"create workflow", "automate", "process"?
create_workflow + start_workflow
← Skill registry
Agent infrastructurePublic skills
Workflow Orchestration
Multi-step workflow engine — create processes with approval gates, advance steps, handle failures with retry/rollback, and track all state transitions.
What this skill teaches
A reusable playbook for a specific kind of work.
An MCP server tells an agent which actions are available. A skill adds the judgment around those actions: how to recognize the job, which sequence to follow, what to avoid, and how to decide that the result is complete.
Orchestrate multi-step workflows with approval gates, state machines, and conditional branching. Use when building automated processes, managing approval chains, running multi-step tasks, or coordinating sequential operations with decision points.
Architecture
How Workflow Orchestration guides an ADK-Rust agent.
The skill stays readable and portable because it contains instructions rather than service credentials or business data. ADK-Rust supplies it to the agent, the agent chooses from its reviewed tool boundary, and the connected MCP server performs the authenticated operation.
01
User request
The agent receives a goal expressed in ordinary language.
02
Workflow Orchestration skill
Matches intent, supplies the decision guide, and narrows the tool boundary.
03
ADK-Rust agent
Plans the workflow and streams each meaningful step through the runtime.
04
mcp-workflow
Executes authenticated operations against the system that owns the capability.
05
Verified result
The skill's completion rules shape the evidence returned to the user.
Decision guide
How the agent turns a request into the right action.
These routes come directly from the skill instructions. They help the model recognize intent and select a focused tool or workflow instead of improvising across the entire capability surface.
"status", "where is", "progress"?
get_instance / list_instances
"approve", "reject", "pending"?
list_approvals / resolve_approval
"advance", "next step", "continue"?
advance_step
"cancel", "abort"?
cancel_instance
Proven workflows
Repeatable sequences for useful outcomes.
A workflow joins several tool calls into a task the user actually recognizes. The skill explains the sequence and the intended result while ADK-Rust streams the agent's progress through the shared runtime.
013 calls
Create & Run
Define steps → start → monitor
022 calls
Handle Approvals
List pending → approve/reject
031 calls
Advance
Move to next step
041 calls
Cancel
Abort with rollback
Tool boundary
The skill may use 10 documented tools.
This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-workflow retains responsibility for authentication, validation, and the connected system.
list_workflows
get_workflow
create_workflow
start_workflow
list_instances
get_instance
advance_step
cancel_instance
list_approvals
resolve_approval
Working rules
What the agent should do.
- Include timeout on every step
- Require approval gates before destructive actions
- Log all state transitions with actor and reason
- Design for idempotency (steps may retry)
Operating boundaries
What the agent should avoid.
- Never skip approval gates for convenience
- Don't leave workflows stuck without escalation
- Don't create workflows without rollback steps for critical paths
Install and connect
Add the skill beside the capability it expects.
Install the repository where your ADK-Rust skill loader can discover it, connect mcp-workflow, and confirm the declared tools are available before asking the agent to use the workflow.
Install the skill
git clone https://github.com/zavora-ai/skill-workflow-orchestration.git \
~/.skills/skills/workflow-orchestrationADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("workflow-orchestration").await?;
let agent = LlmAgentBuilder::new("agent")
.instruction(skill.instructions())
.tools(skill.allowed_tools(toolset)?)
.build()?;The repository's compatibility statement: Requires mcp-workflow server connected.
Official documentation
Read the complete skill package.
The repository remains authoritative for its exact instructions, examples, helper scripts, assets, MCP requirements, license, and later updates.
Keep exploring
More in agent infrastructure.
A2A Agent OrchestrationMulti-agent coordination — discover capabilities, dispatch tasks, stream results, and manage remote agent lifecycles via the A2A protocol.10 allowed toolsACP Workspace ManagementCoding agent workspace control — start sessions, delegate tasks to coding agents, review proposed patches, manage permissions, and publish agents with governance gates.9 allowed toolsArtifact LifecycleGoverned artifact management — versioned storage, provenance tracking, integrity verification, derivation chains, and export packaging for build outputs and documents.10 allowed tools
Source record
Repository metadata for this skill entry.
- License
- Apache-2.0
- Allowed tools
- 10
- References
- 3
- Revision
- c0a23437c0eb
- Updated
- May 31, 2026