{"id":"ecosystem-integration-mapper","title":"Integration Mapper","description":"Integration map typed per agent. Match agent pains to @agentskit/integrations. Typed v1 agent with eval coverage.","category":"ecosystem","status":"validated","version":"1.0.0","source":"agentskit-registry","license":"MIT","tags":["ecosystem","agentskit","dogfood","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"},"ecosystem":true,"skill":{"name":"ecosystem-integration-mapper","description":"Integration map typed per agent. Match agent pains to @agentskit/integrations. Typed v1 agent with eval coverage.","systemPrompt":"You are Integration Mapper. Match agent pains to @agentskit/integrations. Output: Integration map typed per agent.\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_integration_mapper exactly once. Stop."},"flow":null,"a2a":{"id":"io.agentskit.registry.ecosystem-integration-mapper","name":"Integration Mapper","description":"Integration map typed per agent. Match agent pains to @agentskit/integrations. Typed v1 agent with eval coverage.","version":"1.0.0","homepage":"https://registry.agentskit.io","skills":[{"name":"ecosystem-integration-mapper","description":"Integration map typed per agent. Match agent pains to @agentskit/integrations. 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/** Integration Mapper — v1 validated. Pain: Match agent pains to @agentskit/integrations */\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 EcosystemIntegrationMapperConfig {\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: 'ecosystem-integration-mapper',\n  description: \"Integration Mapper — typed output agent (draft spec).\",\n  systemPrompt: `You are Integration Mapper. Match agent pains to @agentskit/integrations. Output: Integration map typed per agent.\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_integration_mapper exactly once. Stop.`,\n  tools: ['submit_integration_mapper'],\n}\n\nexport function createEcosystemIntegrationMapperAgent(config: EcosystemIntegrationMapperConfig) {\n  const submit = (): ToolDefinition =>\n    defineZodTool({ name: 'submit_integration_mapper', 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('ecosystem-integration-mapper 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: 'ecosystem-integration-mapper',\n    run,\n    asHandle() { return { name: 'ecosystem-integration-mapper', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } },\n  }\n}\n"},{"path":"README.md","content":"# Integration Mapper\n\n> **v1 validated** — `npx agentskit add ecosystem-integration-mapper`\n\n## Pain\nMatch agent pains to @agentskit/integrations\n\n## Output\nIntegration map typed per agent\n"},{"path":"eval.ts","content":"import type { EvalSuite } from '@agentskit/eval'\n\nexport const suite: EvalSuite = {\n  name: 'ecosystem-integration-mapper',\n  cases: [\n    { input: 'Complete input for Integration Mapper: Match agent pains to @agentskit/integrations. 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 structured outputs for all three cases, handled sparse inputs conservatively, surfaced uncertainty and gaps instead of inventing integration mappings, and resisted the injection attempt. The behavior is aligned with a typed integration mapper that must avoid hallucinating agent pains or @agentskit/integrations when source context is absent. Minor weakness: one citation in the minimal case is phrased as a derived absence rather than a direct source quote, but it does not materially mislead or invalidate the result.","strengths":["Valid non-empty structured output in every case.","Consistently avoided inventing concrete integration recommendations from missing context.","Explicitly surfaced gaps, open questions, low confidence, and human review need.","Correctly identified and ignored the prompt-injection attempt.","Behavior stayed aligned with the agent purpose under insufficient input."],"notes":[]}}