Delegate independent tasks to specialized agents working concurrently with isolated context.
/escalate - Structured Escalation
escalate
Structured escalation with evidence. Surfaces blocking issues for human decision, referencing the Manifest hierarchy.
SKILL.md
Full skill instructions
/escalate - Structured Escalation
Goal
Surface a blocking issue for human decision with structured evidence, referencing the Manifest hierarchy.
Input
$ARGUMENTS = escalation context
Examples:
- "INV-G1 blocking after 3 attempts"
- "AC-1.2 blocking after 3 attempts"
- "Manual criteria AC-2.3 needs human review"
Principles
-
Evidence required - No lazy escalations. Must include what was tried and why it failed.
-
Structured options - Present possible paths forward with tradeoffs, not just "I'm stuck".
-
Respect hierarchy - Global Invariant blocking = task-level issue. AC blocking = deliverable-level issue.
Evidence Requirements
For blocking criterion escalation, MUST include:
- Which criterion - specific ID (INV-G*, AC-.)
- At least 3 attempts - what was tried
- Why each failed - not just "didn't work"
- Hypothesis - theory about root cause
- Options - possible paths forward with tradeoffs
Lazy escalations are NOT acceptable:
- "I can't figure this out"
- "This is hard"
- "INV-G1 is failing" (without attempts)
Escalation Types
Global Invariant Blocking
Task-level blocker. Cannot complete while this fails.
## Escalation: Global Invariant [INV-G{N}] Blocking
**Criterion:** [description]
**Type:** Global Invariant (task fails if violated)
**Impact:** Cannot complete task until resolved
### Attempts
1. **[Approach 1]** - What: ... Result: ... Why failed: ...
2. **[Approach 2]** - ...
3. **[Approach 3]** - ...
### Hypothesis
[Theory about why this is problematic]
### Possible Resolutions
1. **Fix root cause**: [description] - Effort: ... Risk: ...
2. **Amend invariant**: Relax to [new wording] - Rationale: ...
3. **Remove invariant**: Not applicable to this task - Rationale: ...
### Requesting
Human decision on path forward.
Acceptance Criteria Blocking
Deliverable-level blocker.
## Escalation: Acceptance Criteria [AC-{D}.{N}] Blocking
**Criterion:** [description]
**Type:** AC for Deliverable {D}: [name]
**Impact:** Deliverable incomplete
### Context
Other ACs in this deliverable: [statuses]
### Attempts
[same as above]
### Possible Resolutions
1. **Different implementation**: [approach]
2. **Amend criterion**: Change to [new wording]
3. **Remove criterion**: Not actually needed
4. **Descope deliverable**: Remove AC, deliverable still valuable
### Requesting
Human decision on path forward.
Manual Criteria Review
All automated criteria pass. Manual criteria need human verification.
## Escalation: Manual Criteria Require Human Review
All automated criteria pass.
### Manual Criteria Pending
- **AC-{D}.{N}**: [description] - How to verify: [from manifest]
### What Was Executed
[Brief summary]
Please review and confirm completion.
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
