evals agents

benchflow-ai/benchflow

Agent Codex

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

benchflow-ai/benchflow

Agent Codex

Compare two outputs WITHOUT knowing which skill produced them.

benchflow-ai/benchflow

Agent Codex

Evaluate expectations against an execution transcript and outputs.

AgentEvalHQ/AgentEval

Agent

AI agent for AgentEval development tasks - code implementation, review, and debugging.

AgentEvalHQ/AgentEval

Agent

AI agent for AgentEval documentation - writing, reviewing, and maintaining docs with brand consistency.

AgentEvalHQ/AgentEval

Agent

AI agent for reviewing, planning, and improving AgentEval samples and demos.

rennf93/opus-fable-playbook

Agent

Adversarial verifier. Use PROACTIVELY before claiming a nontrivial change is done, fixed, or passing — give it the claim plus the relevant diff/paths and it attempts to refute the claim with evidence.

hev/vibecheck

Agent Claude Code

Use this agent when you need to create, run, or improve integration tests using the vibecheck evaluation platform. This includes writing YAML evaluation suites, running checks via the CLI, debugging failing evals, optimizing check patterns, or designing comprehensive test strategies. The agent is particularly useful…

ahnafyy/skills-evals

Agent Claude Code

Generates unit tests for existing code. Use when the user asks to add tests for a module or increase coverage.

ahnafyy/skills-evals

Agent

Reviews pull requests for correctness, style, and security issues. Use when the user asks for a code review or PR feedback.

ahnafyy/skills-evals

Agent

Writes and updates documentation pages. Use when the user asks to document a feature or update the docs site.

Abhillashjadhav/AI-PM-essential-skills

Agent

Executes low-complexity tasks (cosmetic edits, formatting, simple lookups, mechanical transformations) delegated by the model-complexity-router. Fast and cheap.

Abhillashjadhav/AI-PM-essential-skills

Agent

Executes high-complexity tasks (architecture, multi-file refactors, novel tradeoff analysis, high error-cost decisions) delegated by the model-complexity-router.

Abhillashjadhav/AI-PM-essential-skills

Agent

Executes mid-complexity tasks (single features, standard analyses, drafts with known patterns) delegated by the model-complexity-router. Balanced cost and quality.