AI & ML

odjaramillo Skill

Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.

richfrem Skill

(Industry standard: Sequential Agent / Agent as a Tool) Primary Use Case: Delegating a well-defined task to a worker agent, verifying its execution, and repeating if necessary. Inner/outer agent delegation pattern. Use when: work needs to be delegated from a strategic controller (Outer Loop) to a tactical executor (Inner Loop) via strategy packets, with verification and correction loops.

richfrem Bundle

Upload primitives for HuggingFace Soul persistence - file, folder, snapshot, JSONL append, and dataset card management with exponential backoff.

richfrem Bundle

(Industry standard: Loop Agent / Single Agent) Primary Use Case: Self-contained research, content generation, and exploration where no inner delegation is required. Self-directed research and knowledge capture loop. Use when: starting a session (Orientation), performing research (Synthesis), or closing a session (Seal, Persist, Retrospective). Ensures knowledge survives across isolated agent sessions.

richfrem Skill

Claude CLI sub-agent system for persona-based analysis. Use when piping large contexts to Anthropic models for security audits, architecture reviews, QA analysis, or any specialized analysis requiring a fresh model context.

richfrem Skill

Gemini CLI sub-agent system for persona-based analysis. Use when piping large contexts to Anthropic models for security audits, architecture reviews, QA analysis, or any specialized analysis requiring a fresh model context.

richfrem Bundle

Start the Native Python ChromaDB background server. Use when semantic search returns connection refused on port 8110, or when the user wants to enable concurrent agent read/writes.

intent-solutions-io Bundle

This skill enables Claude to construct and evaluate classification models using provided datasets or specifications. It leverages the classification-model-builder plugin to automate model creation, optimization, and reporting. Use this skill when the user requests to "build a classifier", "create a classification model", "train a classification model", or needs help with supervised learning tasks involving labeled data. The skill ensures best practices are followed, including data validation, error handling, and performance metric reporting.

intent-solutions-io Bundle

This skill enables Claude to design and visualize database schemas. It leverages normalization guidance (1NF through BCNF), relationship mapping, and ERD generation to create efficient and well-structured databases. Use this skill when the user requests to "design a database schema", "create a database model", "generate an ERD", "normalize a database", or needs help with "database design best practices". The skill is triggered by terms like "database schema", "ERD diagram", "database normalization", and "relational database design".

richfrem Bundle

Interactive initialization script that scaffolds a new Model Context Protocol (MCP) server integration setup. Use when adding native code tools to an agent's environment.

fabioc-aloha Skill

Create and validate .prompt.md files that pass brain-qa on first attempt

fabioc-aloha Skill

Design autonomous AI agents that reason, plan, and execute tasks

fabioc-aloha Skill

Build retrieval-augmented generation systems that ground LLMs in your data.

fabioc-aloha Skill

Build applications powered by GitHub Copilot using the Copilot SDK — session management, custom tools, streaming, hooks, MCP servers, BYOK, deployment patterns

fabioc-aloha Skill

Health Pulse data model, status rules, scoring algorithms, and thresholds — the canonical source the extension consumes

fabioc-aloha Skill

Microsoft Entra Agent ID (preview) — create OAuth2-capable AI agent identities via Microsoft Graph beta API

fabioc-aloha Skill

Craft effective prompts that get the best results from language models.

fabioc-aloha Skill

Choosing the right model for the task — power vs. cost vs. speed.

fabioc-aloha Bundle

Manage VS Code's global AI configuration — user memories, user prompts, and MCP servers

rudironsoni Skill

GitHub MCP Server integration for repository operations, pull requests, issues, and GitHub Actions. Triggers on: github mcp, github operations, pull request, issue, repository, github actions, commit, branch, merge.

rudironsoni Skill

Validates MCP server connectivity and health. Checks stdio and http MCP servers for availability, reports connection status, and provides fallback guidance. Triggers on: mcp health, check mcp, validate mcp, mcp status, mcp connectivity.

rudironsoni Skill

Patterns and techniques for evaluating and improving AI agent outputs.

fabioc-aloha Skill

Externalized prompt store, A/B testing, metrics-driven evolution, quality gates, and auto-rollback

fabioc-aloha Skill

Analyze codebase architecture to generate a STRIDE-based threat model with data flow diagrams, trust boundaries, prioritized threats, and mitigations. Compatible with Microsoft Threat Modeling Tool concepts. Use when asked to "threat model", "security analysis", "STRIDE analysis", "identify security threats", "data flow security", "generate a threat model", or "security architecture review".

rudironsoni Skill

Runs Slopwatch CLI to detect LLM reward hacking -- disabled tests, suppressed warnings.

rudironsoni Skill

Microsoft Learn MCP Server integration for accessing official Microsoft documentation

rudironsoni Skill

Flags agent mistakes in .NET code -- async misuse, NuGet errors, deprecated APIs, DI.

rudironsoni Skill

Hooks and MCP server guide for dotnet-agent-harness. How hooks behave, how to disable them, MCP configuration and troubleshooting.

rudironsoni Skill

Offline mode with local caching for air-gapped environments

rudironsoni Skill

Debugs Windows apps via WinDbg MCP. Crash, hang, high-CPU, and memory triage from dumps or live attach.

rudironsoni Skill

Skill manifest management for dotnet-agent-harness. Tracks skill dependencies, conflicts, version compatibility, and provides validation and resolution tools. Triggers on: skill manifest, dependency resolution, skill compatibility, version conflicts, build manifest, validate dependencies.

rudironsoni Skill

AI-powered skill recommendation engine for dotnet-agent-harness. Analyzes project context and recommends relevant skills based on detected frameworks, packages, and patterns. Triggers on: recommend skill, suggest skills, what skill should I use, skill suggestion, project analysis recommendation.

rudironsoni Skill

Integrates AI/LLM via Microsoft Agent Framework. Agents, workflows, tools, MCP servers, multi-agent orchestration.

rudironsoni Bundle

Comprehensive testing framework for skills

ysyecust Skill

オブザーバビリティ、セキュリティ境界、およびライフサイクル管理を備えた長寿命エージェントワークロードを運用します。

abelrguezr Bundle

Active Directory Certificate Services (AD CS) persistence techniques for security assessments. Use this skill whenever analyzing AD CS configurations, planning certificate-based persistence, understanding PKINIT attacks, working with certificate templates in Active Directory, or investigating altSecurityIdentities abuse. Covers user/machine certificate persistence, certificate renewal, explicit mapping attacks, enrollment agent abuse, and 2025 strong mapping enforcement implications. Make sure to use this skill for any AD CS enumeration, certificate template analysis, or certificate-based authentication attacks in Windows domain environments.