claudecodex

confident-eval-setup

Skills for getting an LLM app ready to evaluate on Confident AI: create and verify an AI connection over the Confident AI MCP server, connect an app with no endpoint through the Confident Agent's handler mode, and upload a dataset.

2 on GitHubby Confident AIv1.0.0Apache-2.0updated 6 days agodeveloper-tools
/

Plugin confident-eval-setup from marketplace confident-skills in confident-ai/confident-skills. Commands read from the repo's manifest — 6 days ago.

What it installs

Skills (2)

  • confident-agent-handler

    Connect an AI app that has no HTTP endpoint to Confident AI with the Confident Agent's handler mode: write a handler function that calls the app's pipeline in-process, run the agent beside it, and create and verify an Agent Handler AI connection. TRIGGER when the user wants Confident AI to evaluate

  • confident-eval-setup

    Get an LLM application ready to evaluate on the Confident AI platform through the Confident AI MCP server. TRIGGER when the user wants to set up evals on Confident AI, connect or register their app's endpoint as a Confident AI AI connection, fix or debug an AI connection that is inactive or failing

View source on GitHub confident-ai.com

More from confident-ai/confident-skills

All 4 plugins →

confident-trace

claudecodex

Skills for instrumenting AI applications with the confident-trace SDK, exporting raw OpenTelemetry traces to Confident AI, and migrating from Langfuse.

3 skills

2

confident-client

claudecodex

Skills for managing Confident AI organizations, projects, members, roles, governance policies, and API keys with the confident-ai SDK.

1 skill

2

Onboard to Confident AI from your coding agent: sign in through the browser, save the API key without exposing it, add tracing, run your app on a batch of inputs, and confirm the traces arrived.

1 skill

2

Similar plugins

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

Scaffold, validate, and publish new Claude Code plugins with proper structure

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Build, train, evaluate, and use open source AI models, datasets, and spaces.

26 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

Maintain confident-eval-setup?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins4 plugins