{
  "description": "Design-phase artifacts: diagrams, decision records, design docs, contracts, schemas, threat models, and the reviews that gate them.",
  "display_name": "Solution architect",
  "keywords": ["architecture", "adr", "design-doc", "threat-model", "diagrams"],
  "links": {
    "documentation": "https://sananthanarayan.github.io/skilldrop/packs/solution-architect/"
  },
  "maintainers": [
    {
      "name": "sananthanarayan"
    }
  ],
  "first-value": {
    "audience-posture": "technical",
    "prerequisites": [],
    "starter-task": "Record an architecture decision your team already made",
    "starter-prompt": "Write an ADR: we're moving our session store from Redis to DynamoDB. We considered staying on Redis, DynamoDB, and Postgres; we chose DynamoDB for managed scaling and lower ops load.",
    "verification": "adr-generator returns an ADR with context, the options considered with their trade-offs, the decision, and its consequences.",
    "recovery": "If adr-generator does not activate, ask for it by name (\"use adr-generator\") and check that its folder exists in your skills folder (`~/.claude/skills/` by default)."
  },
  "requires": ["core"],
  "journey": {
    "when": "You have an agreed requirement and need to decide how to build it, then record that decision.",
    "you_bring": [
      "the ratified requirement or PRD",
      "known constraints: traffic, data, compliance, existing systems",
      "the options you are weighing, if you already have them"
    ],
    "time": "1–3 hours",
    "steps": [
      {
        "skill": "nfr-spec",
        "you_do": "Describe the feature or system and what you know about load, data and users.",
        "you_get": "Every non-functional category set to a measurable target, an explicit n/a, or a tagged default."
      },
      {
        "skill": "design-doc",
        "you_do": "Give it the requirement and the NFR targets.",
        "you_get": "A design doc with problem, goals and non-goals, options considered, the recommended approach, risks and rollout."
      },
      {
        "skill": "architecture-diagrams",
        "you_do": "Ask for diagrams of the recommended approach from the design doc.",
        "you_get": "Mermaid, PlantUML or C4 diagrams that must agree with the doc."
      },
      {
        "skill": "threat-model",
        "you_do": "Hand it the design doc and diagrams.",
        "you_get": "A STRIDE threat model with assets and trust boundaries, attack scenarios at each boundary crossing, and ranked, verifiable mitigations."
      },
      {
        "skill": "council-review",
        "you_do": "Put the design and threat model in front of the review panel.",
        "you_get": "Independent positions from each seat, the named cruxes, and a Chair's verdict that records dissent and what would change the decision.",
        "decide": "Gate G1: PROCEED or PROCEED WITH CONDITIONS moves on; REVISE sends you back to the design doc; SPLIT or RECONSIDER leaves the loop."
      },
      {
        "skill": "adr-generator",
        "you_do": "Ask for the ADR once the panel has agreed, including any conditions it set.",
        "you_get": "An ADR in MADR or Nygard format with context, the options and why each was rejected, the decision and its consequences."
      }
    ],
    "you_end_with": "NFR targets, a design doc with matching diagrams, a threat model, the panel's verdict, and an ADR that carries its conditions."
  }
}