메뉴
Runs a dynamic Pi Fabric workflow with code-held phases, fan-out, pipelines, structured agents, and synthesis. Use for large audits, migrations, parallel research, or explicit workflow requests.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Creates a custom persistent Pi Fabric supervisor or advisor. Use for ambient supervision, ongoing peer review, an advisor, or a goal watcher without another extension.
Runs a bounded multi-perspective Pi Fabric council with independent reviewers and optional synthesis. Use for architecture choices, plans, reviews, and adversarial cross-checking.
Multi-model deliberation. Up to 8 distinct models answer in parallel with web-capable tools, then a judge compares consensus, contradictions, coverage gaps, unique insights, and blind spots. Use when the cost of being wrong justifies multiple completions.
Recursively decomposes oversized tasks into bounded child Pi agents with fresh context windows. Use for whole-repo audits, massive-context analysis, and multi-file refactors that do not fit one context.
Uses Fabric's typed Schema evidence loop and, when enabled, its bounded local-file transaction channel. Use when surprise must void a plan and mutation claims need explicit postconditions.
Creates a self-organizing team of persistent Pi Fabric actors with durable topics, mailboxes, and compare-and-swap tasks. Use for messenger-like collaboration and long-lived delegated work.
| name | fabric-workflow |
| description | Runs a dynamic Pi Fabric workflow with code-held phases, fan-out, pipelines, structured agents, and synthesis. Use for large audits, migrations, parallel research, or explicit workflow requests. |
| disable-model-invocation | true |
Put the complete loop, phases, and branches in one type-checked fabric_exec program.
Core surfaces:
agent(prompt, { label, tools?, schema?, ... }) for a bounded worker; label every call.parallel(thunks, { concurrency }) for fan-out; pass functions, not promises.pipeline(items, ...stages) for sequential stages per item with cross-item concurrency.workflow.configure, phase, workflow.item, workflow.event, and workflow.log for dashboard progress.workflow.budget plus top-level agentBudget/tokenBudget for bounded runs.Use JSON Schema when machine-readable output makes aggregation safer. A reliable shape is discover → analyze in parallel → adversarially verify:
await workflow.configure({
name: "Request analysis",
description: "Discover, analyze, and verify bounded work items",
});
await phase("Discover", { total: 1 });
const inventory = await agent<{ items: string[] }>(
"Discover the bounded work items. Return structured output.",
{
label: "inventory",
tools: ["read", "grep", "find", "ls"],
schema: {
type: "object",
properties: { items: { type: "array", items: { type: "string" } } },
required: ["items"],
additionalProperties: false,
},
},
);
await phase("Analyze", { total: inventory.items.length });
const findings = await parallel(
inventory.items.map((item) => () =>
agent(`Analyze this bounded item with evidence: ${item}`, {
label: `analyze ${item}`.slice(0, 50),
tools: ["read", "grep", "find", "ls"],
}),
),
{ concurrency: 8 },
);
await phase("Verify", { total: 1 });
const result = await agent(
`Adversarially verify these findings, remove unsupported claims, and synthesize:\n${JSON.stringify(findings)}`,
{ label: "verify synthesis", tools: ["read", "grep", "find", "ls"] },
);
await workflow.event({ message: "Verification complete", level: "success" });
return result;
Adapt phases and tools to the request. For edits, partition path ownership or use worktree: true; never let concurrent workers edit the same files. Include a verifier when conclusions combine multiple workers. Use agents.spawn plus status/steer instead of blocking agent() only when a valuable long-running worker must be observed and redirected between turns.