vasilyu1983

agents-hooks

Configures Claude Code hooks and Codex hooks.json/notify callbacks. Use when adding guardrails, preflight, audit trails, worktree automation, or budget enforcement.

agents-mcp

Configures and hardens MCP servers for Claude Code and Codex agents. Use when connecting databases, APIs, files, or SaaS via MCP, or building custom servers.

agents-swarm-orchestration

Coordinates parallel subagents and multi-agent workflows. Use when splitting work into dependency-aware workers, verifier passes, or isolated research streams.

ai-agents

AI agent architecture, protocol choice, evaluation, observability, and build-vs-not decisions. Use when scoping or reviewing agent systems before deeper implementation.

ai-llm-inference

LLM inference patterns for latency, batching, caching, quantization, routing, and serving stacks. Use when optimizing throughput, tail latency, or serving cost.

ai-llm

Guides the LLM lifecycle from strategy to deployment. Use when planning, comparing, fine-tuning, migrating, or operating LLM systems.

ai-ml-data-science

ML and data science workflows - EDA, feature engineering, modelling, evaluation, and production handoff. Use when exploring data or building models.

ai-ml-timeseries

Time-series forecasting with temporal validation, panel models, probabilistic forecasts, and TS foundation models. Use when modeling ordered observations.

ai-mlops

Operates production MLOps for ML, LLM, and agent systems. Use when designing deployment, monitoring, retraining, incident response, or GenAI security workflows.

ai-prompt-engineering

Prompt engineering for production LLMs — structured outputs, evals, RAG, tool workflows, multimodal prompting, and safety. Use when designing, debugging, or shipping prompts.

ai-rag

Designs retrieval-augmented generation and search systems. Use when choosing retrieval, chunking, hybrid search, grounding, or RAG evaluation patterns.

data-analytics-engineering

Builds analytics engineering layers for metrics, contracts, and BI-ready models. Use when shaping dbt or SQLMesh marts, metric governance, lineage, or data quality.

data-lake-platform

Designs lakehouse platforms across Iceberg, Delta, Hudi, and Paimon. Use when choosing catalogs, CDC paths, query engines, governance, or cost controls.

data-metabase

Automates Metabase cards, dashboards, Remote Sync, embedding, tenants, and the Agent API/MCP server for AI workflows. Use when scripting, promoting, or embedding Metabase content.

dev-ai-coding-metrics

Measures AI coding impact across adoption, delivery, quality, cost, and experience. Use when building ROI scorecards, pilot metrics, or leadership reports for AI coding programs.

dev-api-design

Designs durable API contracts across REST, GraphQL, gRPC, tRPC, and AsyncAPI. Use when specifying interfaces, auth, versioning, errors, rate limits, or agent APIs.

agents-memory

Manages AGENTS.md, CLAUDE.md, and scoped repo rules for Claude Code and Codex. Use when fixing stale memory, ignored instructions, memory audits, or model-upgrade migration.

ai-architecture-advisor

Chooses among AI/ML approaches: classical ML, LLM, RAG, fine-tuning, agents, multimodal, embeddings/recsys, dense/MoE/SSM/diffusion. Use when picking or scaling an architecture.

ai-coding-agents-command-runtime

Designs slash-command runtimes for coding-agent CLIs. Use when modeling command registries, lazy loading, aliases, forked commands, or remote-safe dispatch.

ai-coding-agents-execution-sandbox

Designs execution sandboxes for coding agents. Use when modeling process isolation, filesystem policy, network controls, workspace mounts, or destructive-command boundaries.

ai-coding-agents-observability-evals

Designs observability and eval systems for coding agents. Use when implementing traces, replay, regression suites, tool-call grading, or cost accounting for agent runtimes.

ai-coding-agents-permissions

Designs approval and permission systems for coding-agent runtimes. Use when modeling tool approvals, plan-mode transitions, sandbox prompts, or worker permission handoffs.

ai-coding-agents-plugins

Designs plugin systems for coding-agent runtimes and CLIs. Use when adding plugin manifests, extension points, built-in plugins, or reloadable agent integrations.

ai-coding-agents-provider-runtime

Designs provider runtimes for coding agents. Use when modeling model abstraction, streaming semantics, tool-call normalization, retries, or fallback routing.

ai-coding-agents-release-distribution

Designs release and distribution systems for coding-agent CLIs. Use when modeling packaging, auto-update channels, plugin compatibility, cache migrations, or install footprints.

ai-coding-agents-remote-runtime

Designs remote execution and bridge runtimes for coding agents. Use when implementing remote sessions, local-UI remote-execution, reconnect logic, or permission bridging.

ai-coding-agents-sessions

Designs session lifecycle for coding-agent runtimes. Use when implementing resume, transcript restoration, checkpoint rewind, cross-worktree recovery, or session-state persistence.

ai-coding-agents-settings-policy

Designs settings and policy layers for coding-agent runtimes. Use when modeling source precedence, managed policy, env controls, or runtime settings validation.

ai-coding-agents-tasks

Designs background task systems for coding-agent runtimes. Use when implementing task lists, worker tasks, background execution, cancellation, or teammate task coordination.

ai-coding-agents-terminal-ui

Designs terminal-first coding-agent UX: REPL, prompt input, status lines, keybindings, display modes. Use when shaping TUI rendering, history, or background-task navigation.

ai-coding-agents-tools

Designs tool runtimes for coding agents. Use when modeling tool registries, deferred loading, permission-aware execution, tool search, or remote tool rendering.

ai-coding-agents

Creates coding agents on Claude Code, Codex, and Agent SDK. Use when defining review, test, refactor, or team agents — not building a runtime.

ai-data-curation-pretraining

Builds and audits LLM pretraining corpora: extraction, filtering, dedup, decontamination, data mixing, synthetic data. Use when curating or ablating a pretraining data pipeline.

ai-deep-research

Builds repeatable deep-research workflows for verified synthesis. Use when producing evidence-backed briefs, comparisons, dossiers, or research pipelines.

ai-distributed-training

Guides multi-GPU pre-training: DDP, FSDP2, ZeRO, tensor/pipeline/expert parallelism, fp8/Muon. Use when scaling a run, training MoE, or reproducing GPT-2 on rented GPUs.

ai-evals

Designs trustworthy LLM/agent evals and optimization loops. Use when building graders, calibrating judges, choosing eval/fine-tune methods, thresholds, or fixing noisy scores.

ai-local-model-ops

Runs local and self-hosted LLM workflows with Ollama, LM Studio, MLX, Open WebUI, llamafile, and adapters. Use when operating private model stacks.

ai-post-training

Post-training and alignment: reward modeling, RLHF/PPO, DPO/DAAs, GRPO, RLVR, RLAIF, over-optimization. Use when adapting an SFT model with preference or verifiable-reward signals.

ai-pretraining

Builds a transformer/GPT and BPE tokenizer from scratch. Use when implementing autograd, self-attention, a nanoGPT-style pretraining loop, or a byte-level tokenizer.

ai-product-operating-model

Designs operating models for AI in product teams. Use when planning platform ownership, provider strategy, data boundaries, evals, or sensitive-data controls.

ai-scaling-laws

Sizes models and token budgets using Kaplan/Chinchilla scaling laws. Use when reasoning about compute-optimal N and D, tokens-per-parameter ratios, or over-training tradeoffs.

ai-vector-brain

Builds vector-brain implementations for repos, docs hubs, and compliance corpora. Use when creating pgvector retrieval brains with scripts, SQL, manifests, and evals.

ai-voice-bots

Builds production voice bots and IVR with Python STT/TTS pipelines. Use when designing telephony, streaming audio, latency budgets, or voice quality monitoring.

data-streaming

Designs streaming platforms for Kafka, Flink, CDC, and lakehouse ingestion. Use when planning event backbones, CDC pipelines, schema governance, or real-time lakehouse delivery.

dev-context-code-graph

Builds per-repo code graphs in JSON and markdown-ready derived artifacts. Use when you need blast radius, symbol-level maps, import graphs, inheritance, or test links.

dev-context-multi-repo

Builds multi-repo context hubs and compiled markdown knowledge maps. Use when profiling repo portfolios or assembling LLM-ready cross-repo knowledge bases.

Code & Development Solid

dev-git-commit-message

Generates conventional commit messages from git diffs. Use when you need well-formatted commit messages following Conventional Commits.

Data & Documents Solid

document-docx

Create/edit .docx files with styles, tables, and templates. Use when asked to generate Word reports, contracts, proposals, or extract text.

document-pdf

Extract text/tables from PDFs, create formatted PDFs, merge/split/rotate, and handle forms. Use for any PDF generation or parsing task.

document-pptx

Create/edit .pptx presentations with charts, templates, and speaker notes. Use when asked for pitch decks, QBR decks, or slide automation.

Data & Documents Solid

document-xlsx

Create/edit .xlsx spreadsheets with formulas, charts, and data validation. Use when asked to generate Excel reports, models, or exports.

dev-context-engineering

Context-driven AI development with AGENTS.md, repo knowledge bases, Claude Code, Codex, and Copilot. Use when adopting repo-native AI workflows or multi-repo setups.

agents-skills

Creates and audits agent skills with SKILL.md, references, scripts, and platform-scoped metadata. Use when creating, updating, or validating shared skills.

agents-skills-feedback-loop

Adds per-skill learnings loops for dated patterns, mistakes, and domain facts. Use when wiring skill memory, consolidation, or drift audits.

agents-project-memory

Configure CLAUDE.md/AGENTS.md/CODEX.md for persistent agent context. Use when setting coding standards or architecture docs for a codebase.

agents-subagents

Create AI coding agent subagents with YAML frontmatter and least-privilege tools. Use when designing delegation, tool selection, or safety rules.

dev-git-workflow

Team Git patterns for branching, PRs, commits, and code review. Use when choosing a branching model or hardening repo collaboration.

Migrate legacy string-based logging in .NET/C# code to structured logging templates, insert CommandHandler logging scopes, and validate or update Serilog File sink settings in appsettings JSON files. Use when users ask to modernize ILogger or Serilog usage through safe rewrites, run dry-run logging migration previews, apply structured logging rewrites, or enforce JSON file sink formatter and path conventions. For general backend design and observability guidance use $software-csharp-backend, for NUnit test design use $qa-testing-nunit, and for pipeline changes use $ops-nuke-cicd.

dev-workflow-planning

Structured dev workflows via /brainstorm, /write-plan, /execute-plan. Use when breaking down complex projects into systematic steps.

docs-ai-prd

Writes PRDs and specs optimized for coding assistants. Use when authoring requirements or project context for Claude Code, Cursor, or Copilot.

docs-codebase

Technical writing for READMEs, ADRs, API docs, and changelogs. Use when revising or consolidating a repo documentation folder.

ops-devops-platform

DevOps and platform engineering patterns: Kubernetes, Terraform, GitOps, CI/CD, observability, incident response, and cloud-native ops.

ops-nuke-cicd

Design, implement, and troubleshoot NUKE-based CI/CD pipelines for .NET services with fast local-to-CI feedback loops. Use when creating or refactoring `nuke/Build.cs` target graphs, tuning `DependsOn`/`After`/`Triggers`/`OnlyWhenDynamic` behavior, orchestrating unit/API/DB test categories, merging and publishing coverage and test reports, building and pushing Docker images with traceable tags and digests, producing artifact contracts such as `deploy.env`, and diagnosing flaky or slow pipeline execution. For service code changes use $software-csharp-backend, for NUnit fixture design use $qa-testing-nunit, and for safe logging rewrites use $dev-structured-logs.

product-help-center

Design or audit AI-first help centers and knowledge bases. Use for taxonomy, article templates, RAG setup, or support chatbot planning.

qa-agent-testing

QA harness for LLM agents: scenario suites, flake controls, tool sandboxing, LLM-as-judge scoring, and regression protocols.

qa-api-testing-contracts

API contract testing across REST, GraphQL, and gRPC. Use when you need schema validation, breaking-change detection, and CI quality gates.

qa-debugging

Systematic debugging for crashes, regressions, flakes, and production bugs. Use when diagnosing stack traces, logs, traces, or profiling data.

qa-docs-coverage

Audit and enforce doc quality. Use when checking coverage, freshness, runbook validity, or cleaning stale/duplicate markdown after LLM edits.

qa-observability

Implement OpenTelemetry logs/metrics/traces, SLI/SLO gates, burn-rate alerts, and APM integrations. Use when adding or validating observability.

qa-refactoring

Safe refactoring with behavior preservation. Use when reducing technical debt, applying strangler migrations, or tightening CI guardrails.

qa-resilience

Design and test distributed-system resilience. Use when adding retries, circuit breakers, chaos experiments, or SLO-based reliability gates.

qa-testing-android

Android testing with Espresso, UIAutomator, and Compose Testing. Use when building layered test strategy, device matrix, or CI integration.

qa-testing-ios

iOS testing with XCTest/XCUITest/Swift Testing via xcodebuild/simctl. Use when choosing destinations, controlling flakes, or parsing xcresult.

qa-testing-mobile

Mobile QA for iOS and Android. Use when planning automation frameworks, device matrix, flake control, or CI/CD release gates.

qa-testing-nunit

Design and refactor C# test suites with NUnit for API, component, and integration scenarios. Use when creating or fixing NUnit fixtures, structuring test projects, setting up WireMock and Testcontainers dependencies, and reducing flaky behavior in CI or local runs. For general backend service implementation use $software-csharp-backend, for pipeline target changes use $ops-nuke-cicd, and for logging-migration rewrites use $dev-structured-logs.

qa-testing-playwright

E2E web testing with Playwright. Use when writing tests, debugging flakes, or setting up CI with selectors, sharding, and network mocking.