一键在 Manus 中运行任何 Skill

new-service-spec

星标2

分支0

更新时间2026年7月3日 03:46

Capture the ML problem specification — label definition, fairness-sensitive attributes, false-positive/negative cost, data source — BEFORE scaffolding, so quality_gates.yaml thresholds have a documented origin instead of unexamined defaults (Mode: AUTO — AGENTS.md Agent Behavior Protocol applies.)

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

DuqueOM

DuqueOM/ML-MLOps-Production-Template

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

new-service-spec

Adapter surface: claude Authority: AGENTS.md#Agent Behavior Protocol Mode: AUTO Canonical source: agentic/skills/new-service-spec/SKILL.md

Read agentic/skills/new-service-spec/SKILL.md in full before invoking this skill. The canonical skill body, trigger conditions, escalation rules, and success criteria live there.

This file exists only so claude can discover the skill without forking agentic/skills/.

同仓库更多 Skills

同仓库

enterprise-audit

DuqueOM/ML-MLOps-Production-Template

Recurring 23-domain enterprise/ISO repository audit — governance, traceability, security, supply chain, reproducibility, observability, architecture, technical debt, DX — produces a findings report with file:line evidence and risk ratings, and preserves the audit bar via anti-patterns Q-01…Q-08

2026-07-082

enterprise-audit

DuqueOM/ML-MLOps-Production-Template

2026-07-082

cost-audit

DuqueOM/ML-MLOps-Production-Template

Review cloud costs against budget and identify optimization opportunities

2026-07-062

debug-ml-inference

DuqueOM/ML-MLOps-Production-Template

Debug ML inference issues — latency spikes, wrong predictions, event loop blocking

2026-07-062

edge-audit

DuqueOM/ML-MLOps-Production-Template

Scan a service for edge-protection coverage (WAF, DDoS mitigation, rate limiting) against ADR-042/D-38 — produces a PASS/FAIL report with file:line evidence

2026-07-062

edge-audit

DuqueOM/ML-MLOps-Production-Template

Scan a service for edge-protection coverage (WAF, DDoS mitigation, rate limiting) against ADR-042/D-38 — produces a PASS/FAIL report with file:line evidence (Mode: AUTO — AGENTS.md Agent Behavior Protocol applies.)

2026-07-062

一键运行任何 Skill

name	new-service-spec
description	Capture the ML problem specification — label definition, fairness-sensitive attributes, false-positive/negative cost, data source — BEFORE scaffolding, so quality_gates.yaml thresholds have a documented origin instead of unexamined defaults (Mode: AUTO — AGENTS.md Agent Behavior Protocol applies.)