Create a technical design document before implementation by answering questions about the problem, scope, architecture, risks, and delivery plan. The skill adjusts sections to project size and covers security, testing, monitoring, and recovery where relevant.
Turn a recurring workflow into a new agent skill through guided discussion. Define use cases, activation conditions, file structure, and instructions, then create and validate SKILL.md and supporting files, including workflows using external tools through MCP.
Stress-test an idea, plan, or proposal through focused critique. The skill examines assumptions, opposing arguments, failure scenarios, attacks, or evidence, then uses your responses to refine the position and identify unresolved trade-offs and risky assumptions.
Turn Figma screens and components into code that follows an existing project's conventions. Retrieve design details, screenshots, and assets through Figma MCP, an agent connection, then reuse existing components and check the implementation against the design.
Build working web pages, components, and app interfaces around a clear visual concept. Coordinate typography, color, spacing, motion, and interaction details, adapting layouts to different screen sizes while avoiding repetitive visual templates.
Review web interface code for accessibility, visual design, and interaction issues. This skill checks specified files against interface guidelines and returns concise findings grouped by file, with line numbers to help locate each issue.
Guide an AI agent through code changes with explicit assumptions, simple implementations, focused edits, and testable goals. Use it for bug fixes, features, refactoring, or reviews to reduce guesswork and unnecessary changes.
Find and manage documentation in Confluence through Atlassian MCP, a connection to Atlassian tools. Search in plain language, read and summarize pages, create or update structured content, browse spaces, and add page comments.
Write and edit READMEs, guides, and other documentation using the code as evidence. Improve structure, wording, and terminology while checking related pages and links against the project's contribution process and documentation style guide.
Audit AGENTS.md, rules, skills, and their references for broken paths or commands. Optional independent agent reviews assess redundant instructions and practical usefulness, producing reports that identify what to retain, review, or consider trimming.
Explore an early software idea through an interview, clarify the problem, and decide whether to proceed. Produce a design document covering decisions, flows, data structures, and interface agreements so others can plan the work.
Guide feature development from a human-reviewed plan to testable requirements, implementation, and independent verification. Record each requirement with a concrete proof, then have a separate agent check the work and produce a verification report.
Analyze business concepts in a codebase to map business areas and suggest service boundaries. Use Domain-Driven Design, an approach organized around business meaning, to classify responsibilities, assess how closely they belong together, and recommend clearer integration points.
Create ADRs, short records of architectural decisions, that explain what was chosen, why, and with what trade-offs. Choose among three formats and organize dates, status, numbering, and related links for future team members.
Plan personalized sales emails to prospects you have not contacted before. This skill covers prospect selection, contact research, email drafts, follow-up sequences, inbox delivery, and reply handling, with guidance on tools and campaign improvements.
Plan AWS architectures, compare services, and review security using documentation verified through AWS MCP tools, which connect agents to external information. Get implementation examples and trade-offs tailored to the team's existing tools, experience, and constraints.
Draft structured RFCs, proposals for gathering feedback before a major decision. Organize background, weighted criteria, alternatives, costs, and a recommendation so stakeholders can compare choices and understand the reasons for the proposed direction.
Build and troubleshoot Shopify themes, apps, and custom storefronts with task-specific references. It covers Liquid, Shopify’s template language, API data access, custom business rules, and performance improvements, using API version 2026-01.
Find classes left in parent folders or namespaces and identify nested component structures. Compare consolidation, splitting, and shared code extraction, then plan and carry out refactoring with updated references and tests.
Create a phased roadmap for splitting a monolithic application into separate services. Assess current progress, prioritize work by risk, value, and dependencies, and produce milestones, estimated effort, acceptance criteria, and progress reports.
Plan and build frontend interfaces through guided questions, visual references, and agreed design choices. Define colors, typography, and layout before coding, then implement small sections for review, with optional Google Stitch prototyping.
Design specialized assistants that work with their own separate context. Define responsibilities, delegation conditions, working steps, and report formats for reusable subagents handling verification, debugging, security audits, or code reviews.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)