Machine Learning

Implement/review the A2 scalable winner model using canonical playerKey per WinMode + O(1) aggregated counters & winner counts (no loops over players) for daily/monthly commit→reveal→draw→claim.

IagoPrandi0

Machine Learning

Corpus Generator

Generate training data for model distillation by running prompts from the prompt bank through a teacher model and saving responses in ChatML format.

iamthetonyb0

Machine Learning

Structured learning system for continuous self-improvement. Use this skill to log learnings, track errors, record feature requests, detect recurring patterns, and extract new skills from repeated workflows. Triggers on: learning, error tracking, pattern detection, skill extraction, retrospective, what went wrong, lessons learned, improve system.

iamthetonyb0

Machine Learning

Ralph Loop

Use when you need iterative self-improvement on any task. Implements the Ralph Loop pattern: Plan → Execute → Review → Learn → Improve → Repeat. Each cycle produces better output than the last.

iAMv10

Machine Learning

Vera Qs

Use this skill to perform forensic validation of IFC models, specifically focusing on Material Layer Sets, Classification compliance, and Quantity field presence. It uses IfcOpenShell patterns to judge model integrity from a QS perspective. Strictly read-only and verdict-only.

Ic15580

Machine Learning

Segment Anything Model

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

ibragimov-oasis0

Machine Learning

Thom Vision

Advanced Visual Intelligence for AEC (FastVLM + ControlNet)

Ic15580

Machine Learning

Rust Pro

Master Rust 1.75+ with modern async patterns, advanced type system features, and production-ready systems programming. Expert in the latest Rust ecosystem including Tokio, axum, and cutting-edge crates. Use PROACTIVELY for Rust development, performance optimization, or systems programming.

Icebane840

Machine Learning

Prompt Engineering

Prompt engineering best practices for LLM-powered applications including prompt design patterns, structured output, evaluation, safety, and cost optimization. Use when building or reviewing AI-powered features that interact with LLMs.

iceflower0

Machine Learning

N8n Studio Refactor

This skill should be used when the n8n-studio development cycle reaches the refactoring phase (6단계), or when the user asks to "n8n 워크플로우 리팩토링해줘", "워크플로우 단순화해줘". This phase is optional and can be skipped if not needed.

icednut0

Machine Learning

Cost Aware Llm Pipeline

Cost optimization patterns for IDNA's GPT-4.1/GPT-4.1-mini routing — model selection by task complexity, budget tracking, retry logic.

idnaedtech0

Machine Learning

Imbalanced Fine Tuning

均衡データで学習したモデルを不均衡データに適応させるFine-tuning手法

kotaro-desu0

Machine Learning

Mega Engineer

Senior engineer skill — metodología de ejecución. Activar antes de codear (spec), durante (calidad), después (review), al debuggear (root cause). Aplica a nerd-back y nerd-full.

koronet-network0

Machine Learning

Code Reviewer

Hylono regression-focused review skill. Use for code review, remediation review, or pre-merge checks with emphasis on public routes, SEO, compliance, route contracts, and critical user-flow regressions.

Koniorek000

Machine Learning

Module Name

[TODO: Complete description of what this skill does and when to use it]

kongshan0010

Machine Learning

Prompt Engineering CN

Chinese-first prompt engineering for LLM tasks. Use this skill whenever the user asks in Chinese to optimize a prompt, write a system prompt, redesign instructions, stabilize structured output, reduce hallucinations, build few-shot examples, harden a RAG prompt against prompt injection, or review why a model's output is unstable. Also use it when the user says things like "优化这个提示词", "帮我写系统提示词", "改成稳定的 JSON 输出", "降低幻觉", or "这个 prompt 老被注入".

koodfandan0

Machine Learning

Systematic Debugging Lite

轻量化系统调试技能：用于 bug、测试失败、异常行为、构建失败与集成问题排查。强调先根因后修复、先证据后结论、一次只验证一个假设，适合作为 silver-bullet-spec 执行阶段的问题定位辅助。当用户说'根因是什么''为什么失败了''先别修，先查清楚''这个 bug 怎么回事''测试为什么挂了''定位一下问题'时触发。不用于：普通功能开发、需求规划、单纯代码生成、根因已明确且只差一个极小修复的场景。

Ike-li0

Machine Learning

Harness Goal

目标追踪技能，防止任务偏离目标，确保任务执行符合SMART原则

konglong870

Machine Learning

Harness Evaluate Performance

效果量化评估技能，评估任务执行效果、生成性能指标、验证目标达成

konglong870

Machine Learning

Hybrid Live Review Worker

Implement Hybrid live-review runner, artifact, session-targeting, and mismatch-truth fixes with bridge-first validation discipline.

ildunari0

Machine Learning

Confusion Matrix Generator

Confusion Matrix Generator - Auto-activating skill for ML Training. Triggers on: confusion matrix generator, confusion matrix generator Part of the ML Training skill category.

ilfordarber150

Machine Learning

Data Normalization Tool

Data Normalization Tool - Auto-activating skill for ML Training. Triggers on: data normalization tool, data normalization tool Part of the ML Training skill category.

ilfordarber150

Machine Learning

Ml Data Leakage Guard

Detects and prevents data leakage in machine learning and mathematical modeling. Auto-activates after ML tasks involving: data cleaning, feature engineering, data augmentation, algorithm development, normalization, missing value imputation, dimensionality reduction, feature selection, time series modeling. Checks if features/statistics would be available at prediction time.

ilfordarber150

Machine Learning

Harness Evolve

自我进化技能，实现技术债清理、迭代飞轮、持续改进，从错误中学习并优化系统

konglong870

Machine Learning

Mgi Theory Practitioner

Use when you want to apply a known mental model to a real challenge with precision. Takes a mental model from the library and applies it to a real user-provided challenge, generating an actionable protocol grounded in the model's logic.

Imad-Oute0

Machine Learning

Cai Hook Engineer

Engineer high-CTR headlines and hooks using the 7-Component News Matrix. Use when optimizing content hooks or headlines.

Imad-Oute0

Machine Learning

Safe Refactor — Behavioral Specification for Secure Code Restructuring

Chain-combined skill that ensures refactoring is done safely by combining refactor judgment, test coverage verification, and pre-commit review. Encapsulates the decision of WHEN to refactor, HOW to ensure safety, and WHAT verification is needed. Use when user mentions refactoring, code restructuring, improving code quality, or when they want to refactor without breaking behavior. Triggers especially when user says "should I refactor this?", "is it safe to refactor?", "how do I refactor without breaking things?", or "refactor my code".

ImaginerLabs0

Machine Learning

Make Wpf Viewmodel

Generates WPF ViewModel with View, DI registration, and DataTemplate mapping in one step. Use when creating a new screen, adding a View-ViewModel pair, or scaffolding ViewModel boilerplate with DI wiring. Usage: ask Codex to use the `make-wpf-viewmodel` skill <ViewModelName> [--with-view] [--no-mapping]

parksanghoon-sys0

Machine Learning

Algorithms And Data Structures

Enforces complexity analysis, correct data structure selection, vectorization, and algorithm implementation discipline at principal-engineer level.

ParamChordiya0

Machine Learning

Design Microarch

Use when processing RTL modules at the microarchitecture level - including FIFO, state machines, counters, arbiters, decoders, or any Verilog/SystemVerilog hardware design. Load this skill immediately upon identifying RTL design tasks, before diving into brainstorming，planning or implementation.

Paradicat0

Machine Learning

Machine Learning

A2 Key Aggregation

Corpus Generator

Self Improvement

Ralph Loop

Vera Qs

Segment Anything Model

Thom Vision

Rust Pro

Prompt Engineering

N8n Studio Refactor

Cost Aware Llm Pipeline

Imbalanced Fine Tuning

Mega Engineer

Code Reviewer

Module Name

Prompt Engineering CN

Systematic Debugging Lite

Harness Goal

Harness Evaluate Performance

Hybrid Live Review Worker

Confusion Matrix Generator

Data Normalization Tool

Ml Data Leakage Guard

Harness Evolve

Mgi Theory Practitioner

Cai Hook Engineer

Safe Refactor — Behavioral Specification for Secure Code Restructuring

Make Wpf Viewmodel

Algorithms And Data Structures

Design Microarch