跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
其他技能

escalation-governance

Assess whether to escalate models. Use when evaluating reasoning depth.

athola · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add athola/claude-night-market --skill escalation-governance

技能说明


name: escalation-governance description: 'Assess whether to escalate models. Use when evaluating reasoning depth.' alwaysApply: false category: agent-workflow tags:

  • escalation
  • model-selection
  • governance
  • agents
  • orchestration dependencies: [] estimated_tokens: 800 model_hint: standard

Table of Contents

Escalation Governance

Overview

Model escalation (haiku→sonnet→opus) trades speed/cost for reasoning capability. This trade-off must be justified.

Core principle: Escalation is for tasks that genuinely require deeper reasoning, not for "maybe a smarter model will figure it out."

The Iron Law

NO ESCALATION WITHOUT INVESTIGATION FIRST

Verification: Run the command with --help flag to verify availability.

Escalation is never a shortcut. If you haven't understood why the current model is insufficient, escalation is premature.

When to Escalate

Legitimate escalation triggers:

TriggerDescriptionExample
Genuine complexityTask inherently requires nuanced judgmentSecurity policy trade-offs
Reasoning depthMultiple inference steps with uncertaintyArchitecture decisions
Novel patternsNo existing patterns applyFirst-of-kind implementation
High stakesError cost justifies capability investmentProduction deployment
Ambiguity resolutionMultiple valid interpretations need weighingSpec clarification

When NOT to Escalate

Illegitimate escalation triggers:

Anti-PatternWhy It's WrongWhat to Do Instead
"Maybe smarter model will figure it out"This is thrashingInvestigate root cause
Multiple failed attemptsSuggests wrong approach, not insufficient capabilityQuestion your assumptions
Time pressureUrgency doesn't change task complexitySystematic investigation is faster
Uncertainty without investigationYou haven't tried to understand yetGather evidence first
"Just to be safe"False safety - wastes resourcesAssess actual complexity

Decision Framework

Before escalating, answer these questions:

1. Have I understood the problem?

  • Can I articulate why the current model is insufficient?
  • Have I identified what specific reasoning capability is missing?
  • Is this a capability gap or a knowledge gap?

If knowledge gap: Gather more information, don't escalate.

2. Have I investigated systematically?

  • Did I read error messages/outputs carefully?
  • Did I check for similar solved problems?
  • Did I form and test a hypothesis?

If not investigated: Complete investigation first.

3. Is escalation the right solution?

  • Would a different approach work at current model level?
  • Is the task inherently complex, or am I making it complex?
  • Would breaking the task into smaller pieces help?

If decomposable: Break down, don't escalate.

4. Can I justify the trade-off?

  • What's the cost (latency, tokens, money) of escalation?
  • What's the benefit (accuracy, safety, completeness)?
  • Is the benefit proportional to the cost?

If not proportional: Don't escalate.

Escalation Protocol

When escalation IS justified:

  1. Document the reason - State why current model is insufficient
  2. Specify the scope - What specific subtask needs higher capability?
  3. Define success - How will you know the escalated task succeeded?
  4. Return promptly - Drop back to efficient model after reasoning task

Common Rationalizations

ExcuseReality
"This is complex"Complex for whom? Have you tried?
"Better safe than sorry"Safety theater wastes resources
"I tried and failed"How many times? Did you investigate why?
"The user expects quality"Quality comes from process, not model size
"Just this once"Exceptions become habits
"Time is money"Systematic approach is faster than thrashing

Agent Schema

Agents can declare escalation hints in frontmatter:

model: haiku
escalation:
  to: sonnet                 # Suggested escalation target
  hints:                     # Advisory triggers (orchestrator may override)
    - security_sensitive     # Touches auth, secrets, permissions
    - ambiguous_input        # Multiple valid interpretations
    - novel_pattern          # No existing patterns apply
    - high_stakes            # Error would be costly

Verification: Run the command with --help flag to verify availability.

Key points:

  • Hints are advisory, not mandatory
  • Orchestrator has final authority
  • Orchestrator can escalate without hints (broader context)
  • Orchestrator can ignore hints (task is actually simple)

Orchestrator Authority

The orchestrator (typically Opus) makes final escalation decisions:

Can follow hints: When hint matches observed conditions Can override to escalate: When context demands it (even without hints) Can override to stay: When task is simpler than hints suggest Can escalate beyond hint: Go to opus even if hint sa

阅读完整来源 ↗