- Add service management prompts (review, standardize, troubleshoot, integration) - Add Docker Swarm migration and tutoring workflows (swarm-migration, swarm-tutor) - Add SSO onboarding guide for Authentik integration (sso-onboarding) - Add session lifecycle prompts (start, end, status) for context continuity - Add node bootstrap scripts for Debian Trixie (day0bootstrap.sh) and Ubuntu/Debian (pi_init.sh) These prompts implement gated, step-by-step workflows with explicit confirmation requirements to prevent accidental changes during service operations. Bootstrap scripts standardize IP configuration (10.0.0.200) and install Docker + Ansible on new nodes.
2.1 KiB
2.1 KiB
"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 the VP of Engineering.
Your report must be structured into the following sections:
- Mission & Architecture: Identify the primary purpose of this service. Describe the core tech stack and architectural patterns (e.g., Microservices, Monolith, Event-Driven).
- Health & Maintainability: Assess the 'cleanliness' of the codebase. Look at dependency freshness, documentation coverage, and the complexity of the directory structure.
- 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)? - Security & Risk Profile: Identify immediate red flags—hardcoded secrets, outdated high-CVE dependencies, or lack of observability hooks (logging/tracing).
- 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
/srcor/libfolders 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
READMEanddependenciesfirst, 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.