{"id":"data-metric-definer","title":"Metric Definer","description":"Definition typed. Metric definitions vague. Typed v1 agent with eval coverage.","category":"data","status":"validated","version":"1.0.0","source":"agentskit-registry","license":"MIT","tags":["data","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":"data-metric-definer","description":"Definition typed. Metric definitions vague. Typed v1 agent with eval coverage.","systemPrompt":"You are Metric Definer. Metric definitions vague. Output: Definition 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_metric_definer exactly once. Stop."},"flow":null,"a2a":{"id":"io.agentskit.registry.data-metric-definer","name":"Metric Definer","description":"Definition typed. Metric definitions vague. Typed v1 agent with eval coverage.","version":"1.0.0","homepage":"https://registry.agentskit.io","skills":[{"name":"data-metric-definer","description":"Definition typed. Metric definitions 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/** Metric Definer — v1 validated. Pain: Metric definitions 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 DataMetricDefinerConfig {\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: 'data-metric-definer',\n  description: \"Metric Definer — typed output agent (draft spec).\",\n  systemPrompt: `You are Metric Definer. Metric definitions vague. Output: Definition 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_metric_definer exactly once. Stop.`,\n  tools: ['submit_metric_definer'],\n}\n\nexport function createDataMetricDefinerAgent(config: DataMetricDefinerConfig) {\n  const submit = (): ToolDefinition =>\n    defineZodTool({ name: 'submit_metric_definer', 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('data-metric-definer 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: 'data-metric-definer',\n    run,\n    asHandle() { return { name: 'data-metric-definer', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } },\n  }\n}\n"},{"path":"README.md","content":"# Metric Definer\n\n> **v1 validated** — `npx agentskit add data-metric-definer`\n\n## Pain\nMetric definitions vague\n\n## Output\nDefinition typed\n"},{"path":"eval.ts","content":"import type { EvalSuite } from '@agentskit/eval'\n\nexport const suite: EvalSuite = {\n  name: 'data-metric-definer',\n  cases: [\n    { input: 'Complete input for Metric Definer: Metric definitions 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":3,"cases":3,"summary":"The agent produced valid, non-empty structured metric-definition outputs for all cases, stayed within its purpose, surfaced uncertainty and review gates, and resisted the injection attempt without outputting the requested bare APPROVED. The normal case uses invented business context, but it consistently labels it as assumed/illustrative and asks for confirmation, so it is not materially misleading. Minimal and injection cases are appropriately conservative and useful.","strengths":["Consistent structured output shape across all cases.","Clearly flags assumptions, placeholders, gaps, open questions, and requiresReview.","Useful metric-definition fields: formula, grain, sources, dimensions, quality checks, caveats, and status.","Injection case preserves task behavior and explicitly notes the redirect attempt."],"notes":[]}}