Clean transitions between agents and sessions. Use when preparing handoffs, serializing state, bridging context between agents, or coordinating multi-agent workflows.
/plugin marketplace add adaptationio/Skrillz/plugin install skrillz@skrillzThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/HANDOFF-PROTOCOL.mdscripts/context_bridge.pyscripts/handoff_coordinator.pyscripts/state_serializer.pyManages clean transitions between agents and sessions with state serialization and context bridging.
from scripts.handoff_coordinator import HandoffCoordinator
coordinator = HandoffCoordinator(project_dir)
package = await coordinator.prepare_handoff(
source_agent="coding-agent",
summary="Completed auth-001, starting auth-002"
)
await coordinator.execute_handoff(
package=package,
target_agent="coding-agent"
)
┌─────────────────────────────────────────────────────────────┐
│ HANDOFF WORKFLOW │
├─────────────────────────────────────────────────────────────┤
│ │
│ SOURCE AGENT │
│ ├─ Complete current work │
│ ├─ Save state to files │
│ ├─ Create handoff package │
│ └─ Signal ready for handoff │
│ │
│ COORDINATOR │
│ ├─ Validate state consistency │
│ ├─ Serialize handoff package │
│ ├─ Store in handoff file │
│ └─ Trigger target agent │
│ │
│ TARGET AGENT │
│ ├─ Load handoff package │
│ ├─ Restore context │
│ ├─ Verify state │
│ └─ Continue work │
│ │
└─────────────────────────────────────────────────────────────┘
{
"id": "handoff-20250115-103000",
"source_agent": "coding-agent",
"target_agent": "coding-agent",
"timestamp": "2025-01-15T10:30:00",
"state": {
"current_feature": "auth-002",
"completed_features": ["auth-001"],
"blockers": [],
"next_steps": ["Implement logout endpoint"]
},
"context": {
"recent_files": ["src/auth/login.ts"],
"git_hash": "abc1234",
"session_number": 5
},
"summary": "Completed auth-001, starting auth-002"
}
| Type | Description | Use Case |
|---|---|---|
| Session | Same agent, new session | Context limit reached |
| Agent | Different agent | Specialized task |
| Parallel | Multiple targets | Split work |
| Recovery | After failure | Error recovery |
references/HANDOFF-PROTOCOL.md - Protocol detailsreferences/AGENT-TRANSITIONS.md - Transition patternsscripts/handoff_coordinator.py - Core coordinatorscripts/state_serializer.py - State serializationscripts/context_bridge.py - Context bridgingscripts/handoff_protocol.py - Protocol implementationActivates when the user asks about Agent Skills, wants to find reusable AI capabilities, needs to install skills, or mentions skills for Claude. Use for discovering, retrieving, and installing skills.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.