AI & ML

tyler-r-kendrick Bundle

Use when building AI agents with Microsoft.SemanticKernel or Microsoft.Extensions.AI.Agent frameworks. Covers agent creation, tool/plugin registration, multi-agent orchestration, chat completion agents, and OpenAI Assistants integration. USE FOR: building AI agents with tools and plugins, multi-agent chat workflows, Semantic Kernel agent orchestration, OpenAI Assistants API integration, agent-based automation pipelines DO NOT USE FOR: simple chat completions without agent patterns (use microsoft-extensions-ai), inter-service agent communication over A2A protocol (use a2a), ML model training (use mlnet), raw ONNX inference (use onnx)

tyler-r-kendrick Bundle

Use when implementing the Agent-to-Agent (A2A) protocol for inter-agent communication, task delegation, and multi-agent collaboration. USE FOR: agent-to-agent communication, task delegation between agents, Agent Card publishing, multi-agent collaboration DO NOT USE FOR: tool integration (use mcp), agent payments (use ap2 or x402), agent definition (use adl)

tyler-r-kendrick Bundle

Use when defining AI agents declaratively with Agent Definition Language (ADL). Covers agent identity, LLM configuration, tools, permissions, RAG inputs, and governance metadata. USE FOR: declarative agent blueprints, agent identity and permissions, LLM configuration, governance metadata DO NOT USE FOR: agent runtime orchestration (use cagent), tool integration (use mcp), agent communication (use a2a)

tyler-r-kendrick Bundle

Use when implementing or integrating with the Model Context Protocol (MCP) for AI tool servers, resources, prompts, and context management. USE FOR: building MCP tool servers, exposing resources to agents, prompt templates, connecting agents to external APIs DO NOT USE FOR: agent-to-agent communication (use a2a), interactive UI rendering (use mcp-apps), agent payments (use x402 or ap2)

tyler-r-kendrick Bundle

USE FOR: Defining high-performance validation specifications using Validot's fluent specification builder. Use when you need allocation-free validation with reusable specifications, fast execution, and detailed error output. DO NOT USE FOR: Async validation with database lookups (Validot is synchronous), ASP.NET Core automatic model validation integration (use FluentValidation), or guard-clause-style argument checking (use CommunityToolkit Guard).

tyler-r-kendrick Bundle

Hexagonal Architecture (Ports and Adapters), Onion Architecture, and their relationship to Clean Architecture -- enabling technology-independent domain logic with high testability. USE FOR: hexagonal architecture, ports and adapters, onion architecture, driving/driven adapters, technology-independent domain design, adapter-based testability DO NOT USE FOR: clean architecture layers specifically (use dev/craftsmanship/clean-architecture), microservice boundaries (use microservices), domain model design (use domain-driven-design)

agents-inc Bundle

Chroma vector database -- collection management, automatic embedding, metadata filtering, document storage, query patterns

tyler-r-kendrick Bundle

USE FOR: IL weaving at build time to inject cross-cutting concerns such as INotifyPropertyChanged implementation, null-guard checks, method timing, logging, and resource embedding into .NET assemblies. DO NOT USE FOR: Runtime AOP frameworks, source generators that produce C# code, or scenarios where compile-time code generation (Roslyn generators) would be more transparent and debuggable.

agents-inc Bundle

Sequelize ORM, model definitions, associations, queries, transactions, migrations

agents-inc Bundle

SurrealDB multi-model database - SurrealQL queries, record links, graph relations, live queries, schema definitions, authentication, TypeScript SDK

agents-inc Bundle

Weaviate vector database patterns with weaviate-client v3 -- collection management, vectorizer modules, hybrid search, filtering, generative search (RAG), multi-tenancy, batch imports

tryboy869 Bundle

[Applies to: **/*] This guide provides definitive, actionable best practices for developing with the OpenAI API, covering prompt engineering, robust client usage, agent design, and testing.

tryboy869 Bundle

[Applies to: **/*.py] This guide provides opinionated best practices for structuring, optimizing, and testing autogen multi-agent systems to ensure maintainability, reproducibility, and cost-efficiency.

agents-inc Bundle

Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint

tryboy869 Bundle

Apply when integrating LLM APIs (OpenAI, Groq, Anthropic, Mistral) into applications. Covers: prompt engineering, streaming, retry logic, cost control, structured outputs, function calling. Trigger for: LLM, GPT, Claude, Groq, AI API, prompt, OpenAI, Anthropic.

tyler-r-kendrick Bundle

Use when a user corrects, rejects, edits, or redirects an LLM/agent response and the correction should become a reusable reasoning strategy. Converts feedback into generalized learnings for ~/.agents/STEERING.md with linked RDF/Turtle evidence. USE FOR: user corrections, preference feedback, rejected agent behavior, reasoning strategy updates, steering file maintenance DO NOT USE FOR: storing task facts (use memory), ordinary skill authoring (use agent-skills), project instruction files unrelated to feedback (use agents-md)

tyler-r-kendrick Bundle

Use when configuring or using SSH for remote access, secure file transfer, tunneling, and key management. Covers ssh, scp, sftp, ssh-keygen, SSH config, agent forwarding, port forwarding, and ProxyJump for jump hosts. USE FOR: SSH, scp, sftp, ssh-keygen, SSH config, SSH keys, agent forwarding, port forwarding, SSH tunneling, ProxyJump, jump hosts, authorized_keys, known_hosts, SSH hardening DO NOT USE FOR: general network security (use security skills), VPN configuration, remote desktop protocols

tyler-r-kendrick Bundle

Use when producing agent/LLM evals, synthetic simulation data, or self-improvement pipelines for prompts, code, skills, agents, harnesses, and workflows. Covers AgentEvals/AgentV, Agent Skills evals, ASSERT, GEPA, Trace, VISTA, Agent Lightning, SkillOpt, Simula-style data design, progressive disclosure, deterministic workspaces, and release evidence. USE FOR: eval creation, EVAL.yaml, AgentEvals, AgentV, evals.json, ASSERT, judge-traces, behavior taxonomy, judges, graders, rubrics, synthetic data, simulation data, Simula, QDC, source-grounded generation, prompt optimization, agent improvement, skill improvement, harness hardening, progressive disclosure, deterministic workflows, GEPA, Trace, VISTA, Agent Lightning, SkillOpt DO NOT USE FOR: ordinary unit/integration tests without AI quality criteria (use testing), refactoring without eval or trace feedback (use refactor), generic Agent Skills packaging without eval or improvement work (use agent-skills)

agents-inc Bundle

Zod schema validation patterns for TypeScript - schema definitions, type inference, refinements, transforms, discriminated unions

agents-inc Bundle

LiteLLM proxy server setup, TypeScript client patterns via OpenAI SDK, model routing, fallbacks, load balancing, spend tracking, virtual keys, and production deployment

agents-inc Bundle

LLM observability with Langfuse — OpenTelemetry-based tracing, evaluations, prompt management, datasets, and production best practices

agents-inc Bundle

Official Anthropic SDK patterns for TypeScript/Node.js — client setup, Messages API, streaming, tool use, vision, extended thinking, structured outputs, prompt caching, batch API, and production best practices

agents-inc Bundle

AI specification planning frameworks. Use when a spec touches model calls, prompts, retrieval, tool calling, agentic loops, or evals. Covers approach selection, model and provider choice, structured output contracts, loop guards, budgets, failure modes, and eval design.

agents-inc Bundle

LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing

agents-inc Bundle

CLI specification planning frameworks. Use when a spec touches a command surface, an interactive flow, config precedence, exit codes, or output modes. Covers flag contracts, prompt flow design, precedence tables, exit-code taxonomy, TTY/piped/JSON output, error text, signals, and cross-platform concerns.

agents-inc Bundle

Playwright E2E testing patterns - test structure, Page Object Model, locator strategies, assertions, network mocking, visual regression, parallel execution, fixtures, and configuration

tyler-r-kendrick Bundle

Use when applying OWASP standards to identify and mitigate common security vulnerabilities. Covers OWASP Top 10 (2021), OWASP API Security Top 10 (2023), and CWE/SANS Top 25 with mitigation strategies for each category. USE FOR: OWASP Top 10, API Security Top 10, CWE Top 25, web application vulnerabilities, vulnerability classification, security baseline, broken access control, injection, XSS, SSRF DO NOT USE FOR: AI/LLM-specific vulnerabilities (use ai-security), security tool configuration (use security-testing), cryptographic implementation (use cryptography)

tyler-r-kendrick Bundle

Use when creating, packaging, or distributing Agent Skills. Covers the SKILL.md specification, frontmatter schema, naming conventions, marketplace publishing, and the skills-ref validator. USE FOR: creating SKILL.md files, packaging reusable agent capabilities, marketplace publishing, frontmatter schema validation DO NOT USE FOR: project-level agent guidance (use agents-md), agent runtime configuration (use adl or cagent)

tyler-r-kendrick Bundle

Analyzes markdown files for token efficiency. TRIGGERS: optimize markdown, reduce tokens, token count, token bloat, too many tokens, make concise, shrink file, file too large, optimize for AI, token efficiency, verbose markdown, reduce file size

agents-inc Bundle

Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training

agents-inc Bundle

LlamaIndex.TS data framework for RAG, indexing, retrieval, query engines, chat engines, and agentic workflows in TypeScript

agents-inc Bundle

AI integration review patterns. Use when reviewing model API calls, prompt construction, LLM output handling, RAG pipelines, and tool-calling code. Covers prompt-injection call-chain tracing, output validation, token budgets, retry/timeout handling, streaming, and key/PII exposure.

agents-inc Bundle

Provider-agnostic patterns for LLM function calling, tool loops, and agentic workflows

tyler-r-kendrick Bundle

Use when creating software architecture diagrams, system visualizations, or technical drawings. Covers text-based and visual diagramming approaches for architecture communication. USE FOR: choosing diagram types, comparing diagramming tools, architecture visualization strategy, diagrams-as-code workflows, embedding diagrams in documentation DO NOT USE FOR: specific diagram syntax (use c4-diagrams, mermaidjs, uml, d2, plantuml, etc.), requirements documents (use documentation sub-skills)

tryboy869 Bundle

Build applications powered by GitHub Copilot using the Copilot SDK. Use when creating programmatic integrations with Copilot across Node.js/TypeScript, Python, Go, or .NET. Covers session management, custom tools, streaming, hooks, MCP servers, BYOK providers, session persistence, custom agents, skills, and deployment patterns. Requires GitHub Copilot CLI installed and a GitHub Copilot subscription (unless using BYOK).

tryboy869 Bundle

[Applies to: **/*.py] Definitive guidelines for writing robust, performant, and maintainable Python code using Hugging Face Transformers and the Hugging Face Hub.