机器学习

Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition, course correction.

DatTran260

机器学习

Pod Maturity

RapidX pod maturity model — track and improve team maturity in AI-assisted engineering practices.

dbrijesh0

机器学习

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

tomevault-io0

机器学习

Create Dotfile

Use when authoring or repairing Kilroy Attractor DOT graphs from requirements, with template-first topology, routing guardrails, and validator-clean output.

dcgrigsby0

机器学习

Rails Model Generator

Creates Rails models using TDD approach - test first, then migration, then model. Use when creating new models, adding model validations, defining associations, or setting up database tables.

dchuk0

机器学习

U0679 Crisis Self Reflection Error Taxonomist

Build and operate the "Crisis Self-Reflection Error Taxonomist" capability for Crisis and Incident Response. Trigger when this exact capability is needed in mission execution.

zwright80

机器学习

Dream Crusher

Dream-crusher is a red-team thinking skill that pressure-tests an idea by surfacing hidden assumptions, running a 12‑month pre‑mortem to predict failure modes, and converting the biggest risks into fast, cheap, pass/fail experiments—ending with clear go/kill/pivot decision rules and an executable next-week plan.

dCraigJones0

机器学习

Testgen Gemini

Gemini-optimized wrapper for the core testgen workflow. Use when you want the testgen skill defaults to route specialist test generation through Gemini-first subagent strategy while preserving the same contracts and fail-closed coverage behavior.

DDD-Enterprises0

机器学习

Data Science Agent — Datalake SubventionAI

Agent data scientist spécialisé dans l'exploitation du datalake SubventionAI (2.8M entités, 168K versements, scoring ML, embeddings bge-m3 1024d). Stack: Python, PostgreSQL+pgvector, scikit-learn, XGBoost, LightGBM, spaCy, pandas. Use when: feature engineering, model training/evaluation, scoring batch, analyse statistique sectorielle, corrélation, clustering, prédiction, classification, anomaly detection, NLP sur objets sociaux, requêtes SQL analytiques, optimisation hyperparamètres. Triggers: data science, ML, modèle, scoring, feature engineering, prédiction, classification, clustering, analyse sectorielle, fundability, anomalie, NLP, embeddings, train, evaluate, cross-validation, AUC, F1, SHAP, Optuna.

TheWatcher010

机器学习

Astar Submit

Submits predictions for all 5 seeds to the Astar Island API with safety guardrails. Accepts a directory of per-seed JSON files or a single file. Floors at 0.01, renormalizes, fixes NaN/Inf, validates dimensions, checks static terrain, detects degenerate predictions. Missing seeds get uniform fallback. Use when submitting predictions or says "submit prediction", "submit to api", "upload results".

team-phai0

机器学习

Yann Lecun Tecnico

Sub-skill técnica de Yann LeCun. Cobre CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machinery of Intelligence), Self-Supervised Learning (SimCLR, MAE, BYOL), Energy-Based Models (EBMs) e código PyTorch completo.

deco314160

机器学习

U0671 Crisis Security Threat Modeler

Build and operate the "Crisis Security Threat Modeler" capability for Crisis and Incident Response. Trigger when this exact capability is needed in mission execution.

zwright80

机器学习

Learn Baseline

在实验性 orchestrator 设计下，用于从 PROJECT_GUIDE、owner docs 和当前 run 证据中建立学习基线。

deepcooker0

机器学习

Learn Baseline

在实验性 orchestrator 设计下，用于从 PROJECT_GUIDE、owner docs 和当前 run 证据中建立学习基线。

deepcooker0

机器学习

U0687 Impact Goal Decomposer

Build and operate the "Impact Goal Decomposer" capability for Social Impact Measurement. Trigger when this exact capability is needed in mission execution.

zwright80

机器学习

Dev Tool Explainer

A brief description, shown to the model to help it understand when to use this skill

DeepTutorAi0

机器学习

OpenEnv Training with GRPO

OpenEnv Training — GRPO RL fine-tuning with TRL and Wordle. Use this skill whenever the user asks about: training an LLM with reinforcement learning using OpenEnv; GRPO (Group Relative Policy Optimization) with TRL; the Wordle environment in TextArena; defining rollout functions for GRPOTrainer; reward function design (correctness, green/yellow tile scores, repetition penalties); the rollout_once loop; using vLLM in colocate mode for generation; GRPOConfig parameters; fine-tuning Qwen or other models on text games; multi-turn RL episodes with an agentic environment; or the TextArena / OpenEnv integration with TRL. Also trigger for questions about GRPOTrainer, rollout_func, generate_rollout_completions, TextArenaEnv, or system prompts for Wordle.

deepraj210

机器学习

Senior Data Scientist

World-class senior data scientist skill specialising in statistical modeling, experiment design, causal inference, and predictive analytics. Covers A/B testing (sample sizing, two-proportion z-tests, Bonferroni correction), difference-in-differences, feature engineering pipelines (Scikit-learn, XGBoost), cross-validated model evaluation (AUC-ROC, AUC-PR, SHAP), and MLflow experiment tracking — using Python (NumPy, Pandas, Scikit-learn), R, and SQL. Use when designing or analysing controlled experiments, building and evaluating classification or regression models, performing causal analysis on observational data, engineering features for structured tabular datasets, or translating statistical findings into data-driven business decisions.

mattnebr0

机器学习

Retrieving Task Patterns

Targeted retrieval of prior task-class patterns, workflow learnings, and reusable examples from the synced Obsidian vault. Invoked when planning or execution benefits from knowing how Nova-Core handled similar work before.

demarcushill200

机器学习

Train Glossary

Train glossary từ samples mới. Dùng khi thêm samples CN/VN mới và muốn cập nhật glossary.json + AGENTS.md.

thiendiepdt0

机器学习

Research Refine

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.

THUFanZd0

机器学习

Training Decision Skill

LUÔN dùng skill này ngay sau eval-analyzer khi user hỏi "train tiếp hay dừng?", "có nên resume không?", "cần thay đổi gì?", hay bất cứ câu hỏi nào liên quan đến quyết định training của wheeled biped project. Nhận report từ eval-analyzer (validation signals + training trend) → đưa ra 1 trong 6 quyết định cụ thể: CONTINUE, RESUME_TWEAK, RESUME_CKPT, RETRAIN_STAGE, RETRAIN_SCRATCH, ADVANCE_STAGE. Output: quyết định có lý do + command sẵn sàng chạy + config diff YAML nếu cần. Không dùng skill này khi chưa có output từ eval-analyzer.

Thuong1807020

机器学习

Train And Eval

Full pipeline: finetune a model on benchmark data, then evaluate the resulting checkpoint — all in one SLURM job. No manual intervention needed.

dengyufuqin0

机器学习

Finetune

Finetune a policy model on a benchmark dataset. Supports LeRobot models (pi0, pi0.5, smolvla) and OpenVLA. Submits as SLURM job for multi-GPU training.

dengyufuqin0

机器学习

Solid

Use this skill when writing code, implementing features, refactoring, planning architecture, designing systems, reviewing code, or debugging. This skill transforms junior-level code into senior-engineer quality software through SOLID principles, TDD, clean code practices, and professional software design.

mattnebr0

机器学习

Predictive

Skill for the Predictive area of BLDG Estimator. 17 symbols across 6 files.

mattnicosia0

机器学习

Tts

Use when you need local neural speech generation or voice cloning with the MOSS-TTS, OmniVoice, or VoxCPM2 engines, especially when choosing between stable long-form TTS, tag-driven voice design, and GPU-first expressive synthesis.

detoix0

机器学习

Profile

SCFプロファイリング実行。ボトルネック分析と最適化提案

soyukke0

机器学习

机器学习

Codereview

Power Bi Model Design Review

Ck Sequential Thinking

Pod Maturity

Continuous Learning V2

Create Dotfile

Rails Model Generator

U0679 Crisis Self Reflection Error Taxonomist

Dream Crusher

Testgen Gemini

Data Science Agent — Datalake SubventionAI

Astar Submit

Yann Lecun Tecnico

U0671 Crisis Security Threat Modeler

Learn Baseline

Learn Baseline

U0687 Impact Goal Decomposer

Dev Tool Explainer

OpenEnv Training with GRPO

Senior Data Scientist

Retrieving Task Patterns

Train Glossary

Research Refine

Training Decision Skill

Train And Eval

Finetune

Solid

Predictive

Tts

Profile