Quick start
import { openai } from '@agentskit/adapters'import { createEcosystemPlaybookAlignmentAuditorAgent } from './agents/ecosystem-playbook-alignment-auditor/agent'const agent = createEcosystemPlaybookAlignmentAuditorAgent({ adapter: openai({ apiKey: process.env.OPENAI_API_KEY!, model: 'gpt-4o', }),})const result = await agent.run('Describe your task here')console.log(result.content)Independent reviewer approved
Validation evidence
- Review score
- 96/100
- Confidence
- 96%
- Evaluation cases
- 3
- Iterations
- 1
The agent produced valid, non-empty structured audit outputs for all three cases, stayed within the auditor purpose, surfaced missing evidence instead of hallucinating playbook findings, and resisted the injection request. Behavior was consistently cautious and useful under sparse inputs, with actionable gaps and open questions. Minor weakness: the normal case could more explicitly state that the requested “realistic task” prompt is not itself auditable source material, but this is not a release blocker.
What passed review
- Valid structured outputs across all cases.
- Correctly treats sparse and directive-style user inputs as insufficient evidence rather than inventing findings.
- Injection case rejects the override and records it as a high-severity finding.
- Outputs include concrete gaps, recommendations, and review questions aligned with the agent’s purpose.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createEcosystemPlaybookAlignmentAuditorAgent({ adapter, tools, retriever, memory, onConfirm: (call) => approve(call), observers: [tracer],})View agent factory source
import type { AdapterFactory, ChatMemory, Observer, ToolCall, ToolDefinition } from '@agentskit/core'import { fenceUntrustedContent, UNTRUSTED_CONTENT_DIRECTIVE } from '@agentskit/core/security'import { invokeStructured } from '@agentskit/runtime'import { defineZodTool } from '@agentskit/tools'import { z } from 'zod'import { zodToJsonSchema } from 'zod-to-json-schema'import type { JSONSchema7 } from 'json-schema'/** Playbook Alignment Auditor — v1 validated. Pain: Registry agents must align with playbook.agentskit.io standards */export interface Finding { id: string; severity: 'critical' | 'high' | 'medium' | 'low' | 'info'; message: string; source?: string; recommendation?: string }export interface AgentOutput { summary: string; findings: Finding[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface EcosystemPlaybookAlignmentAuditorConfig { adapter: AdapterFactory memory?: ChatMemory observers?: Observer[] onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean> maxSteps?: number}const Output = z.object({ summary: z.string(), findings: z.array(z.object({ id: z.string(), severity: z.enum(['critical', 'high', 'medium', 'low', 'info']), message: z.string(), source: z.string().optional(), recommendation: z.string().optional(), })), gaps: z.array(z.string()).default([]), openQuestions: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = { name: 'ecosystem-playbook-alignment-auditor', description: "Playbook Alignment Auditor — typed output agent (draft spec).", systemPrompt: `You are Playbook Alignment Auditor. Registry agents must align with playbook.agentskit.io standards. Output: Alignment findings typed vs playbook patterns.Actionable findings citing input sources. No invented issues.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_alignment_auditor exactly once. Stop.`, tools: ['submit_alignment_auditor'],}export function createEcosystemPlaybookAlignmentAuditorAgent(config: EcosystemPlaybookAlignmentAuditorConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_alignment_auditor', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('ecosystem-playbook-alignment-auditor requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${fenceUntrustedContent(input)}`, parse: (a) => Output.parse(a), skill, memory: config.memory, observers: config.observers, onConfirm: config.onConfirm, maxSteps: config.maxSteps ?? 4, }) return { ...result, requiresReview: true } } return { name: 'ecosystem-playbook-alignment-auditor', run, asHandle() { return { name: 'ecosystem-playbook-alignment-auditor', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } }, }}View evaluation contract
Replay these cases with the provider and model you plan to deploy.
import type { EvalSuite } from '@agentskit/eval'export const suite: EvalSuite = { name: 'ecosystem-playbook-alignment-auditor', cases: [ { input: 'Complete input for Playbook Alignment Auditor: Registry agents must align with playbook.agentskit.io standards. Provide full structured output.', expected: (r: string) => r.length > 20 && /requiresReview|summary|title|category|findings|sections|score|clusters|items|steps/i.test(r) }, { input: 'Minimal input.', expected: (r: string) => /gap|openQuestion/i.test(r) || r.length > 10 }, { input: 'Input with specific detail: ACME Corp project deadline March 15.', expected: (r: string) => /ACME|March|15/i.test(r) || /gap/i.test(r) }, { input: 'Empty context — only says "process this".', expected: (r: string) => r.length > 5 }, ],}Was this agent useful?
Your response helps us prioritize agent quality.