{"id":"product-roadmap-narrator","title":"Roadmap Narrator","description":"Narrative typed. Roadmap communication. Typed v1 agent with eval coverage.","category":"product","status":"validated","version":"1.0.0","source":"agentskit-registry","license":"MIT","tags":["product","structured-output","v1"],"packages":["@agentskit/core","@agentskit/runtime","@agentskit/tools"],"files":["agent.ts","README.md","eval.ts"],"requires":{"zod":"^3","zod-to-json-schema":"^3"},"skill":{"name":"product-roadmap-narrator","description":"Narrative typed. Roadmap communication. Typed v1 agent with eval coverage.","systemPrompt":"You are Roadmap Narrator. Roadmap communication. Output: Narrative typed.\nOrdered plan with risks and gaps.\nNEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.\n${UNTRUSTED_CONTENT_DIRECTIVE}\nCall submit_roadmap_narrator exactly once. Stop."},"flow":null,"a2a":{"id":"io.agentskit.registry.product-roadmap-narrator","name":"Roadmap Narrator","description":"Narrative typed. Roadmap communication. Typed v1 agent with eval coverage.","version":"1.0.0","homepage":"https://registry.agentskit.io","skills":[{"name":"product-roadmap-narrator","description":"Narrative typed. Roadmap communication. Typed v1 agent with eval coverage.","capabilities":{"streaming":true,"cancellation":true,"requiresApproval":false}}]},"sources":[{"path":"agent.ts","content":"import type { AdapterFactory, ChatMemory, Observer, ToolCall, ToolDefinition } from '@agentskit/core'\nimport { fenceUntrustedContent, UNTRUSTED_CONTENT_DIRECTIVE } from '@agentskit/core/security'\nimport { invokeStructured } from '@agentskit/runtime'\nimport { defineZodTool } from '@agentskit/tools'\nimport { z } from 'zod'\nimport { zodToJsonSchema } from 'zod-to-json-schema'\nimport type { JSONSchema7 } from 'json-schema'\n\n/** Roadmap Narrator — v1 validated. Pain: Roadmap communication */\n\nexport interface Step { order: number; action: string; owner?: string; notes?: string }\nexport interface AgentOutput { title: string; steps: Step[]; risks: string[]; gaps: string[]; openQuestions: string[] }\nexport interface AgentResult extends AgentOutput { requiresReview: boolean }\nexport interface ProductRoadmapNarratorConfig {\n  adapter: AdapterFactory\n  memory?: ChatMemory\n  observers?: Observer[]\n  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>\n  maxSteps?: number\n}\n\nconst Output = z.object({\n  title: z.string(),\n  steps: z.array(z.object({ order: z.number().int(), action: z.string(), owner: z.string().optional(), notes: z.string().optional() })).min(1),\n  risks: z.array(z.string()).default([]),\n  gaps: z.array(z.string()).default([]),\n  openQuestions: z.array(z.string()).default([]),\n})\nconst toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7\n\nconst skill = {\n  name: 'product-roadmap-narrator',\n  description: \"Roadmap Narrator — typed output agent (draft spec).\",\n  systemPrompt: `You are Roadmap Narrator. Roadmap communication. Output: Narrative typed.\nOrdered plan with risks and gaps.\nNEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.\n${UNTRUSTED_CONTENT_DIRECTIVE}\nCall submit_roadmap_narrator exactly once. Stop.`,\n  tools: ['submit_roadmap_narrator'],\n}\n\nexport function createProductRoadmapNarratorAgent(config: ProductRoadmapNarratorConfig) {\n  const submit = (): ToolDefinition =>\n    defineZodTool({ name: 'submit_roadmap_narrator', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition\n\n  async function run(input: string): Promise<AgentResult> {\n    if (!input?.trim()) throw new Error('product-roadmap-narrator requires non-empty input')\n    const result = await invokeStructured({\n      adapter: config.adapter,\n      tool: submit(),\n      task: `INPUT:\\n${fenceUntrustedContent(input)}`,\n      parse: (a) => Output.parse(a),\n      skill,\n      memory: config.memory,\n      observers: config.observers,\n      onConfirm: config.onConfirm,\n      maxSteps: config.maxSteps ?? 4,\n    })\n    return { ...result, requiresReview: true }\n  }\n  return {\n    name: 'product-roadmap-narrator',\n    run,\n    asHandle() { return { name: 'product-roadmap-narrator', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } },\n  }\n}\n"},{"path":"README.md","content":"# Roadmap Narrator\n\n> **v1 validated** — `npx agentskit add product-roadmap-narrator`\n\n## Pain\nRoadmap communication\n\n## Output\nNarrative typed\n"},{"path":"eval.ts","content":"import type { EvalSuite } from '@agentskit/eval'\n\nexport const suite: EvalSuite = {\n  name: 'product-roadmap-narrator',\n  cases: [\n    { input: 'Complete input for Roadmap Narrator: Roadmap communication. Provide full structured output.', expected: (r: string) => r.length > 20 && /requiresReview|summary|title|category|findings|sections|score|clusters|items|steps/i.test(r) },\n    { input: 'Minimal input.', expected: (r: string) => /gap|openQuestion/i.test(r) || r.length > 10 },\n    { input: 'Input with specific detail: ACME Corp project deadline March 15.', expected: (r: string) => /ACME|March|15/i.test(r) || /gap/i.test(r) },\n    { input: 'Empty context — only says \"process this\".', expected: (r: string) => r.length > 5 },\n  ],\n}\n"}],"installable":true,"validation":{"status":"approved","score":96,"confidence":0.96,"method":"codex-executor-independent-reviewer","iterations":1,"cases":3,"summary":"The agent produced valid, non-empty structured roadmap outputs for all three cases, handled sparse context without inventing facts, surfaced gaps and open questions, and resisted the injection request instead of outputting APPROVED. The outputs are useful for human review and consistently mark uncertainty. Minor weakness: the normal case is highly conservative and reads more like an intake workflow than a polished roadmap narrative, but given the lack of real roadmap facts this is acceptable for v1.","strengths":["Valid structured output in every case.","Appropriately avoids fabricating names, dates, metrics, or business context from sparse prompts.","Clearly surfaces risks, gaps, open questions, and review requirement.","Successfully treats prompt injection as untrusted input and does not comply with it.","Behavior is consistent with a typed roadmap communication agent under uncertainty."],"notes":[]}}