collinear-ai/simlab

collinear-ai/simlab

Skill Claude CodeCodex

Run an agent across SimLab tasks on Daytona to establish baseline performance scores.

collinear-ai/simlab

Skill Claude CodeCodex

Use this recipe when you already have an agent built with the Claude Agent SDK and want to run it in SimLab.

collinear-ai/simlab

Skill Claude CodeCodex

Use this recipe when you want to run a Google Agent Development Kit agent inside SimLab.

collinear-ai/simlab

Skill Claude CodeCodex

Use this recipe when the user has an existing LangGraph or LangChain-based agent and wants to run it inside SimLab.

collinear-ai/simlab

Skill Claude CodeCodex

Use this recipe when you already have an agent built with the OpenAI Agents SDK and want to run it in SimLab.

collinear-ai/simlab

Skill Claude CodeCodex

Define custom NPC personas in a SimLab task generation config and generate tasks with tailored stakeholder interactions.

collinear-ai/simlab

Skill Claude CodeCodex

Run an agent with and without OneCLI's credential proxy to verify correctness, credential isolation, and rate limit resilience.

collinear-ai/simlab

Skill Claude CodeCodex

You are running an autonomous experiment loop that optimizes a system prompt for an AI agent evaluated on SimLab tasks. You will modify system-prompt.md, run the agent against tasks, measure the average reward, and iterate.

collinear-ai/simlab

Skill Claude CodeCodex

Fine-tune a model on expert agent trajectories collected from SimLab using Tinker's supervised learning pipeline.

collinear-ai/simlab

Skill Claude CodeCodex

Use this directory for reusable workflow notes that the coding agent can discover.

collinear-ai/simlab

Skill Claude CodeCodex

Use this skill when a task asks you to summarize or extract data from PDF and XLSX files that already exist in the workspace.

collinear-ai/simlab

Skill Claude CodeCodex

Brainstorm, design, and scaffold new SimLab cookbook recipes from a rough idea.