Explore skills

Use when you want to audit environment variable usage — scans the entire codebase for all env var references across all sources (code, Docker, CI, config files) and flags anything undocumented or inconsistent. Works for any stack and any env var pattern.

Structure the trade-off decision between AI models, providers, or approaches for a given product use case. Use this skill when a team needs to choose between AI options with different capability, cost, latency, and risk profiles.

Structure and facilitate a product or delivery retrospective to extract learning and improve team practices. Use this skill when a team needs to reflect on a completed cycle, launch, or experiment and turn observations into action.

Use before committing or opening a pull request — reviews staged changes as a principal engineer for correctness, edge cases, and logic flaws. Always invoke this before creating a PR.

Define a clear strategic positioning statement that articulates where the product plays, who it serves best, and what makes it the right choice for that segment. Use this skill when the team needs to anchor strategy in a specific market position.

This skill should be used when the user asks to "optimize a task with parallel strategies", "deploy winning strategies", "run competing approaches", "find the best approach by trying multiple strategies", or mentions "winning", "parallel optimization", "strategy competition". Orchestrates multiple background agents running Ralph-style loops to converge on the best solution.

Evaluate and prioritize strategic bets — high-uncertainty, high-potential initiatives — against business goals and risk tolerance. Use this skill when a team needs to decide which big bets to pursue, pause, or stop.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Compile a genai.recipe.yml into a deployable Claude Code skill bundle (SKILL.md + input.schema.json + README). Use when the user asks to compile, build, or generate a skill from a recipe.

Import and adapt an existing AI app concept (prompt, web form, API spec) into a Genai recipe skeleton following the clean-room philosophy. Use when the user wants to port or convert an existing AI application into a Genai skill.

Apply structured ethical frameworks to evaluate product decisions and identify potential harms. Use this skill when a product decision raises ethical concerns or involves trade-offs between user wellbeing and business goals.

Comprehensive guide for Pixi package manager - Python environment management, CUDA/GPU support, PyPI integration, Docker/Pixi-Pack deployment, and best practices for ML research