Session memory management, browser-based QA testing, and multi-agent coordination skill. Use when the user wants to persist learnings across sessions, review what the agent has learned about their codebase, prune stale knowledge, run browser-based testing with real Chromium, coordinate multiple AI agents on the same…
Expert AI/LLM engineering guidance. Use when the user asks about RAG, OpenAI, Azure OpenAI, prompt engineering, AI agents, MCP, vector databases, or evaluation pipelines.
Design production-grade APIs — REST, GraphQL, gRPC, and WebSocket — with a focus on consistency, versioning, error standards, and developer experience. Use when the user asks to design an API, define endpoints, choose between REST and GraphQL, structure request/response schemas, handle API versioning, design…
Automated full review pipeline skill. Use when the user wants to run a complete plan review in one command, automatically chain CEO review then design review then engineering review then DX review, surface only the decisions that need human taste judgment, or compress the full planning workflow into a single…
Production-grade backend development guidance — language and framework agnostic. Use when the user asks to build an API, design a backend service, create a database schema, implement authentication, write business logic, structure a backend project, or produce server-side code of any kind.
Performance benchmarking skill — baseline and compare page load times, Core Web Vitals, bundle sizes, and API response times. Use when the user wants to measure performance before and after a change, catch performance regressions in a PR, establish a performance baseline, or understand what is making their app slow.
Apply brand voice, tone, colors, typography, and visual style consistently across any artifact. Use when the user wants to ensure a document, presentation, email, website, or any content matches their brand identity — including color palette, font choices, tone of voice, imagery guidelines, and design standards. Also…
Review code changes for bugs, security issues, performance problems, and style before shipping. Use when the user asks for a code review, wants to check a diff or PR, needs a second opinion on implementation, or says "review this", "check this code", or "is this safe to ship".
Write clean Conventional Commits messages and pull request descriptions from staged changes or diffs. Use when the user asks to write a commit message, commit their changes, describe a PR, open a pull request, summarise a branch, or says "write a commit", "create a PR", "what should I call this commit", or "draft my…
Design and build production-grade data pipelines, ETL/ELT workflows, data warehouses, and streaming architectures. Use when the user asks about data pipelines, ETL/ELT, dbt models, Airflow DAGs, Kafka, data warehouses (Snowflake, BigQuery, Redshift), data quality, schema design for analytics, event streaming, or says…
Expert database architecture and design guidance — schema/data modeling, ER diagrams, indexing, query optimization, partitioning, replication and high availability, transactions and locking, connection pooling, migrations, and multi-tenancy patterns across PostgreSQL, MySQL, MongoDB, and Redis. Use this whenever the…
Systematic root-cause debugging skill. Use when the user has a bug, error, crash, unexpected behaviour, failing test, or performance issue and needs to find the root cause before fixing it. Iron law: no fixes without investigation first.
Visual design exploration and design system creation skill. Use when the user wants to explore multiple design directions, generate design variants, build a design system from scratch, convert a mockup to production HTML, compare design options, or needs a design partner to challenge aesthetic choices and catch AI…
Developer experience audit and improvement skill. Use when the user wants to review their API, CLI, SDK, or docs from a developer perspective, benchmark their onboarding flow against competitors, measure Time to Hello World (TTHW), trace friction points step-by-step, or improve the developer experience of a product…
Production-grade DevOps and platform engineering guidance — Docker, Kubernetes, CI/CD pipelines, Terraform/IaC, GitOps, deployment strategies (rolling/blue-green/canary), monitoring and alerting, and cloud patterns across AWS/Azure/GCP. Use this whenever the user asks about containerizing an app, writing a Dockerfile…
Structured co-authoring workflow for PRDs, design docs, RFCs, decision docs, proposals, and any substantial written document. Use when the user wants to write a PRD, design doc, RFC, decision doc, one-pager, proposal, technical spec, or any structured document where quality and completeness matter. Goes deeper than…
Expert guidance for Forward Deployment Engineers (FDEs) — customer-facing technical specialists who deploy, integrate, configure, and operationalize complex software systems at customer sites. Use when the user asks about customer onboarding, on-site deployment, system integration, customer-facing technical delivery…
Design and implement distinctive, production-ready web interfaces. Use when creating or substantially redesigning a page, component, dashboard, marketing site, or product UI; when choosing visual direction, typography, layout, responsive behavior, states, or accessibility; or when an existing interface feels generic…
Write clear, well-structured internal communications — incident reports, post-mortems, launch announcements, team updates, all-hands summaries, 3P updates (Progress/Plans/Problems), project status updates, leadership briefings, and FAQs. Use when the user needs to communicate something to their team, engineering org…
Build, review, debug, and maintain production Java applications, libraries, services, and APIs. Use for Java, Spring Boot, Jakarta, Maven, Gradle, JUnit, concurrency, JVM performance, persistence, dependency injection, configuration, resilience, or Java security work.
Merge, deploy, and verify production skill. Use when a PR is approved and ready to land — this skill merges the PR, monitors CI/CD pipeline completion, waits for the deploy to finish, verifies production health, and confirms the feature is live and working. The final step from "approved" to "verified in production".
Build production-grade MCP (Model Context Protocol) servers that connect AI agents to external APIs, databases, and services. Use when the user wants to build an MCP server, integrate an external API with Claude or any AI agent, create custom tools for an AI agent, expose a service via MCP, or asks how to connect…
Pre-code ideation and startup validation skill. Use when the user wants to validate a product idea, stress-test assumptions before building, run a YC-style office hours session, brainstorm feature alternatives, or needs forcing questions that challenge their thinking before writing a line of code.
Read, extract, create, merge, split, and manipulate PDF files. Use whenever a .pdf file is involved — extracting text or tables from a PDF, creating a new PDF from content or data, merging multiple PDFs, splitting a PDF into pages, rotating pages, adding watermarks, filling PDF forms, encrypting or decrypting PDFs…