redistributed material for identified license terms, provenance, compatibility, notices, attribution

91 causal-inference-review SkillLLM & Model APIs
Assess whether available observational or quasi-experimental evidence supports a causal conclusion and select a defensible identification strategy when possible.

91 forecasting-model SkillLLM & Model APIs
Build and evaluate a forecast with time-aware validation, baselines, uncertainty intervals, covariates, and scenario sensitivity.

91 replication-consistency SkillLLM & Model APIs
Implement replicated state with an explicit consistency model, conflict policy, convergence mechanism, and durability/recovery behavior.

91 openhands SkillLLM & Model APIs
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).

91 outlines SkillLLM & Model APIs
Outlines: structured JSON/regex/Pydantic LLM generation.

91 instructor SkillLLM & Model APIs
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with In

91 obliteratus SkillLLM & Model APIs
OBLITERATUS: abliterate LLM refusals (diff-in-means).

91 sparse-autoencoder-training SkillLLM & Model APIs
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering inte

91 simpo-training SkillLLM & Model APIs
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficie

91 distributed-llm-pretraining-torchtitan SkillLLM & Model APIs
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale

91 axolotl SkillLLM & Model APIs
Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

91 fine-tuning-with-trl SkillLLM & Model APIs
TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

91 claude-code SkillLLM & Model APIs
Delegate coding to Claude Code CLI (features, PRs).

91 codex SkillLLM & Model APIs
Delegate coding to OpenAI Codex CLI (features, PRs).

91 weights-and-biases SkillLLM & Model APIs
W&B: log ML experiments, sweeps, model registry, dashboards.

91 llama-cpp SkillLLM & Model APIs
llama.cpp local GGUF inference + HF Hub model discovery.

91 serving-llms-vllm SkillLLM & Model APIs
vLLM: high-throughput LLM serving, OpenAI API, quantization.

91 llm-wiki SkillLLM & Model APIs
Karpathy's LLM Wiki: build/query interlinked markdown KB.

91 ortools-pickup-delivery-routing SkillLLM & Model APIs
Model OR-Tools paired pickup-and-delivery routing problems, including PDPTW, dial-a-ride, paratransit, patient transport, and courier jobs with same-vehicle pairing, precedence, ca

91 routing-subtour-elimination SkillLLM & Model APIs
Subtour-elimination methods for TSP, VRP, pickup/dropoff routing, and routing MIPs with binary arc variables. Use when route-continuity constraints may permit disconnected cycles a

91 evolve SkillLLM & Model APIs
Create, extend, repair, or verify Local web and API services, including model-generation actions and improvements discovered during ordinary use.

91 manage-providers SkillLLM & Model APIs
Inspect, add, connect, customize, refresh, or restore model providers and their model lists in this Ox installation.

91 model-fine-tuning SkillLLM & Model APIs
Use when fine-tune LLMs and ML models — LoRA, QLoRA, PEFT, Hugging Face.

91 omniroute-integration SkillLLM & Model APIs
Use when integrate with OmniRoute AI Router for multi-provider LLM routing,

89 pave-catalog SkillLLM & Model APIs
Build a service catalog — schema, starter entries, and governance model. Produces what information to capture per service, how it's maintained, and where it lives. Use when asked t

89 work-decomposition SkillLLM & Model APIs
Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.

89 external-tool-coordination SkillLLM & Model APIs
Coordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated implementation.

89 guardrails-ai-setup SkillLLM & Model APIs
Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.

89 cortex-eval SkillLLM & Model APIs
Evaluate model performance — check for accuracy drops, data drift, and error patterns. Use when asked about "model accuracy dropped", "evaluate the model", "check for drift", or "m

89 cortex-model SkillLLM & Model APIs
Build an ML pipeline — from data to trained model to serving endpoint. Use when asked to "build ML model", "train a model", "prediction pipeline", "classification", or "regression"

89 text-creator SkillLLM & Model APIs
通过指导agent智能调度 Deepseek、Kimi、Claude 等顶尖文本模型，按办公任务类型自动匹配最优模型与调用策略，完成周报纪要、合同要点、邮件拟稿、多语言稿件、长报告总结、汇报大纲、多步推理与结构化改写，支持长文档处理。

88 bio-atac-seq-co-accessibility SkillLLM & Model APIs
Infer cis-regulatory connections (peak-to-peak co-accessibility) from scATAC-seq using Cicero, ArchR getCoAccessibility, or SCENIC+. Use when linking enhancer accessibility to prom

88 mortality-modeling SkillLLM & Model APIs
Model age-specific mortality rates and project future longevity improvements using the Lee-Carter bilinear log-mortality decomposition.

88 mortality-models SkillLLM & Model APIs
Life tables, mortality laws, survival analysis, longevity risk modeling, and population projections

88 init SkillLLM & Model APIs
Initialize a new CLAUDE.md file with codebase documentation

88 deepface SkillLLM & Model APIs
Use DeepFace for face recognition, verification, embeddings, face

88 model-and-backend-selection SkillLLM & Model APIs
Select and troubleshoot DeepFace models, detector backends,

88 subject-folder-binder SkillLLM & Model APIs
Package the approved subject-sorting working set for the organized LLM, trapped_ion_and_qc, black_hole, DNA, and music_history folders into a compact continuation packet, and recor

88 ai-wrapper-product SkillLLM & Model APIs
Expert in building products that wrap AI APIs (OpenAI, Anthropic,

88 eval-harness SkillLLM & Model APIs
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

88 deactivate SkillLLM & Model APIs
Deactivate the Flowy claude-scholar overlay for this session (clears its routing obligation).

88 status SkillLLM & Model APIs
Report whether the Flowy claude-scholar overlay is active and whether the enforcement hook is live this session.

88 leeway-formula-authority-recovery SkillLLM & Model APIs
Recover, verify, preserve and reuse proven LeeWay Formula authority before replacing evaluator contracts or runtime bindings. Resolve configured authority resources without dependi

88 verification-loop SkillLLM & Model APIs
A comprehensive verification system for Claude Code sessions.

88 setup SkillLLM & Model APIs
Configure the current repository for the team: .claude/settings.json, .gitignore entries, CLAUDE.md.

88 inference-backend SkillLLM & Model APIs
Flask inference backend on Hugging Face Spaces: job lifecycle, endpoints, telemetry, model loading, limits, proxy routes.

88 onboard SkillLLM & Model APIs
Generate or refresh CLAUDE.md from the repository (stack, run commands, data layout, conventions).

88 train-template SkillLLM & Model APIs
Structure for a PyTorch segmentation training script: resume, early stopping, cosine LR, AMP, full-state checkpoints, tiled inference.

88 boundary-inference SkillLLM & Model APIs
Chunked low-RAM boundary model inference over an AOI from XYZ tiles: tile cache, patch scan, Hanning blending, hysteresis, merged COG.

88 landuse-classify SkillLLM & Model APIs
Train or run the XGBoost land-use classifier: classes, T-minus alignment, model bundle, unified parcel/sub-parcel inference, predictions.gpkg.

88 Angular Signal State Pattern SkillLLM & Model APIs
Model feature state with signals while keeping derived state and effects separated.

88 release-model SkillLLM & Model APIs
Creates, upgrades, or audits RELEASING.md branching policy. Use when

88 release-model SkillLLM & Model APIs
Creates, upgrades, or audits RELEASING.md branching policy. Use when defining a release process, adding maintenance branches, or checking release-model drift.

88 delegate SkillLLM & Model APIs
Live in-session delegation from Claude to Codex via the approval/delegation packet contract

88 oculpm-codex SkillLLM & Model APIs
Use ocul-pm journals and planners from Codex without relying on Claude-only plugin variables.

88 laravel-scope-dont-check-after-fetch SkillLLM & Model APIs
Use when a route resolves an id from the request into a model: never findOrFail then an ownership check, always load through the relationship the caller actually has.

88 laravel-seed-new-features SkillLLM & Model APIs
Use when a change introduces or changes persisted data (a new model, an extended enum, a new column): ship its seed data in the same change, not three weeks later.

87 eval-harness SkillLLM & Model APIs
Framework formal de evaluación para sesiones de Claude Code que implementa principios de desarrollo orientado a evals (EDD)

87 verification-loop SkillLLM & Model APIs
Sistema de verificación completo para sesiones de Claude Code.

87 ai-wrapper-product SkillLLM & Model APIs
Expert in building products that wrap AI APIs (OpenAI, Anthropic,

86 ablation-response-fidelity-behavioral-models SkillLLM & Model APIs
Use when validating input ablations of behavioral/cognitive models. Oracle-calibrated response fidelity.

86 adversarial-distillation-defense SkillLLM & Model APIs
Defend reasoning models from distillation attacks.

86 claude-code SkillLLM & Model APIs
Anthropic's official AI-powered coding companion. Use when user wants to run claude-code CLI, needs help with code using Anthropic's Claude, or mentions claude-code, anthropic codi

86 agentic-fusion-materials SkillLLM & Model APIs
Agentic AI framework for materials discovery that synergizes Large Atomic Models (LAMs) with Large Language Models (LLMs). Use for designing autonomous materials discovery pipeline

86 complex-valued-kuramoto-network-control SkillLLM & Model APIs
Complex-Valued Kuramoto Networks control framework - unified control-theoretic approach for synchronization in coupled oscillator networks via complex state space embedding. Activa

86 computational-auditory-periphery-models SkillLLM & Model APIs
Cross-species computational modeling of the auditory periphery using 1-D nonlinear cochlear transmission-line models adapted across human, mouse, and gerbil. Covers species-specifi

86 computational-lesions-multilingual-language-models SkillLLM & Model APIs
多语言语言模型计算性损伤方法论。通过因果干预分离共享和语言特异性脑对齐模式，揭示语言理解的神经基础。适用于多语言神经科学、语言模型解释性、跨语言脑对齐。触发词：计算损伤、多语言、脑对齐、因果干预、共享表征。

86 cornn-convex-rnn-optimization SkillLLM & Model APIs
CORNN凸优化递归神经网络方法论。将RNN训练转化为凸优化问题，训练速度比传统方法快100倍，支持百万参数RNN在标准计算机上亚分钟级训练。适用于大规模神经记录实时建模、神经动力学推断、吸引子结构恢复。触发词：RNN训练、凸优化、神经动力学、实时建模、数据约束RNN、convex optimization、recurrent neural network、

86 cortical-microcircuit-information-flux-optimization SkillLLM & Model APIs
Simulation-based reverse engineering methodology for analyzing how cortical microcircuits optimize information flux (mutual information between successive network states). Use when

86 discounted-mpc-plant-model-mismatch SkillLLM & Model APIs
Discounted MPC under plant-model mismatch - stability and suboptimality analysis for infinite-horizon optimal control with surrogate models. Activation: MPC, model predictive contr

86 integrative-neurocybernetic-modeling SkillLLM & Model APIs
Integrative neurocybernetic modeling framework for large-scale neuroscience. Treats brain as controller pursuing latent objectives in closed-loop coupling with body and environment

86 llm-self-correction-confidence-signals SkillLLM & Model APIs
大型语言模型通过内部置信度信号检测和纠正自身错误的研究。基于决策神经科学二阶置信度模型和PANL token机制。

86 llm-self-correction-confidence-signals SkillLLM & Model APIs
大型语言模型通过内部置信度信号检测和纠正自身错误的研究。基于决策神经科学二阶置信度模型。

86 llm-serving-system-adaptive-architecture SkillLLM & Model APIs
LLM服务系统自适应架构设计 - 自进化系统、解耦架构、冷启动优化、黑盒调度、能效优化的综合技能框架。激活词: llm serving, adaptive architecture, autopoiesis, lora serving, llm cold start, inference scheduling.

86 neuro-bursty-persistent-networks SkillLLM & Model APIs
Bursty Persistent Brain Network (PBN) modeling methodology for neural dynamics with non-Markovian temporal structure. Combines renewal theory, state-dependent intensity functions,

86 neurocybernetic-modeling-large-scale SkillLLM & Model APIs
Integrative neurocybernetic modeling in the era of large-scale neuroscience. Closed-loop brain-body-environment models, nonlinear state-space, meta-dynamical extensions, knowledge

86 physical-foundation-models-pfm SkillLLM & Model APIs
Physical Foundation Models (PFMs) — Fixed hardware implementations of large-scale neural networks where parameters are realized directly in physical substrate dynamics. Use when: d

86 physical-foundation-models SkillLLM & Model APIs
Physical Foundation Models (PFMs): Fixed hardware implementations of large-scale neural networks realized directly in physical materials. Covers optical, nanoelectronic, and other

86 plant-model-mismatch-mpc SkillLLM & Model APIs
Model Predictive Control under plant-model mismatch - stability and suboptimality guarantees. Handles model uncertainty in control systems. Activation: MPC, model mismatch, robust

86 poisson-gradient-estimation SkillLLM & Model APIs
Systematic comparison of Poisson gradient estimation methods (EAT vs GSM) for latent variable models in computational neuroscience. Activation: poisson gradient, EAT method, Gumbel

86 relaxation-informed-surrogate-training SkillLLM & Model APIs
Relaxation-Informed Training (RIT) for neural network surrogate models enabling exact MILP embedding with reduced binary variables. Activation triggers: surrogate optimization, MIL

86 self-orthogonalizing-attractor-networks SkillLLM & Model APIs
Formalizes how attractor networks emerge from the free energy principle applied to universal partitioning of random dynamical systems. Results in self-orthogonalizing attractor rep

86 spike-driven-large-language-model-sdllm SkillLLM & Model APIs
Spike-driven Large Language Model (SDLLM) methodology. Eliminates dense matrix multiplications in LLMs through sparse addition operations using gamma-SQP two-step spike encoding. R

86 spike-driven-large-language-model SkillLLM & Model APIs
Spike-driven Large Language Model - Spike-based computation for large language models. Activation triggers: spike, driven, large, neuroscience, SNN.

86 stateful-streaming-transformer-inference SkillLLM & Model APIs
Stateful streaming transformer inference methodology with persistent KV cache, Flash Queries prefetching, and multi-tenant continuous-batching for efficient streaming workloads.

86 training-free-looped-transformers SkillLLM & Model APIs
Training-free looped transformers — inference-time technique that loops a contiguous mid-stack block of layers in a frozen pretrained LLM to improve reasoning without fine-tuning.

86 wavemoe-time-series SkillLLM & Model APIs
Wavelet-Enhanced Mixture-of-Experts (WaveMoE) foundation model for time series forecasting. Use when building time series prediction models, incorporating frequency-domain informat

86 2028-ai-leadership-scenarios SkillLLM & Model APIs
Methodology from Anthropic policy analysis examining possible trajectories for US-China AI competition by 2028 — focusing on compute advantage, export controls, distillation attack

86 81k-ai-expectations SkillLLM & Model APIs
Methodology for understanding how users use AI, what they dream it could enable, and what they fear based on Anthropic's large multilingual qualitative study.