escalation

Classify pipeline findings into escalation tiers and output recommended actions.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/nok0321/claude-pipeline --skill escalation-nok0321
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: escalation
Source: https://github.com/nok0321/claude-pipeline/tree/main/skills/escalation
Command: npx skills add https://github.com/nok0321/claude-pipeline --skill escalation-nok0321

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

パイプライン全体で発生する Findings を Tier 1(必ずユーザー確認)/ Tier 2(自律対応+事後報告)/ Tier 3(自律対応・報告不要)の3段階に分類し、エスカレーション判断を一貫して提供します。CLAUDE.md の Escalation Overrides を参照し、プロジェクト固有のルールを適用します。

Core Features & Use Cases

  • パイプライン全段階の Finding を Tier 分類する標準化フレームワークを提供
  • CLAUDE.md の Escalation Overrides を動的に適用してルールをカスタマイズ
  • エスカレーションキューのフォーマット出力と報告方針の一貫したガイドラインを提供

Quick Start

Finding を説明してエスカレーション分類を実行し、推奨アクションを出力します。

Frequently Asked Questions about escalation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I classify pipeline findings into escalation tiers for governance workflows?

Pipeline findings are classified into Tier 1 (user confirmation required), Tier 2 (autonomous with post-reporting), and Tier 3 (autonomous, no reporting) to ensure consistent escalation handling across all project phases.

How do I apply custom escalation overrides to a governance pipeline?

Custom escalation overrides are dynamically applied by referencing the Escalation Overrides section in CLAUDE.md, allowing project-specific rules to override standard tier classification logic.

How do I route escalation findings during the testing and reporting phases?

Escalation routing applies uniformly across planning, design, implementation, testing, and reporting scenarios by evaluating findings against deterministic rules, dynamic overrides, and user-guided decision points to output recommended actions.

What is the best way to standardize escalation queue formatting across pipeline phases?

Standardized escalation queue formatting provides consistent output structures and reporting guidelines, ensuring findings classified across tier levels generate uniform recommended actions throughout the pipeline workflow.

Can I use dynamic overrides for tier-classification without modifying deterministic rules?

Dynamic overrides from CLAUDE.md are applied alongside deterministic rules without modification, enabling project-specific escalation customization while preserving the baseline tier classification framework.

How does tier-classification handle user-guided decision points in a governance pipeline?

User-guided decision points integrate with deterministic rules and dynamic overrides to evaluate findings, routing Tier 1 items to mandatory user confirmation while allowing Tier 2 and Tier 3 autonomous handling.