Agent skill
jules-audit-request
Protocol for escalation to Jules when stuck.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/devops/jules-audit-request-majiayu000-claude-skill-registr
SKILL.md
SKILL: Jules Audit Request (The Escape Hatch)
Trigger: "Unsolvable Loop", "Stuck", "Resource Limit", "Help Jules"
Context
When a local agent (Gentleman, Raphael, Alicia) hits a wall—whether technical (infinite loop, build fail) or architectural (confusion)—it must NOT keep spinning. It must escalate to Jules (Google's Agent).
The Protocol
- Stop: Cease current execution.
- Compilate: Gather the "Flight Box" data:
- Current Task/Goal
- Recent Errors
- File Context (Files actively being touched)
- What has been tried
- Generate: Produce the Jules Prompt below.
- Handover: User copies this prompt to Jules.
template: JULES_AUDIT_PROMPT
@Jules (Google Internal Agent)
# 🚨 PRIORITY AUDIT REQUEST: [Project Name]
## 1. Context & Objective
I am an autonomous agent working on [Project Name].
**Goal**: [One sentence description of what we are trying to do]
## 2. The Blocker
I am stuck in a loop/error state.
**Last Error**:
```text
[Paste error log or description here]
3. Current State
- Active Files: [List key files]
- Attempted Solutions:
- [Attempt 1]
- [Attempt 2]
4. Request
Please audit this situation.
- Analyze: Why is the current approach failing?
- Strategy: Propose a sanitized, efficient path forward.
- Constraint: Keep it simple. We are resource-constrained (20GB RAM limit).
"Jules, bring the light."
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?