gkt-node 3.3.0

package/assets/.agent/skills/monday-automation/SKILL.md

@@ -0,0 +1,233 @@
+---
+name: monday-automation
+description: "Automate Monday.com work management including boards, items, columns, groups, subitems, and updates via Rube MCP (Composio). Always search tools first for current schemas."
+requires:
+  mcp: [rube]
+---
+
+# Monday.com Automation via Rube MCP
+
+Automate Monday.com work management workflows including board creation, item management, column value updates, group organization, subitems, and update/comment threads through Composio's Monday toolkit.
+
+## Prerequisites
+
+- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
+- Active Monday.com connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `monday`
+- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas
+
+## Setup
+
+**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
+
+
+1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
+2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `monday`
+3. If connection is not ACTIVE, follow the returned auth link to complete Monday.com OAuth
+4. Confirm connection status shows ACTIVE before running any workflows
+
+## Core Workflows
+
+### 1. Create and Manage Boards
+
+**When to use**: User wants to create a new board, list existing boards, or set up workspace structure.
+
+**Tool sequence**:
+1. `MONDAY_GET_WORKSPACES` - List available workspaces and resolve workspace ID [Prerequisite]
+2. `MONDAY_LIST_BOARDS` - List existing boards to check for duplicates [Optional]
+3. `MONDAY_CREATE_BOARD` - Create a new board with name, kind, and workspace [Required]
+4. `MONDAY_CREATE_COLUMN` - Add columns to the new board [Optional]
+5. `MONDAY_CREATE_GROUP` - Add groups to organize items [Optional]
+6. `MONDAY_BOARDS` - Retrieve detailed board metadata [Optional]
+
+**Key parameters**:
+- `board_name`: Name for the new board (required)
+- `board_kind`: "public", "private", or "share" (required)
+- `workspace_id`: Numeric workspace ID; omit for default workspace
+- `folder_id`: Folder ID; must be within `workspace_id` if both provided
+- `template_id`: ID of accessible template to clone
+
+**Pitfalls**:
+- `board_kind` is required and must be one of: "public", "private", "share"
+- If both `workspace_id` and `folder_id` are provided, the folder must exist within that workspace
+- `template_id` must reference a template the authenticated user can access
+- Board IDs are large integers; always use the exact value from API responses
+
+### 2. Create and Manage Items
+
+**When to use**: User wants to add tasks/items to a board, list existing items, or move items between groups.
+
+**Tool sequence**:
+1. `MONDAY_LIST_BOARDS` - Resolve board name to board ID [Prerequisite]
+2. `MONDAY_LIST_GROUPS` - List groups on the board to get group_id [Prerequisite]
+3. `MONDAY_LIST_COLUMNS` - Get column IDs and types for setting values [Prerequisite]
+4. `MONDAY_CREATE_ITEM` - Create a new item with name and column values [Required]
+5. `MONDAY_LIST_BOARD_ITEMS` - List all items on the board [Optional]
+6. `MONDAY_MOVE_ITEM_TO_GROUP` - Move an item to a different group [Optional]
+7. `MONDAY_ITEMS_PAGE` - Paginated item retrieval with filtering [Optional]
+
+**Key parameters**:
+- `board_id`: Board ID (required, integer)
+- `item_name`: Item name, max 256 characters (required)
+- `group_id`: Group ID string to place the item in (optional)
+- `column_values`: JSON object or string mapping column IDs to values
+
+**Pitfalls**:
+- `column_values` must use column IDs (not titles); get them from `MONDAY_LIST_COLUMNS`
+- Column value formats vary by type: status uses `{"index": 0}` or `{"label": "Done"}`, date uses `{"date": "YYYY-MM-DD"}`, people uses `{"personsAndTeams": [{"id": 123, "kind": "person"}]}`
+- `item_name` has a 256-character maximum
+- Subitem boards are NOT supported by `MONDAY_CREATE_ITEM`; use GraphQL via `MONDAY_CREATE_OBJECT`
+
+### 3. Update Item Column Values
+
+**When to use**: User wants to change status, date, text, or other column values on existing items.
+
+**Tool sequence**:
+1. `MONDAY_LIST_COLUMNS` or `MONDAY_COLUMNS` - Get column IDs and types [Prerequisite]
+2. `MONDAY_LIST_BOARD_ITEMS` or `MONDAY_ITEMS_PAGE` - Find the target item ID [Prerequisite]
+3. `MONDAY_CHANGE_SIMPLE_COLUMN_VALUE` - Update text, status, or dropdown with a string value [Required]
+4. `MONDAY_UPDATE_ITEM` - Update complex column types (timeline, people, date) with JSON [Required]
+
+**Key parameters for MONDAY_CHANGE_SIMPLE_COLUMN_VALUE**:
+- `board_id`: Board ID (integer, required)
+- `item_id`: Item ID (integer, required)
+- `column_id`: Column ID string (required)
+- `value`: Simple string value (e.g., "Done", "Working on it")
+- `create_labels_if_missing`: true to auto-create status/dropdown labels (default true)
+
+**Key parameters for MONDAY_UPDATE_ITEM**:
+- `board_id`: Board ID (integer, required)
+- `item_id`: Item ID (integer, required)
+- `column_id`: Column ID string (required)
+- `value`: JSON object matching the column type schema
+- `create_labels_if_missing`: false by default; set true for status/dropdown
+
+**Pitfalls**:
+- Use `MONDAY_CHANGE_SIMPLE_COLUMN_VALUE` for simple text/status/dropdown updates (string value)
+- Use `MONDAY_UPDATE_ITEM` for complex types like timeline, people, date (JSON value)
+- Column IDs are lowercase strings with underscores (e.g., "status_1", "date_2", "text"); get them from `MONDAY_LIST_COLUMNS`
+- Status values can be set by label name ("Done") or index number ("1")
+- `create_labels_if_missing` defaults differ: true for CHANGE_SIMPLE, false for UPDATE_ITEM
+
+### 4. Work with Groups and Board Structure
+
+**When to use**: User wants to organize items into groups, add columns, or inspect board structure.
+
+**Tool sequence**:
+1. `MONDAY_LIST_BOARDS` - Resolve board ID [Prerequisite]
+2. `MONDAY_LIST_GROUPS` - List all groups on a board [Required]
+3. `MONDAY_CREATE_GROUP` - Create a new group [Optional]
+4. `MONDAY_LIST_COLUMNS` or `MONDAY_COLUMNS` - Inspect column structure [Required]
+5. `MONDAY_CREATE_COLUMN` - Add a new column to the board [Optional]
+6. `MONDAY_MOVE_ITEM_TO_GROUP` - Reorganize items across groups [Optional]
+
+**Key parameters**:
+- `board_id`: Board ID (required for all group/column operations)
+- `group_name`: Name for new group (CREATE_GROUP)
+- `column_type`: Must be a valid GraphQL enum token in snake_case (e.g., "status", "text", "long_text", "numbers", "date", "dropdown", "people")
+- `title`: Column display title
+- `defaults`: JSON string for status/dropdown labels, e.g., `'{"labels": ["To Do", "In Progress", "Done"]}'`
+
+**Pitfalls**:
+- `column_type` must be exact snake_case values; "person" is NOT valid, use "people"
+- Group IDs are strings (e.g., "topics", "new_group_12345"), not integers
+- `MONDAY_COLUMNS` accepts an array of `board_ids` and returns column metadata including settings
+- `MONDAY_LIST_COLUMNS` is simpler and takes a single `board_id`
+
+### 5. Manage Subitems and Updates
+
+**When to use**: User wants to view subitems of a task or add comments/updates to items.
+
+**Tool sequence**:
+1. `MONDAY_LIST_BOARD_ITEMS` - Find parent item IDs [Prerequisite]
+2. `MONDAY_LIST_SUBITEMS_BY_PARENT` - Retrieve subitems with column values [Required]
+3. `MONDAY_CREATE_UPDATE` - Add a comment/update to an item [Optional]
+4. `MONDAY_CREATE_OBJECT` - Create subitems via GraphQL mutation [Optional]
+
+**Key parameters for MONDAY_LIST_SUBITEMS_BY_PARENT**:
+- `parent_item_ids`: Array of parent item IDs (integer array, required)
+- `include_column_values`: true to include column data (default true)
+- `include_parent_fields`: true to include parent item info (default true)
+
+**Key parameters for MONDAY_CREATE_OBJECT** (GraphQL):
+- `query`: Full GraphQL mutation string
+- `variables`: Optional variables object
+
+**Pitfalls**:
+- Subitems can only be queried through their parent items
+- To create subitems, use `MONDAY_CREATE_OBJECT` with a `create_subitem` GraphQL mutation
+- `MONDAY_CREATE_UPDATE` is for adding comments/updates to items (Monday's "updates" feature), not for modifying item values
+- `MONDAY_CREATE_OBJECT` is a raw GraphQL endpoint; ensure correct mutation syntax
+
+## Common Patterns
+
+### ID Resolution
+Always resolve display names to IDs before operations:
+- **Board name -> board_id**: `MONDAY_LIST_BOARDS` and match by name
+- **Group name -> group_id**: `MONDAY_LIST_GROUPS` with `board_id`
+- **Column title -> column_id**: `MONDAY_LIST_COLUMNS` with `board_id`
+- **Workspace name -> workspace_id**: `MONDAY_GET_WORKSPACES` and match by name
+- **Item name -> item_id**: `MONDAY_LIST_BOARD_ITEMS` or `MONDAY_ITEMS_PAGE`
+
+### Pagination
+Monday.com uses cursor-based pagination for items:
+- `MONDAY_ITEMS_PAGE` returns a `cursor` in the response for the next page
+- Pass the `cursor` to the next call; `board_id` and `query_params` are ignored when cursor is provided
+- Cursors are cached for 60 minutes
+- Maximum `limit` is 500 per page
+- `MONDAY_LIST_BOARDS` and `MONDAY_GET_WORKSPACES` use page-based pagination with `page` and `limit`
+
+### Column Value Formatting
+Different column types require different value formats:
+- **Status**: `{"index": 0}` or `{"label": "Done"}` or simple string "Done"
+- **Date**: `{"date": "YYYY-MM-DD"}`
+- **People**: `{"personsAndTeams": [{"id": 123, "kind": "person"}]}`
+- **Text/Numbers**: Plain string or number
+- **Timeline**: `{"from": "YYYY-MM-DD", "to": "YYYY-MM-DD"}`
+
+## Known Pitfalls
+
+### ID Formats
+- Board IDs and item IDs are large integers (e.g., 1234567890)
+- Group IDs are strings (e.g., "topics", "new_group_12345")
+- Column IDs are short strings (e.g., "status_1", "date4", "text")
+- Workspace IDs are integers
+
+### Rate Limits
+- Monday.com GraphQL API has complexity-based rate limits
+- Large boards with many columns increase query complexity
+- Use `limit` parameter to reduce items per request if hitting limits
+
+### Parameter Quirks
+- `column_type` for CREATE_COLUMN must be exact snake_case enum values; "people" not "person"
+- `column_values` in CREATE_ITEM accepts both JSON string and object formats
+- `MONDAY_CHANGE_SIMPLE_COLUMN_VALUE` auto-creates missing labels by default; `MONDAY_UPDATE_ITEM` does not
+- `MONDAY_CREATE_OBJECT` is a raw GraphQL interface; use it for operations without dedicated tools (e.g., create_subitem, delete_item, archive_board)
+
+### Response Structure
+- Board items are returned as arrays with `id`, `name`, and `state` fields
+- Column values include both raw `value` (JSON) and rendered `text` (display string)
+- Subitems are nested under parent items and cannot be queried independently
+
+## Quick Reference
+
+| Task | Tool Slug | Key Params |
+|------|-----------|------------|
+| List workspaces | `MONDAY_GET_WORKSPACES` | `kind`, `state`, `limit` |
+| Create workspace | `MONDAY_CREATE_WORKSPACE` | `name`, `kind` |
+| List boards | `MONDAY_LIST_BOARDS` | `limit`, `page`, `state` |
+| Create board | `MONDAY_CREATE_BOARD` | `board_name`, `board_kind`, `workspace_id` |
+| Get board metadata | `MONDAY_BOARDS` | `board_ids`, `board_kind` |
+| List groups | `MONDAY_LIST_GROUPS` | `board_id` |
+| Create group | `MONDAY_CREATE_GROUP` | `board_id`, `group_name` |
+| List columns | `MONDAY_LIST_COLUMNS` | `board_id` |
+| Get column metadata | `MONDAY_COLUMNS` | `board_ids`, `column_types` |
+| Create column | `MONDAY_CREATE_COLUMN` | `board_id`, `column_type`, `title` |
+| Create item | `MONDAY_CREATE_ITEM` | `board_id`, `item_name`, `column_values` |
+| List board items | `MONDAY_LIST_BOARD_ITEMS` | `board_id` |
+| Paginated items | `MONDAY_ITEMS_PAGE` | `board_id`, `limit`, `query_params` |
+| Update column (simple) | `MONDAY_CHANGE_SIMPLE_COLUMN_VALUE` | `board_id`, `item_id`, `column_id`, `value` |
+| Update column (complex) | `MONDAY_UPDATE_ITEM` | `board_id`, `item_id`, `column_id`, `value` |
+| Move item to group | `MONDAY_MOVE_ITEM_TO_GROUP` | `item_id`, `group_id` |
+| List subitems | `MONDAY_LIST_SUBITEMS_BY_PARENT` | `parent_item_ids` |
+| Add comment/update | `MONDAY_CREATE_UPDATE` | `item_id`, `body` |
+| Raw GraphQL mutation | `MONDAY_CREATE_OBJECT` | `query`, `variables` |

package/assets/.agent/skills/multi-agent-patterns/SKILL.md

@@ -0,0 +1,262 @@
+---
+name: multi-agent-patterns
+description: "Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures"
+source: "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/skills/multi-agent-patterns"
+risk: safe
+---
+
+## When to Use This Skill
+
+Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures
+
+Use this skill when working with master orchestrator, peer-to-peer, and hierarchical multi-agent architectures.
+# Multi-Agent Architecture Patterns
+
+Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.
+
+## When to Activate
+
+Activate this skill when:
+- Single-agent context limits constrain task complexity
+- Tasks decompose naturally into parallel subtasks
+- Different subtasks require different tool sets or system prompts
+- Building systems that must handle multiple domains simultaneously
+- Scaling agent capabilities beyond single-context limits
+- Designing production agent systems with multiple specialized components
+
+## Core Concepts
+
+Multi-agent systems address single-agent context limitations through distribution. Three dominant patterns exist: supervisor/orchestrator for centralized control, peer-to-peer/swarm for flexible handoffs, and hierarchical for layered abstraction. The critical design principle is context isolation—sub-agents exist primarily to partition context rather than to simulate organizational roles.
+
+Effective multi-agent systems require explicit coordination protocols, consensus mechanisms that avoid sycophancy, and careful attention to failure modes including bottlenecks, divergence, and error propagation.
+
+## Detailed Topics
+
+### Why Multi-Agent Architectures
+
+**The Context Bottleneck**
+Single agents face inherent ceilings in reasoning capability, context management, and tool coordination. As tasks grow more complex, context windows fill with accumulated history, retrieved documents, and tool outputs. Performance degrades according to predictable patterns: the lost-in-middle effect, attention scarcity, and context poisoning.
+
+Multi-agent architectures address these limitations by partitioning work across multiple context windows. Each agent operates in a clean context focused on its subtask. Results aggregate at a coordination layer without any single context bearing the full burden.
+
+**The Token Economics Reality**
+Multi-agent systems consume significantly more tokens than single-agent approaches. Production data shows:
+
+| Architecture | Token Multiplier | Use Case |
+|--------------|------------------|----------|
+| Single agent chat | 1× baseline | Simple queries |
+| Single agent with tools | ~4× baseline | Tool-using tasks |
+| Multi-agent system | ~15× baseline | Complex research/coordination |
+
+Research on the BrowseComp evaluation found that three factors explain 95% of performance variance: token usage (80% of variance), number of tool calls, and model choice. This validates the multi-agent approach of distributing work across agents with separate context windows to add capacity for parallel reasoning.
+
+Critically, upgrading to better models often provides larger performance gains than doubling token budgets. Claude Sonnet 4.5 showed larger gains than doubling tokens on earlier Sonnet versions. GPT-5.2's thinking mode similarly outperforms raw token increases. This suggests model selection and multi-agent architecture are complementary strategies.
+
+**The Parallelization Argument**
+Many tasks contain parallelizable subtasks that a single agent must execute sequentially. A research task might require searching multiple independent sources, analyzing different documents, or comparing competing approaches. A single agent processes these sequentially, accumulating context with each step.
+
+Multi-agent architectures assign each subtask to a dedicated agent with a fresh context. All agents work simultaneously, then return results to a coordinator. The total real-world time approaches the duration of the longest subtask rather than the sum of all subtasks.
+
+**The Specialization Argument**
+Different tasks benefit from different agent configurations: different system prompts, different tool sets, different context structures. A general-purpose agent must carry all possible configurations in context. Specialized agents carry only what they need.
+
+Multi-agent architectures enable specialization without combinatorial explosion. The coordinator routes to specialized agents; each agent operates with lean context optimized for its domain.
+
+### Architectural Patterns
+
+**Pattern 1: Supervisor/Orchestrator**
+The supervisor pattern places a central agent in control, delegating to specialists and synthesizing results. The supervisor maintains global state and trajectory, decomposes user objectives into subtasks, and routes to appropriate workers.
+
+```
+User Query -> Supervisor -> [Specialist, Specialist, Specialist] -> Aggregation -> Final Output
+```
+
+When to use: Complex tasks with clear decomposition, tasks requiring coordination across domains, tasks where human oversight is important.
+
+Advantages: Strict control over workflow, easier to implement human-in-the-loop interventions, ensures adherence to predefined plans.
+
+Disadvantages: Supervisor context becomes bottleneck, supervisor failures cascade to all workers, "telephone game" problem where supervisors paraphrase sub-agent responses incorrectly.
+
+**The Telephone Game Problem and Solution**
+LangGraph benchmarks found supervisor architectures initially performed 50% worse than optimized versions due to the "telephone game" problem where supervisors paraphrase sub-agent responses incorrectly, losing fidelity.
+
+The fix: implement a `forward_message` tool allowing sub-agents to pass responses directly to users:
+
+```python
+def forward_message(message: str, to_user: bool = True):
+    """
+    Forward sub-agent response directly to user without supervisor synthesis.
+    
+    Use when:
+    - Sub-agent response is final and complete
+    - Supervisor synthesis would lose important details
+    - Response format must be preserved exactly
+    """
+    if to_user:
+        return {"type": "direct_response", "content": message}
+    return {"type": "supervisor_input", "content": message}
+```
+
+With this pattern, swarm architectures slightly outperform supervisors because sub-agents respond directly to users, eliminating translation errors.
+
+Implementation note: Implement direct pass-through mechanisms allowing sub-agents to pass responses directly to users rather than through supervisor synthesis when appropriate.
+
+**Pattern 2: Peer-to-Peer/Swarm**
+The peer-to-peer pattern removes central control, allowing agents to communicate directly based on predefined protocols. Any agent can transfer control to any other through explicit handoff mechanisms.
+
+```python
+def transfer_to_agent_b():
+    return agent_b  # Handoff via function return
+
+agent_a = Agent(
+    name="Agent A",
+    functions=[transfer_to_agent_b]
+)
+```
+
+When to use: Tasks requiring flexible exploration, tasks where rigid planning is counterproductive, tasks with emergent requirements that defy upfront decomposition.
+
+Advantages: No single point of failure, scales effectively for breadth-first exploration, enables emergent problem-solving behaviors.
+
+Disadvantages: Coordination complexity increases with agent count, risk of divergence without central state keeper, requires robust convergence constraints.
+
+Implementation note: Define explicit handoff protocols with state passing. Ensure agents can communicate their context needs to receiving agents.
+
+**Pattern 3: Hierarchical**
+Hierarchical structures organize agents into layers of abstraction: strategic, planning, and execution layers. Strategy layer agents define goals and constraints; planning layer agents break goals into actionable plans; execution layer agents perform atomic tasks.
+
+```
+Strategy Layer (Goal Definition) -> Planning Layer (Task Decomposition) -> Execution Layer (Atomic Tasks)
+```
+
+When to use: Large-scale projects with clear hierarchical structure, enterprise workflows with management layers, tasks requiring both high-level planning and detailed execution.
+
+Advantages: Mirrors organizational structures, clear separation of concerns, enables different context structures at different levels.
+
+Disadvantages: Coordination overhead between layers, potential for misalignment between strategy and execution, complex error propagation.
+
+### Context Isolation as Design Principle
+
+The primary purpose of multi-agent architectures is context isolation. Each sub-agent operates in a clean context window focused on its subtask without carrying accumulated context from other subtasks.
+
+**Isolation Mechanisms**
+Full context delegation: For complex tasks where the sub-agent needs complete understanding, the planner shares its entire context. The sub-agent has its own tools and instructions but receives full context for its decisions.
+
+Instruction passing: For simple, well-defined subtasks, the planner creates instructions via function call. The sub-agent receives only the instructions needed for its specific task.
+
+File system memory: For complex tasks requiring shared state, agents read and write to persistent storage. The file system serves as the coordination mechanism, avoiding context bloat from shared state passing.
+
+**Isolation Trade-offs**
+Full context delegation provides maximum capability but defeats the purpose of sub-agents. Instruction passing maintains isolation but limits sub-agent flexibility. File system memory enables shared state without context passing but introduces latency and consistency challenges.
+
+The right choice depends on task complexity, coordination needs, and acceptable latency.
+
+### Consensus and Coordination
+
+**The Voting Problem**
+Simple majority voting treats hallucinations from weak models as equal to reasoning from strong models. Without intervention, multi-agent discussions devolve into consensus on false premises due to inherent bias toward agreement.
+
+**Weighted Voting**
+Weight agent votes by confidence or expertise. Agents with higher confidence or domain expertise carry more weight in final decisions.
+
+**Debate Protocols**
+Debate protocols require agents to critique each other's outputs over multiple rounds. Adversarial critique often yields higher accuracy on complex reasoning than collaborative consensus.
+
+**Trigger-Based Intervention**
+Monitor multi-agent interactions for specific behavioral markers. Stall triggers activate when discussions make no progress. Sycophancy triggers detect when agents mimic each other's answers without unique reasoning.
+
+### Framework Considerations
+
+Different frameworks implement these patterns with different philosophies. LangGraph uses graph-based state machines with explicit nodes and edges. AutoGen uses conversational/event-driven patterns with GroupChat. CrewAI uses role-based process flows with hierarchical crew structures.
+
+## Practical Guidance
+
+### Failure Modes and Mitigations
+
+**Failure: Supervisor Bottleneck**
+The supervisor accumulates context from all workers, becoming susceptible to saturation and degradation.
+
+Mitigation: Implement output schema constraints so workers return only distilled summaries. Use checkpointing to persist supervisor state without carrying full history.
+
+**Failure: Coordination Overhead**
+Agent communication consumes tokens and introduces latency. Complex coordination can negate parallelization benefits.
+
+Mitigation: Minimize communication through clear handoff protocols. Batch results where possible. Use asynchronous communication patterns.
+
+**Failure: Divergence**
+Agents pursuing different goals without central coordination can drift from intended objectives.
+
+Mitigation: Define clear objective boundaries for each agent. Implement convergence checks that verify progress toward shared goals. Use time-to-live limits on agent execution.
+
+**Failure: Error Propagation**
+Errors in one agent's output propagate to downstream agents that consume that output.
+
+Mitigation: Validate agent outputs before passing to consumers. Implement retry logic with circuit breakers. Use idempotent operations where possible.
+
+## Examples
+
+**Example 1: Research Team Architecture**
+```text
+Supervisor
+├── Researcher (web search, document retrieval)
+├── Analyzer (data analysis, statistics)
+├── Fact-checker (verification, validation)
+└── Writer (report generation, formatting)
+```
+
+**Example 2: Handoff Protocol**
+```python
+def handle_customer_request(request):
+    if request.type == "billing":
+        return transfer_to(billing_agent)
+    elif request.type == "technical":
+        return transfer_to(technical_agent)
+    elif request.type == "sales":
+        return transfer_to(sales_agent)
+    else:
+        return handle_general(request)
+```
+
+## Guidelines
+
+1. Design for context isolation as the primary benefit of multi-agent systems
+2. Choose architecture pattern based on coordination needs, not organizational metaphor
+3. Implement explicit handoff protocols with state passing
+4. Use weighted voting or debate protocols for consensus
+5. Monitor for supervisor bottlenecks and implement checkpointing
+6. Validate outputs before passing between agents
+7. Set time-to-live limits to prevent infinite loops
+8. Test failure scenarios explicitly
+
+## Integration
+
+This skill builds on context-fundamentals and context-degradation. It connects to:
+
+- memory-systems - Shared state management across agents
+- tool-design - Tool specialization per agent
+- context-optimization - Context partitioning strategies
+
+## References
+
+Internal reference:
+- [Frameworks Reference](./references/frameworks.md) - Detailed framework implementation patterns
+
+Related skills in this collection:
+- context-fundamentals - Context basics
+- memory-systems - Cross-agent memory
+- context-optimization - Partitioning strategies
+
+External resources:
+- [LangGraph Documentation](https://langchain-ai.github.io/langgraph/) - Multi-agent patterns and state management
+- [AutoGen Framework](https://microsoft.github.io/autogen/) - GroupChat and conversational patterns
+- [CrewAI Documentation](https://docs.crewai.com/) - Hierarchical agent processes
+- [Research on Multi-Agent Coordination](https://arxiv.org/abs/2308.00352) - Survey of multi-agent systems
+
+---
+
+## Skill Metadata
+
+**Created**: 2025-12-20
+**Last Updated**: 2025-12-20
+**Author**: Agent Skills for Context Engineering Contributors
+**Version**: 1.0.0