本文へ移動
cccskills
無料GitHub で公開

mcp-sampling-critic

Expert guide for MCP client sampling (sampling/createMessage), Critic-in-the-Loop agentic quality gates, autonomous human-in-the-loop emulation, and multi-model consensus verification / Panduan ahli sampling MCP client, quality gate agen Critic-in-the-Loop, dan verifikasi konsensus multi-model.

日本語の概要は準備中です。原文の説明を表示しています。

インストール方法を見る

含まれるファイル(1)

  • SKILL.md6.8 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

mcp-sampling-critic — vibes-plug Skill

English | Bahasa Indonesia


<a name="english"></a>

English

Orchestration & Integration

Connects and orchestrates with mcp-server-architect, autonomous-red-teamer, ai-code-review-autonomous, speculative-multi-draft-synthesizer, anti-slop, and zero-to-prod-orchestrator to establish autonomous Critic-in-the-Loop validation before any state or disk mutations.

Description

Production protocol for leveraging Model Context Protocol (MCP v1.x) Client Sampling (sampling/createMessage) to create recursive adversarial quality gates. In standard architectures, tools execute code blindly upon invocation. With MCP Sampling, a specialized Critic engine pauses execution, initiates a nested sampling call to the host LLM (or a secondary frontier model), and asks the Critic model to inspect proposed diffs against the 7 Anti-Slop Pillars, security boundaries, and invariant state machines. Writes are only permitted when the Critic grants an APPROVED verdict.

Trigger Conditions

Activate this skill when:

  • Designing autonomous agent loops that modify filesystem files or execute database migrations.
  • Implementing the CRITIC_VALIDATOR swarm topology where an implementer agent's draft must pass an independent quality audit.
  • Eliminating AI-generated placeholders (// TODO), silent error suppressions, or SQL injection vectors before pull request creation.
  • Enforcing human-in-the-loop or critic-in-the-loop safeguards without requiring manual human clicking.

Critic-in-the-Loop Protocol Architecture

PROPOSED CODE DRAFT
        │
        ▼
┌───────────────────────────┐
│ STATIC REGEX & AST FILTER │  Instant rule scan (P1-P7 Anti-Slop, silent catches)
└─────────────┬─────────────┘
              │
  ┌───────────┴───────────┐
  ▼                       ▼
FAIL (Score < 85)     PASS (Score >= 85)
  │                       │
Reject immediately   ┌────▼────────────────────────┐
with suggestions     │ MCP SAMPLING REQUEST        │  sampling/createMessage
                     │ to Host LLM (Independent)   │
                     └────────────┬────────────────┘
                                  │
                                  ▼
                        FINAL CRITIC VERDICT
                     (APPROVED -> Write to disk)

1. MCP Sampling Request Construction (TypeScript)

export interface SamplingMessagePayload {
  messages: Array<{
    role: 'user' | 'assistant';
    content: { type: 'text'; text: string };
  }>;
  systemPrompt: string;
  maxTokens: number;
  modelPreferences?: {
    hints?: Array<{ name: string }>;
    costPriority?: number;
    speedPriority?: number;
    intelligencePriority?: number;
  };
}

export function buildCriticSamplingPayload(
  targetFile: string,
  proposedCode: string,
  staticFindings: Array<{ ruleName: string; message: string }>
): SamplingMessagePayload {
  const findingsSummary = staticFindings.length > 0
    ? staticFindings.map(f => `- ${f.ruleName}: ${f.message}`).join('\n')
    : 'None detected by initial AST filter.';

  return {
    systemPrompt: `You are the Sovereign Anti-Slop Critic (2026 Edition).
Perform a strict code audit against:
1. Zero placeholder stubs (// TODO, // ...rest of code).
2. Zero silent error suppression (empty catch blocks).
3. 5-state interactive UI contract (hover, focus-visible, active, disabled).
4. SQL injection prevention (parameterized queries only).
Output JSON: { "verdict": "APPROVED" | "REJECTED", "score": 0-100, "rationale": "..." }`,
    maxTokens: 2048,
    modelPreferences: {
      intelligencePriority: 1.0,
      costPriority: 0.2
    },
    messages: [
      {
        role: 'user',
        content: {
          type: 'text',
          text: `Target: ${targetFile}\nPreliminary AST Warnings:\n${findingsSummary}\n\nCode to Audit:\n\`\`\`typescript\n${proposedCode}\n\`\`\``
        }
      }
    ]
  };
}

<a name="bahasa-indonesia"></a>

Bahasa Indonesia

Integrasi Orkestrasi

Terhubung dan mengorkestrasikan skill mcp-server-architect, autonomous-red-teamer, ai-code-review-autonomous, speculative-multi-draft-synthesizer, anti-slop, dan zero-to-prod-orchestrator untuk menetapkan validasi Critic-in-the-Loop otonom sebelum mutasi file atau database.

Deskripsi

Protokol produksi untuk memanfaatkan Client Sampling pada Model Context Protocol (sampling/createMessage) guna membangun gerbang kualitas adversarial rekursif. Menggunakan MCP Sampling, server atau subagen menghentikan eksekusi sementara, melakukan panggilan sampling ke LLM host untuk mengaudit usulan perubahan kode terhadap 7 Pilar Anti-Slop, keamanan injeksi SQL, dan penanganan error. Kode hanya ditulis ke disk apabila mendapatkan status APPROVED.

Kondisi Pemicu

  • Merancang alur agen otonom yang memodifikasi file repositori atau migrasi basis data.
  • Menjalankan topologi swarm CRITIC_VALIDATOR di mana draf implementer harus diverifikasi auditor independen.
  • Menghapus stub placeholder malas (// TODO) dan penelanan error secara otomatis sebelum commit.

Pembuatan Payload Permintaan MCP Sampling (TypeScript)

export interface PayloadPesanSampling {
  messages: Array<{
    role: 'user' | 'assistant';
    content: { type: 'text'; text: string };
  }>;
  systemPrompt: string;
  maxTokens: number;
}

export function bangunPayloadSamplingCritic(
  fileTarget: string,
  drafKode: string,
  peringatanAwal: string[]
): PayloadPesanSampling {
  return {
    systemPrompt: `Anda adalah Auditor Anti-Slop Berdaulat (Edisi 2026).
Lakukan audit kode ketat terhadap:
1. Ketiadaan stub placeholder (// TODO, // ...rest of code).
2. Ketiadaan penelanan error diam-diam (empty catch block).
3. Kontrak 5-state UI interaktif (hover, focus-visible, active, disabled).
4. Pencegahan injeksi SQL (wajib parameterized query).
Keluarkan JSON: { "verdict": "APPROVED" | "REJECTED", "score": 0-100, "rationale": "..." }`,
    maxTokens: 2048,
    messages: [
      {
        role: 'user',
        content: {
          type: 'text',
          text: `File: ${fileTarget}\nPeringatan AST Awal: ${peringatanAwal.join(', ')}\n\nKode yang Diaudit:\n\`\`\`typescript\n${drafKode}\n\`\`\``
        }
      }
    ]
  };
}

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

Expert guide for automated and manual Web Accessibility (a11y) testing — axe-core, Pa11y, Playwright a11y, screen reader testing, and WCAG 2.2 Level AA/AAA compliance / Panduan ahli pengujian aksesibilitas web.

日本語の概要は準備中です。原文の説明を表示しています。

roedyrustam/vibes-plug772026年10月18日 更新

Expert guide for intelligent model cascading and routing — complexity-scored task routing from Flash/Haiku to Sonnet/Opus/Astra, dynamic escalation with quality gates, 40-60% token cost reduction while maintaining output quality / Panduan ahli untuk kaskade dan routing model cerdas — routing tugas berbasis skor kompleksitas dari Flash/Haiku ke Sonnet/Opus/Astra, eskalasi dinamis dengan gerbang kualitas, pengurangan biaya token 40-60% dengan kualitas output terjaga.

日本語の概要は準備中です。原文の説明を表示しています。

roedyrustam/vibes-plug772026年10月18日 更新

Expert guide for Affective Computing, emotional AI, and real-time sentiment analysis through native multimodal tokens (voice intonation and facial micro-expressions) / Panduan ahli komputasi afektif, AI emosional, dan analisis sentimen real-time melalui token multimodal native.

日本語の概要は準備中です。原文の説明を表示しています。

roedyrustam/vibes-plug772026年10月18日 更新

Expert guide for AI-assisted coding workflows — agentic code generation, multi-agent code swarms, self-healing CI/CD, automated PR review, spec-to-code pipelines, codebase knowledge graphs, and human-in-the-loop approval gates / Panduan ahli untuk workflow pengkodean berbasis AI — generasi kode agentic, code swarm multi-agen, CI/CD self-healing, review PR otomatis, pipeline spec-to-code, knowledge graph codebase, dan gate persetujuan human-in-the-loop.

日本語の概要は準備中です。原文の説明を表示しています。

roedyrustam/vibes-plug772026年10月18日 更新

Expert guide for autonomous Machine-to-Machine (M2M) agent settlement, dual-rail fiat & stablecoin micro-clearing, dynamic budget envelopes, and cryptographic agent invoicing / Panduan ahli settlement otonom antar-agen (M2M), kliring mikro dual-rail fiat & stablecoin, pagu anggaran dinamis, dan penagihan agen kriptografis.

日本語の概要は準備中です。原文の説明を表示しています。

roedyrustam/vibes-plug772026年10月18日 更新

Expert guide for long-term episodic memory integration (Mem0 v2, Letta/MemGPT, Zep v2), memory tier architecture, pgvector HNSW storage, and unified context management for autonomous AI agents / Panduan ahli untuk integrasi memori episodik jangka panjang (Mem0 v2, Letta/MemGPT, Zep v2), arsitektur tier memori, penyimpanan pgvector HNSW, dan manajemen konteks terpadu untuk agen AI otonom.

日本語の概要は準備中です。原文の説明を表示しています。

roedyrustam/vibes-plug772026年10月18日 更新

roedyrustam のスキルをすべて見る

このスキルの問題を報告する