nathan/homelab
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Releases Wiki Activity
homelab/.github/prompts/repo-exec-overview.prompt.md

2.1 KiB
Raw Blame History

"Act as a Principal Software Architect and DevOps Strategist. I am granting you terminal access to this repository. Your task is to perform a deep-dive analysis and generate a high-level Executive Overview for my VP.

Your report must be structured into the following sections:

  1. Mission & Architecture: Identify the primary purpose of this service. Describe the core tech stack and architectural patterns (e.g., Microservices, Monolith, Event-Driven).
  2. Health & Maintainability: Assess the 'cleanliness' of the codebase. Look at dependency freshness, documentation coverage, and the complexity of the directory structure.
  3. DevOps & CI/CD Posture: Analyze the .github, .gitlab, or Jenkinsfiles. How is this deployed? Are there robust testing suites, containerization (Docker/K8s), and Infrastructure as Code (Terraform/CDK)?
  4. Security & Risk Profile: Identify immediate red flags—hardcoded secrets, outdated high-CVE dependencies, or lack of observability hooks (logging/tracing).
  5. The 'So What?' (Strategic Recommendation): Provide 3-5 bullet points on what an executive needs to know regarding technical debt vs. feature velocity for this specific repo.

Instructions for Analysis:

  • Start by listing the files in the root directory.
  • Read the README.md, package.json/requirements.txt/go.mod, and any configuration files.
  • Examine the /src or /lib folders to understand the logic flow.
  • Do not output raw code unless it illustrates a critical failure point. Keep the tone professional, objective, and concise."

Why this works for a DevOps Leader

  • Contextual Roleplaying: By telling the AI to act as a Principal Architect, you're forcing it to prioritize system design over line-by-line syntax.
  • Chain of Thought: The "Instructions for Analysis" section ensures the model doesn't hallucinate. It forces it to check the README and dependencies first, which is exactly how a human lead would audit a new repo.
  • Risk Focus: Executives don't care about "neat code"; they care about risk. This prompt specifically hunts for security flaws and deployment bottlenecks.