"upload", "store", "put file"?
upload_object
← Skill registry
Agent infrastructurePublic skills
Cloud Storage
Universal cloud storage for AI agents — upload, download, share, search, and manage files across AWS S3, Google Cloud Storage, Cloudflare R2, and MinIO.
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 cloud storage operations — list buckets, upload/download files, generate presigned URLs, copy/move objects, search across storage, and monitor usage. Use when uploading files, downloading objects, sharing files via presigned URLs, organizing storage, searching for files, or checking storage usage.
Architecture
How Cloud Storage 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
Cloud Storage 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-storage
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.
"download", "get file", "fetch"?
download_object
"share", "link", "URL"?
generate_presigned_url (time-limited!)
"find", "search", "where is"?
search_objects / list_objects
"copy", "duplicate"?
copy_object
"move", "rename"?
move_object
"delete", "remove"?
delete_object (confirm first!)
"buckets", "list storage"?
list_buckets
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.
011 calls
Upload
Store file with content type
021 calls
Share
Time-limited presigned URL
031-2 calls
Search
Find files by prefix/pattern
041-2 calls
Organize
Copy, move, rename
051 calls
Monitor
Storage usage per bucket
06Setup calls
Provider
Setup
Tool boundary
The skill may use 12 documented tools.
This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-storage retains responsibility for authentication, validation, and the connected system.
list_buckets
list_objects
get_object_info
download_object
generate_presigned_url
upload_object
copy_object
move_object
delete_object
create_bucket
search_objects
get_storage_usage
Working rules
What the agent should do.
- Use presigned URLs for sharing (never make objects public)
- Set appropriate content_type on uploads
- Confirm before deleting (irreversible)
- Check storage usage periodically
Operating boundaries
What the agent should avoid.
- Never delete without explicit user confirmation
- Never make buckets publicly accessible
- Don't upload without specifying content_type
- Don't generate presigned URLs with 24h expiry without justification
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-storage, 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-cloud-storage.git \
~/.skills/skills/cloud-storageADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("cloud-storage").await?;
let agent = LlmAgentBuilder::new("agent")
.instruction(skill.instructions())
.tools(skill.allowed_tools(toolset)?)
.build()?;The repository's compatibility statement: Requires mcp-storage server connected (AWS S3, Google Cloud Storage, Cloudflare R2, MinIO, or any S3-compatible provider).
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
- 12
- References
- 3
- Revision
- e4263b2e9b8a
- Updated
- May 31, 2026