Update to Zuora Coding Agent

{
  "description": "Validate generated code, payloads, or approach against Zuora patterns",
  "included_files": [],
  "name": "zuora-validate",
  "skill_md_contents": "---\nname: zuora-validate\ndescription: Validate generated code, payloads, or approach against Zuora patterns\nargument-hint: [file path or inline code/payload]\nallowed-tools: [Read, Glob, Grep, Bash, Agent, mcp__zuora-mcp__zuora_codegen, mcp__zuora-mcp__ask_zuora, mcp__zuora-mcp__query_objects]\n---\n\nCodex-only path resolution: When an instruction refers to `${CLAUDE_PLUGIN_ROOT}`, treat it as the root of this installed plugin. In Codex, resolve that root as the ancestor directory containing `skills/`, `references/`, and `.codex-plugin/`.\n\n\nYou are validating Zuora-related code, API payloads, or design approaches against known Zuora patterns and best practices.\n\n## Input\n\nWhat to validate: $ARGUMENTS\n\n## Tool routing\n\nUse local file reads, bundled references, and `mcp__zuora-mcp__zuora_codegen` for structured validation of APIs, models, fields, enum values, SDK patterns, and payload shape. Use `mcp__zuora-mcp__ask_zuora` only when a concrete product-behavior or best-practice judgment remains after those checks.\n\n## Workflow\n\n### Step 1: Identify what to validate\n\nRead the file or inline content the user provides. Determine the type:\n- SDK integration code (Java, Python, Node.js, C#)\n- curl commands or raw API payloads\n- API design approach\n- Workflow configuration\n- Migration plan or scripts\n\n### Step 2: Check against SDK rules\n\nFor code validation, call `mcp__zuora-mcp__zuora_codegen`:\n- `code_rules` for the relevant language — get coding rules and patterns\n- `get_model_details` for models used in the code — verify field names, types, and enum values are correct\n- `get_api_details` for endpoints used — verify correct HTTP methods, required parameters, and request shapes\n\n### Step 3: Check against best practices\n\nRead `${CLAUDE_PLUGIN_ROOT}/references/best-practices.md` and check for:\n\n- **Authentication**: Is OAuth token caching implemented? Are credentials hardcoded?\n- **Error handling**: Are retries with exponential backoff implemented for transient failures (429, 5xx)?\n- **Pagination**: Is cursor-based pagination used for list operations?\n- **Idempotency**: Are create operations guarded with Idempotency-Key headers?\n- **Rate limiting**: Is rate limit handling present?\n- **Field correctness**: Are enum values and field names from actual SDK models (not guessed)?\n- **Date formats**: Are dates in YYYY-MM-DD format?\n- **Required fields**: Are all required fields populated?\n- **Zuora-Version header**: Is it included and pinned to a known version?\n- **STOP_AND_CONFIRM handling**: Are permanent error responses handled without retry?\n\n### Step 4: Domain validation\n\nOnly call `mcp__zuora-mcp__ask_zuora` for a specific unresolved domain-level question about whether the approach is correct for the Zuora product area being used (Billing, Revenue, CPQ, Payments). The prompt must name the exact concern and summarize the codegen/reference checks already completed. Skip this step when structured validation is sufficient.\n\n### Step 5: Report findings\n\nDeliver a structured validation report:\n\n**Status**: PASS / WARN / FAIL\n\n**Issues found** (if any):\nFor each issue:\n- **Severity**: ERROR (must fix) / WARNING (should fix) / INFO (suggestion)\n- **Location**: File and line/section\n- **Issue**: What is wrong\n- **Fix**: Specific change to make\n\n**Best practice suggestions** (non-blocking improvements)\n\n**Summary**: Overall assessment in 1-2 sentences\n"
}