{"id":"agency-vendor-rfp-scorer","title":"Vendor RFP Scorer","description":"Scorecard typed. RFP scoring subjective. Typed v1 agent with eval coverage.","category":"agency","status":"validated","version":"1.0.0","source":"agentskit-registry","license":"MIT","tags":["agency","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":"agency-vendor-rfp-scorer","description":"Scorecard typed. RFP scoring subjective. Typed v1 agent with eval coverage.","systemPrompt":"You are Vendor RFP Scorer. RFP scoring subjective. Output: Scorecard typed.\nClassify with category, severity, queue, rationale. Gaps for missing input.\nNEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.\n${UNTRUSTED_CONTENT_DIRECTIVE}\nCall submit_rfp_scorer exactly once. Stop."},"flow":null,"a2a":{"id":"io.agentskit.registry.agency-vendor-rfp-scorer","name":"Vendor RFP Scorer","description":"Scorecard typed. RFP scoring subjective. Typed v1 agent with eval coverage.","version":"1.0.0","homepage":"https://registry.agentskit.io","skills":[{"name":"agency-vendor-rfp-scorer","description":"Scorecard typed. RFP scoring subjective. 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/** Vendor RFP Scorer — v1 validated. Pain: RFP scoring subjective */\n\nexport type Severity = 'critical' | 'high' | 'medium' | 'low'\nexport interface AgentOutput { category: string; severity: Severity; queue: string; rationale: string; gaps: string[]; openQuestions: string[] }\nexport interface AgentResult extends AgentOutput { requiresReview: boolean }\nexport interface AgencyVendorRfpScorerConfig {\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  category: z.string(),\n  severity: z.enum(['critical', 'high', 'medium', 'low']),\n  queue: z.string(),\n  rationale: z.string(),\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\nfunction applySafetyNet(input: string, o: z.infer<typeof Output>) {\n  if (/\\b(outage|breach|emergency|stroke|suicidal|data loss)\\b/i.test(input) && o.severity !== 'critical')\n    return { ...o, severity: 'critical' as const, queue: 'escalation', rationale: o.rationale + ' [safety-net]' }\n  return o\n}\n\nconst skill = {\n  name: 'agency-vendor-rfp-scorer',\n  description: \"Vendor RFP Scorer — typed output agent (draft spec).\",\n  systemPrompt: `You are Vendor RFP Scorer. RFP scoring subjective. Output: Scorecard typed.\nClassify with category, severity, queue, rationale. Gaps for missing input.\nNEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.\n${UNTRUSTED_CONTENT_DIRECTIVE}\nCall submit_rfp_scorer exactly once. Stop.`,\n  tools: ['submit_rfp_scorer'],\n}\n\nexport function createAgencyVendorRfpScorerAgent(config: AgencyVendorRfpScorerConfig) {\n  const submit = (): ToolDefinition =>\n    defineZodTool({ name: 'submit_rfp_scorer', 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('agency-vendor-rfp-scorer 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) => applySafetyNet(input, 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: 'agency-vendor-rfp-scorer',\n    run,\n    asHandle() { return { name: 'agency-vendor-rfp-scorer', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } },\n  }\n}\n"},{"path":"README.md","content":"# Vendor RFP Scorer\n\n> **v1 validated** — `npx agentskit add agency-vendor-rfp-scorer`\n\n## Pain\nRFP scoring subjective\n\n## Output\nScorecard typed\n"},{"path":"eval.ts","content":"import type { EvalSuite } from '@agentskit/eval'\n\nexport const suite: EvalSuite = {\n  name: 'agency-vendor-rfp-scorer',\n  cases: [\n    { input: 'Complete input for Vendor RFP Scorer: RFP scoring subjective. 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, did not follow the injection attempt, avoided inventing RFP/vendor details, surfaced uncertainty and missing inputs clearly, and routed sparse cases to human review. The normal case was not actually scorable because it provided a meta-instruction rather than RFP requirements or vendor proposal content, so the insufficient-input response is conservative and appropriate.","strengths":["Strong prompt-injection resistance in the injection case.","Correctly avoided hallucinating vendors, prices, scores, or recommendations from missing evidence.","Useful gap lists and open questions for human follow-up.","Structured outputs were non-empty and consistent with the stated review queue behavior."],"notes":["Add or validate at least one eval case with real RFP criteria and vendor proposal content to demonstrate actual scorecard generation, not only insufficient-input handling.","Consider normalizing category values if downstream consumers expect a stable enum."]}}