"start session", "workspace", "code task"?
start_session + delegate_task
← Skill registry
Agent infrastructurePublic skills
ACP Workspace Management
Coding agent workspace control — start sessions, delegate tasks to coding agents, review proposed patches, manage permissions, and publish agents with governance gates.
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.
Manage ACP coding workspaces — start sessions, delegate tasks to coding agents, review proposed patches, handle permissions, and publish agents. Use when provisioning coding environments, delegating code tasks, reviewing agent patches, managing workspace permissions, or publishing coding agents.
Architecture
How ACP Workspace Management 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
ACP Workspace Management 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-acp-workspace
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.
"what changed", "patches", "review"?
get_proposed_changes / review_patch
"permissions", "access"?
handle_permission
"status", "updates"?
get_session_updates / list_participants
"stop", "end session"?
stop_session
"publish", "deploy agent"?
publish_agent
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.
012-3 calls
Delegate Task
Start session → assign → monitor
022 calls
Review Patch
Get changes → approve/reject
031 calls
Permissions
Scope access to specific files
041 calls
Publish
Make agent available to others
Tool boundary
The skill may use 9 documented tools.
This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-acp-workspace retains responsibility for authentication, validation, and the connected system.
list_participants
start_session
delegate_task
get_session_updates
handle_permission
get_proposed_changes
review_patch
stop_session
publish_agent
Working rules
What the agent should do.
- Review ALL patches before allowing merge
- Scope workspace permissions to minimum required files
- Stop sessions after task completion (don't leave running)
- Log all delegated tasks with context
Operating boundaries
What the agent should avoid.
- Never auto-merge without review
- Don't grant write access to production paths
- Don't leave sessions running indefinitely
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-acp-workspace, 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-acp-workspace-management.git \
~/.skills/skills/acp-workspace-managementADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("acp-workspace-management").await?;
let agent = LlmAgentBuilder::new("agent")
.instruction(skill.instructions())
.tools(skill.allowed_tools(toolset)?)
.build()?;The repository's compatibility statement: Requires mcp-acp-workspace 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 toolsArtifact LifecycleGoverned artifact management — versioned storage, provenance tracking, integrity verification, derivation chains, and export packaging for build outputs and documents.10 allowed toolsCloud InfrastructureCloud operations for AI agents — deploy services, scale replicas, manage DNS, rotate secrets, promote between environments, monitor costs, and rollback on failure.24 allowed tools
Source record
Repository metadata for this skill entry.
- License
- Apache-2.0
- Allowed tools
- 9
- References
- 3
- Revision
- 7577f29c744f
- Updated
- May 31, 2026