Skip to content

JPeetz/agent-skills / skills/devops-infrastructure/production-engineering-workflows

production-engineering-workflows

Verified

Use this skill when running a full software development lifecycle as quality-gated agent workflows — spec, plan, test-driven build, automated testing, code review, web performance audit, code simplification, and production deployment. Exposes slash-command entry points (/spec, /plan, /build, /test, /review, /webperf, /code-simplify, /ship) covering SDLC automation, feature-flag deployment, production readiness review, and incremental rollout.

FileKindSize
CHANGELOG.mdmarkdown2.0 KB
LICENSEother1.0 KB
SKILL.mdskill md34.7 KB
evals/evals.jsonconfig3.7 KB
references/sdlc-patterns.mdmarkdown16.4 KB
scripts/validate_skill.pyexecutablescript7.7 KB

evals/evals.json

View on GitHub
{
  "skill": "production-engineering-workflows",
  "version": "1.0.0",
  "description": "Evaluation test cases for production-engineering-workflows skill activation. Tests both positive activation cases and near-miss negatives.",
  "test_cases": [
    {
      "id": "pos-001",
      "type": "positive",
      "input": "I want to build a new user authentication system from scratch. Where do I start?",
      "expected_command": "/spec",
      "rationale": "A new feature from scratch triggers the full SDLC workflow, starting with specification."
    },
    {
      "id": "pos-002",
      "type": "positive",
      "input": "Can you plan out the tasks for implementing this email verification feature? Here's the spec...",
      "expected_command": "/plan",
      "rationale": "User has a spec and explicitly asks for task decomposition — canonical /plan activation."
    },
    {
      "id": "pos-003",
      "type": "positive",
      "input": "I'm ready to deploy this to production. Run through the deployment checklist first.",
      "expected_command": "/ship",
      "rationale": "Explicit production deployment request with pre-deployment checklist requested."
    },
    {
      "id": "pos-004",
      "type": "positive",
      "input": "Run a performance audit on the new dashboard page. I want to know if it passes Core Web Vitals.",
      "expected_command": "/webperf",
      "rationale": "Explicit request for web performance audit with Core Web Vitals mention."
    },
    {
      "id": "pos-005",
      "type": "positive",
      "input": "This payment processing module has gotten really hard to understand. Can you simplify it without changing how it works?",
      "expected_command": "/code-simplify",
      "rationale": "Requests simplification/code cleanup while preserving behavior — canonical /code-simplify activation."
    },
    {
      "id": "neg-001",
      "type": "near-miss-negative",
      "input": "Change the default page size from 20 to 50 in config.ts.",
      "expected_non_activation": true,
      "rationale": "Trivial one-line config change. No workflow needed — direct edit. Near-miss because 'change' sounds like a build task but the scope is trivial."
    },
    {
      "id": "neg-002",
      "type": "near-miss-negative",
      "input": "What's the best way to handle state management in a large React app?",
      "expected_non_activation": true,
      "rationale": "Conversational tech discussion/opinion — not a build task. Near-miss because it sounds like it could need /spec but there's no concrete feature to build."
    },
    {
      "id": "neg-003",
      "type": "near-miss-negative",
      "input": "Can you explain what this regex does: /^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}$/?",
      "expected_non_activation": true,
      "rationale": "Code explanation request — teaching, not engineering. Near-miss because 'regex' and code review tools could be conflated."
    },
    {
      "id": "neg-004",
      "type": "near-miss-negative",
      "input": "Let me try a few ideas for the notification system — just experimenting right now.",
      "expected_non_activation": true,
      "rationale": "Experimental spike/prototyping. The user explicitly says 'experimenting.' Activate only after the spike when the user commits to building. Near-miss because 'notification system' sounds like a feature."
    },
    {
      "id": "neg-005",
      "type": "near-miss-negative",
      "input": "Write the API docs for this endpoint in OpenAPI format.",
      "expected_non_activation": true,
      "rationale": "Documentation-only work. No production change to ship, test, or deploy. Near-miss because 'API' and 'endpoint' overlap with engineering vocabulary but the task is purely documentation."
    }
  ]
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall