eggboy
- 13 skills
- 0 followers
- 6 hours ago last updated
- ▌ Fastapi · eggboy bundleBuild and configure FastAPI applications following best practices with uv project setup, Pydantic models, dependency injection, async/sync endpoints, SSE streaming, and OpenAPI docs. Use when developing APIs with FastAPI or setting up new FastAPI projects. DO NOT use for general Python style (use python-best-practices) or dataframe workflows.
- ▌ Skillshare · eggboy bundleManages and syncs AI CLI skills across 50+ tools from a single source. Use this skill whenever the user mentions "skillshare", runs skillshare commands, manages skills (install, update, uninstall, sync, audit, check, diff, search), or troubleshoots skill configuration (orphaned symlinks, broken targets, sync issues). Covers both global (~/.config/skillshare/) and project (.skillshare/) modes. Also use when: adding new AI tool targets (Claude, Cursor, Windsurf, etc.), setting target include/exclude filters or copy vs symlink mode, using backup/restore or trash recovery, piping skillshare output to scripts (--json), setting up CI/CD audit pipelines, or building/sharing skill hubs (hub index, hub add).
- ▌ CLI Creator · eggboy bundleCreate command-line interface (CLI) tools following clig.dev best practices. Covers argument parsing, help text, error handling, output formatting, signals, and configuration. Supports Python (Click, Typer), Node.js (Commander), Go (Cobra), Rust (Clap), and Bash. Includes starter templates. DO NOT use for web applications, web servers, GUI apps, or long-running services.
- ▌ Agentic Eval · eggboyPatterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality Do NOT use for unit testing, code linting, static analysis, benchmarking non-agent outputs, or simple pass/fail validation without iteration.
- ▌ Skill Creator · eggboyCreate and update Agent Skills following the agentskills.io specification. Use when building reusable procedural knowledge, workflows, or tool integrations that extend AI agent capabilities. Applicable to GitHub Copilot, Claude, and other AI assistants. DO NOT use when the task can be accomplished with a simple prompt or when the user is not creating reusable skill packages.
- ▌ Write Judge Prompt · eggboy bundleDesign LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.
- ▌ Azure Cost Analysis · eggboy bundleAnalyze Azure service costs using the Microsoft.CostManagement REST API via az rest. Use when investigating Azure spending, querying cost breakdowns by resource, meter, or service, identifying cost anomalies, or providing cost reduction recommendations. Covers query construction, valid dimensions and filters, daily and monthly granularity, and common pitfalls. Triggers on Azure cost, Azure spending, Azure billing, cost analysis, cost breakdown, cost optimization, expensive resource, cost management query.
- ▌ Java Best Practices · eggboy bundleApply modern Java best practices (JDK 8–25) when writing, reviewing, refactoring, or migrating code. Covers step-by-step workflows for language features (records, sealed classes, pattern matching, virtual threads), Spring Boot integration, testing with JUnit 5, exception handling, DTO design, and JDK migration playbooks (8→11→17→21→25). DO NOT use for non-Java languages, Android SDK, or beginner tutorials.
- ▌ Python Best Practices · eggboy bundleApply modern Python best practices, conventions, and architectural patterns to production-ready code. Use when writing, reviewing, or refactoring Python to follow PEP 8, type hints, pytest and hypothesis testing, dataframe workflows (Pandas, Polars, DuckDB, Spark), and Python data model patterns (dunder methods, iterators, context managers, descriptors). For Python 3.12+ with pyproject.toml and Ruff. DO NOT use for FastAPI (use fastapi skill).
- ▌ Terraform Style Guide · eggboy bundleGenerate Terraform HCL code following HashiCorp's official style conventions and best practices. Use when writing, reviewing, or generating Terraform configurations, HCL code, infrastructure as code, Terraform modules, or refactoring existing Terraform projects. Not for Pulumi, CloudFormation, Bicep, or other IaC tools.
- ▌ Azure Verified Modules · eggboy bundleDevelop, review, and consume certified Azure Verified Modules (AVM) for Terraform following AVM requirements and best practices. Use when creating AVM-compliant modules, or configuring VNet injection, subnet delegation, or NSG rules in Terraform. DO NOT use for generic Terraform style guidance (use terraform-style-guide), non-AVM community modules, or non-Azure providers.
- ▌ Azure Naming Convention · eggboy bundleGenerate compliant Azure resource names following Microsoft Cloud Adoption Framework (CAF) best practices. Use when naming any Azure resource, generating IaC (Bicep, Terraform, ARM), scaffolding Azure projects, or reviewing existing resource names for compliance. Triggers on Azure resource naming, name Azure resources, naming convention, resource abbreviation, CAF naming.
- ▌ Microsoft Agent Framework · eggboy bundleBuild AI agents using the Microsoft Agent Framework Python SDK 1.0.0. Use when creating agents with OpenAI, Azure OpenAI, Foundry, or Anthropic providers. Covers Agent creation, function tools, workflows, orchestrations, streaming, structured outputs, MCP integration, middleware, and content types. Applies to agent-framework-core and provider packages.