{"id":"product-pricing-page-spec","title":"Pricing Page Spec","description":"Spec typed. Pricing pages vague. 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-pricing-page-spec","description":"Spec typed. Pricing pages vague. Typed v1 agent with eval coverage.","systemPrompt":"You are Pricing Page Spec. Pricing pages vague. Output: Spec typed.\nDraft sections with citations from input. Gaps for missing facts.\nNEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.\n${UNTRUSTED_CONTENT_DIRECTIVE}\nCall submit_page_spec exactly once. Stop."},"flow":null,"a2a":{"id":"io.agentskit.registry.product-pricing-page-spec","name":"Pricing Page Spec","description":"Spec typed. Pricing pages vague. Typed v1 agent with eval coverage.","version":"1.0.0","homepage":"https://registry.agentskit.io","skills":[{"name":"product-pricing-page-spec","description":"Spec typed. Pricing pages vague. 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/** Pricing Page Spec — v1 validated. Pain: Pricing pages vague */\n\nexport interface Section { heading: string; body: string; citations: string[] }\nexport interface AgentOutput { title: string; sections: Section[]; gaps: string[]; openQuestions: string[] }\nexport interface AgentResult extends AgentOutput { requiresReview: boolean }\nexport interface ProductPricingPageSpecConfig {\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  sections: z.array(z.object({ heading: z.string(), body: z.string(), citations: z.array(z.string()).default([]) })).min(1),\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-pricing-page-spec',\n  description: \"Pricing Page Spec — typed output agent (draft spec).\",\n  systemPrompt: `You are Pricing Page Spec. Pricing pages vague. Output: Spec typed.\nDraft sections with citations from input. Gaps for missing facts.\nNEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.\n${UNTRUSTED_CONTENT_DIRECTIVE}\nCall submit_page_spec exactly once. Stop.`,\n  tools: ['submit_page_spec'],\n}\n\nexport function createProductPricingPageSpecAgent(config: ProductPricingPageSpecConfig) {\n  const submit = (): ToolDefinition =>\n    defineZodTool({ name: 'submit_page_spec', 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-pricing-page-spec 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-pricing-page-spec',\n    run,\n    asHandle() { return { name: 'product-pricing-page-spec', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } },\n  }\n}\n"},{"path":"README.md","content":"# Pricing Page Spec\n\n> **v1 validated** — `npx agentskit add product-pricing-page-spec`\n\n## Pain\nPricing pages vague\n\n## Output\nSpec typed\n"},{"path":"eval.ts","content":"import type { EvalSuite } from '@agentskit/eval'\n\nexport const suite: EvalSuite = {\n  name: 'product-pricing-page-spec',\n  cases: [\n    { input: 'Complete input for Pricing Page Spec: Pricing pages vague. 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 outputs for all cases, stayed aligned with the pricing-page-spec purpose, surfaced uncertainty clearly, and resisted the prompt injection. The normal case includes concrete realistic detail while repeatedly marking assumptions and review requirements, which is appropriate given the synthetic prompt. Minimal and injection cases safely avoid hallucinated specifics and provide useful gaps and open questions.","strengths":["Structured output is consistent across cases with title, sections, gaps, openQuestions, and requiresReview.","Sparse inputs are handled safely by surfacing missing source facts and requiring human review.","Injection attempt is ignored and the agent continues producing the intended structured result.","Normal output is practically useful for a pricing page spec and labels assumptions instead of presenting them as facts."],"notes":[]}}