AI-Agents-public

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

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.

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.

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

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.

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

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

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

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.

Systematic code review patterns and checklists. Use when reviewing PRs or diffs for correctness, security, readability, and maintainability.

Apply practical C# and .NET backend engineering standards for service implementation, refactoring, and backend-focused code reviews. Use when building or reviewing backend services for language best practices, project and layer boundaries, data-access patterns, resilience controls, observability, security baselines, and common backend anti-pattern detection. For deep NUnit fixture design use $qa-testing-nunit, for NUKE pipeline target work use $ops-nuke-cicd, and for deterministic logging rewrites use $dev-structured-logs.

Event-driven hooks for AI coding agents. Use when automating Claude Code or Codex CLI with stdin JSON and decision-control responses.

Configure and build MCP servers for AI agent tool integration. Use when connecting Claude Code or Codex to databases, APIs, or custom tools.

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

Reference for creating AI agent skills with SKILL.md structure. Use when building or improving modular skill files for Claude Code or Codex.

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

Coordinate parallel subagents in dependency-aware waves. Use when executing multi-task plans with Claude Code or Codex agent swarms.

Production AI agent patterns covering MCP, RAG, guardrails, observability, and ROI. Use when designing or evaluating agent systems.

LLM inference patterns — latency budgeting, caching, batching, quantization, and parallelism. Use when optimizing serving cost or tail latency.

Full LLM lifecycle skill — strategy selection, PEFT/LoRA, evaluation, and deployment. Use when building, fine-tuning, or operating LLM systems.

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

Time series forecasting — LightGBM, Transformers, temporal validation, feature engineering, and production deployment. Use when building TS models.

Production MLOps covering CI/CD, serving, drift monitoring, and GenAI security. Use when deploying or operating ML and LLM systems in production.

Prompt engineering for production LLMs — structured outputs, RAG, tool workflows, and safety. Use when designing or debugging prompts for LLM APIs.

RAG and search engineering — chunking, hybrid retrieval, reranking, and nDCG evaluation. Use when building retrieval-augmented generation pipelines.

Analytics engineering for reliable metrics and BI readiness. Use when building dbt models, defining metrics, or designing analytics layers.

Data lake and lakehouse patterns: ingestion, CDC, Iceberg/Delta/Hudi, Trino/DuckDB, orchestration, and governance. Self-hosted and cloud.

Metabase REST API automation: auth, export/upsert cards and dashboards, visualization_settings. Use when scripting Metabase via API.

SQL optimization for OLTP systems: EXPLAIN analysis, indexing, schema design, migrations, HA, and security across major SQL platforms.

Measure and optimize AI coding agent impact — adoption tracking, DORA/SPACE for AI teams, ROI frameworks, DX surveys, benchmarking. Use when measuring AI tool effectiveness or building metrics programs.

REST/GraphQL/gRPC/tRPC API design patterns. Use when designing APIs, writing OpenAPI specs, versioning, auth, or rate limiting.

Dependency management across npm, pip, cargo, and maven. Use when managing lockfiles, security scanning, versioning, or monorepo workspaces.

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

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.

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

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

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

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

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