A Claude Code plugin that teaches Claude how to use the Rapidata Python SDK for human annotation tasks.
When installed, Claude can write working Rapidata code for classification, comparison, ranking, benchmarks, and more — without you needing to look up the API docs.
In Claude Code:
/install-plugin https://github.com/RapidataAI/skills
The plugin provides Claude with knowledge of the Rapidata SDK, covering:
The plugin is three markdown files that get loaded into Claude's context when relevant:
SKILL.md — core concepts, task types, and common patternsreference.md — full API reference (parameters, filters, result formats, error handling)examples.md — runnable code examples for every task typeThese live in plugins/rapidata-sdk-plugin/skills/rapidata/.
The plugin version tracks the Rapidata SDK version (currently 3.2.13). A GitHub Actions workflow automatically syncs the version when a new SDK release is published.
.claude-plugin/
marketplace.json # marketplace metadata
.github/workflows/
sync-sdk-version.yml # auto-sync plugin version to SDK releases
plugins/rapidata-sdk-plugin/
.claude-plugin/
plugin.json # plugin name + version
skills/rapidata/
SKILL.md # main skill definition
reference.md # API reference
examples.md # code examples
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub rapidataai/skills --plugin rapidata-sdk-pluginBuild high-quality datasets and computer vision models. Visualize datasets, analyze models, find duplicates, run inference, evaluate predictions, and develop custom plugins.
Design experiments, profile datasets, build models, and audit them for bias before shipping
Track and analyze AI experiments with a web dashboard and MCP tools
Build Retrieval-Augmented Generation pipelines
Self-documenting, self-improving framework for analytical repositories
Skills for building LLM evaluations: pipeline audit, error analysis, synthetic data generation, LLM-as-Judge design, evaluator validation, RAG evaluation, and annotation interfaces.