Develops custom FiftyOne plugins (operators and panels) from scratch. Use when creating plugins, extending FiftyOne with custom operators, building interactive panels, or integrating external APIs.
Develop FiftyOne Plugins
Key Directives
ALWAYS follow these rules:
1. Understand before coding
Ask clarifying questions. Never assume what the plugin should do.
2. Plan before implementing
Present file structure and design. Get user approval before generating code.
3. Search existing plugins for patterns
list_plugins(enabled=True)
list_operators(builtin_only=False)
get_operator_schema(operator_uri="@voxel51/brain/compute_similarity")
4. Test locally before done
Install plugin and verify it works in FiftyOne App.
5. Iterate on feedback
Refine until the plugin works as expected.
Workflow
Phase 1: Requirements
Ask these questions:
- "What should your plugin do?" (one sentence)
- "Operator (action) or Panel (interactive UI)?"
- "What inputs from the user?"
- "What outputs/results?"
- "External APIs or secrets needed?"
- "Background execution for long tasks?"
Phase 2: Design
- Search existing plugins for similar patterns
- Create plan with:
- Plugin name (
@org/plugin-name) - File structure
- Operator/panel specs
- Input/output definitions
- Plugin name (
- Get user approval before coding
See PLUGIN-STRUCTURE.md for file formats.
Phase 3: Generate Code
Create these files:
| File | Required | Purpose |
|---|---|---|
fiftyone.yml |
Yes | Plugin manifest |
__init__.py |
Yes | Python operators/panels |
requirements.txt |
If deps | Python dependencies |
package.json |
JS only | Node.js metadata |
src/index.tsx |
JS only | React components |
Reference docs:
Phase 4: Install & Test
# Find plugins directory
python -c "import fiftyone as fo; print(fo.config.plugins_dir)"
# Copy plugin
cp -r ./my-plugin ~/.fiftyone/plugins/
# Verify detection
python -c "import fiftyone as fo; print(fo.plugins.list_plugins())"
Test in App:
launch_app(dataset_name="test-dataset")
# Press Cmd/Ctrl + ` to open operator browser
# Search for your operator
Phase 5: Iterate
- Get user feedback
- Fix issues
- Re-copy to plugins directory
- Restart App if needed
- Repeat until working
Quick Reference
Plugin Types
| Type | Language | Use Case |
|---|---|---|
| Operator | Python | Data processing, computations |
| Panel | Python | Simple interactive UI |
| Panel | JavaScript | Rich React-based UI |
Operator Config Options
| Option | Effect |
|---|---|
dynamic=True |
Recalculate inputs on change |
execute_as_generator=True |
Stream progress |
allow_delegated_execution=True |
Background execution |
unlisted=True |
Hide from browser |
Input Types
| Type | Method |
|---|---|
| Text | inputs.str() |
| Number | inputs.int() / inputs.float() |
| Boolean | inputs.bool() |
| Dropdown | inputs.enum() |
| File | inputs.file() |
| View | inputs.view_target() |
Minimal Example
fiftyone.yml:
name: "@myorg/hello-world"
type: plugin
operators:
- hello_world
init.py:
import fiftyone.operators as foo
import fiftyone.operators.types as types
class HelloWorld(foo.Operator):
@property
def config(self):
return foo.OperatorConfig(
name="hello_world",
label="Hello World"
)
def resolve_input(self, ctx):
inputs = types.Object()
inputs.str("message", label="Message", default="Hello!")
return types.Property(inputs)
def execute(self, ctx):
print(ctx.params["message"])
return {"status": "done"}
def register(p):
p.register(HelloWorld)
Troubleshooting
Plugin not appearing:
- Check
fiftyone.ymlexists in plugin root - Verify location:
~/.fiftyone/plugins/ - Check for Python syntax errors
- Restart FiftyOne App
Operator not found:
- Verify operator listed in
fiftyone.yml - Check
register()function - Run
list_operators()to debug
Secrets not available:
- Add to
fiftyone.ymlundersecrets: - Set environment variables before starting FiftyOne
Resources
You Might Also Like
Related Skills

coding-agent
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
openclaw
add-uint-support
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
pytorch
at-dispatch-v2
Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.
pytorch
skill-writer
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
pytorch
implementing-jsc-classes-cpp
Implements JavaScript classes in C++ using JavaScriptCore. Use when creating new JS classes with C++ bindings, prototypes, or constructors.
oven-sh
implementing-jsc-classes-zig
Creates JavaScript classes using Bun's Zig bindings generator (.classes.ts). Use when implementing new JS APIs in Zig with JSC integration.
oven-sh