Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, review experiments, and inspect datasets. Use when debugging AI/LLM applications, analyzing trace data, working with...
Plan and execute a product launch/release with speed and safety. Produces a Shipping & Launch Pack (release brief, rollout/rollback plan, product quality list, comms + enablement, monitoring plan,...
クラウドインフラ(Terraform/CloudFormation/Pulumi)とローカル開発環境(Docker Compose/dev setup/環境変数)両面の環境プロビジョニングを担当。IaC設計、環境構築、マルチクラウド対応が必要な時に使用。
|
Manage auto-approve hook for Claude Code - reduces permission prompts using Haiku as security reviewer
Create an AI Evals Pack (eval PRD, test set, rubric, judge plan, results + iteration loop). Use for LLM evaluation, benchmarks, rubrics, error analysis/open coding, and ship/no-ship quality gates...
Handle npm package installation in non-interactive environments by piping confirmations. Use when installing Node.js packages that require user confirmation prompts.
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
Configuration module patterns for LlamaFarm. Covers Pydantic v2 models, JSONSchema generation, YAML processing, and validation.
Coach product managers and produce a PM Coaching Pack (context-specific definition of “good PM”, evidence-based assessment, growth bets + development plan, coaching cadence + session toolkit,...
Help address review or issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
Extract learnings from session transcripts or notes and incorporate them into existing skills or create new ones. Use when the user has analysis documents, session learnings, or patterns they want...
Generate 30+ LinkedIn posts that attract your target prospects. Creates industry insights, thought leadership, engagement prompts, and comment strategies. Use when building personal brand to...
GSAP integration with React including useGSAP hook, ref handling, cleanup patterns, and context management. Use when implementing GSAP animations in React components, handling component lifecycle,...
Expert product marketing guidance for SaaS growth - trial acquisition, user activation to first value, and freemium-to-paid conversion. Use when writing landing pages, onboarding flows, email...
EffectComposer setup and architecture for Three.js post-processing pipelines. Use when setting up multi-pass rendering, combining effects, creating custom passes, managing render targets, or...
Build modern, composable, and accessible React UI components following the components.build specification. Use when creating, reviewing, or refactoring component libraries, design systems, or any...
Implement comprehensive observability for LLM applications including tracing (Langfuse/Helicone), cost tracking, token optimization, RAG evaluation metrics (RAGAS), hallucination detection, and...
Guide for migrating Apache Airflow 2.x projects to Airflow 3.x. Use when the user mentions Airflow 3 migration, upgrade, compatibility issues, breaking changes, or wants to modernize their Airflow...
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable -...