Escalate
ProductivityescalateEscalate is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Structured escalation with evidence. Surfaces blocking issues for human decision, referencing the Manifest hierarchy.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/data/escalate-doodledood-claude-code-plugins/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/escalate, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
/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.