AI Agent Skills

Use when the plan rests on an unproven assumption that could be tested cheaply before committing serious effort — will people turn up, will anyone donate, does this mess…

Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when use…

Generate a Python code skeleton from an experiment blueprint

标准化实验日志记录——直接上传或读取本地图片、语音和文字，产出带 YAML frontmatter 的 Markdown；可选集成飞书 CLI 与 Obsidian。

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "spli…

When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change,"…

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experimen…

Designs chaos experiments, creates failure injection frameworks, and facilitates game day exercises for distributed systems — producing runbooks, experiment manifests, r…

Package a finished local project into an intentional GitHub repository, create a strong README and visual preview, push it safely, configure a public GitHub Pages URL wh…

RenoDX workflow for generating, validating, or debugging BT.2020/BT.2100 HDR PNG artifacts from EXR, linear RGB, nits arrays, scalar maps, or analysis images. Use when c…

Read, edit, commit, and diff experiment code; coordinate shared worktrees and preserve frozen branch history. Use before branch work, when starting work alongside other…

The ultimate playground to learn, experiment with, and compare modern open-source AI agent frameworks — from basics to production-ready setups.

Sample project to experiment with Cypress to test the GitLab application.