
TypeScript coding patterns and implementation standards. Load when structuring logic, defining boundaries, handling errors, or deciding what belongs in a route, feature, or shared module.
Testing implementation guidance for application code. Load when deciding what to test, how to split tests across layers, or how to avoid redundant tests.
Creates or updates docs/behavior.md — a lightweight summary of expected behavior per feature or page. Load when adding a new feature, clarifying intent of an existing one, or aligning behavior with test coverage. Assumes code and tests are the source of truth; this document is supplementary.
Design system setup and UI implementation guidance for this project. Load when building new UI components, setting up design tokens, implementing animations or visual effects, or making aesthetic and layout decisions. Covers Tailwind CSS v4 @theme token structure, typography, color, motion, and visual design direction.
Hono + HTMX architecture guidelines for Cloudflare Workers. Use when developing server-rendered applications with Hono, HTMX, and Hono JSX.
Core Skill. Hono API architecture guidelines for Cloudflare Workers with module boundaries, request validation, resource existence checks, Result-based error flow, layered caching, and testable route composition. Use when building or refactoring Hono APIs, edge image/data endpoints, or Worker-first backend services.
Manages GitHub Issues using gh CLI — creation, decomposition, update, and close. Load when asked to create a new issue, break down a large task into issues, update issue status or labels, or close an issue after a PR is merged. Human decides whether to create an issue. Agent handles all gh CLI operations.
Manages GitHub Issues using gh CLI — creation, decomposition, update, and close. Load when asked to create a new issue, break down a large task into issues, update issue status or labels, or close an issue after a PR is merged. Human decides whether to create an issue. Agent handles all gh CLI operations.
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
Testing implementation guidance for this project. Load when writing new tests, deciding what to test, setting up Vitest, or implementing E2E tests with Playwright. Covers unit testing with Vitest, component testing, integration testing, and the decision tree for choosing the right approach.
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
Implements a new feature using docs-first delivery, boundary-driven structure, and skeleton-first execution. Load when adding a route, feature, or new user-visible behavior.
Core Skill. Next.js 15+ App Router architecture guidelines including component patterns, state management with Zustand, server actions, and project structure. Use when developing Next.js applications.
Implements a new feature using vertical slice architecture and skeleton-first approach. Load when adding a new feature, route, or domain concept to the project. Covers file structure, colocation pattern, implementation order, and how to verify completion. Works regardless of framework.
Creates a new Architecture Decision Record in docs/adr/. Load when making a significant architectural decision, choosing between technical approaches, establishing a new pattern, or recording why an alternative was rejected. Covers ADR format, status lifecycle, and what qualifies as an ADR.
Creates a new Architecture Decision Record in docs/adr/. Load when making a significant architectural decision, choosing between technical approaches, establishing a new pattern, or recording why an alternative was rejected. Covers ADR format, status lifecycle, and what qualifies as an ADR.
Bootstraps project documentation for an existing repository by reading the codebase, README, tests, and package metadata, then creates or updates docs/overview.md, docs/spec.md, and ADRs when significant architectural decisions are discovered. Use when asked to document a repo, extract project purpose, write overview/spec docs, review an existing codebase, or capture architecture decisions from source.
TypeScript coding patterns and implementation standards for this project. Load when implementing new logic, refactoring existing code, handling errors, or when unsure how to structure state, side effects, or component architecture. Covers Result<T,E> pattern, composable logic design, and component architecture decisions.
Core Skill. HonoX architecture guidelines including file-based routing, Islands pattern, component types, performance optimization, and best practices for full-stack development.
Core Skill. Save and recall reusable project knowledge across sessions. Result must be in Japanese.
Core Skill. This skill is for document creation. User ask you to create planning documents, such as requirement and task breakdown.
Composite Skill. This skill is designed to handle general tasks that may arise during the development process. It encompasses a wide range of activities, including coding, design, testing, and project management.
Design system setup and UI implementation guidance for this project. Load when building new UI components, setting up design tokens, implementing animations or visual effects, or making aesthetic and layout decisions. Covers Tailwind CSS v4 @theme token structure, typography, color, motion, and visual design direction.
Core Skill. Save and recall reusable project knowledge across sessions. Result must be in Japanese.
Creates or updates docs/overview.md — the project's purpose and background. Load when starting a new project, when the project's goals or context have changed, or when docs/overview.md does not exist. Covers what to write, what to omit, and how to keep the document agent-friendly.
Composite Skill. This skill is used for project planning. Users request that a project plan be created, particularly during the initial stages.
Bootstraps project documentation for an existing repository by reading the codebase, README, tests, and package metadata, then creates or updates docs/overview.md, docs/behavior.md, and ADRs when significant architectural decisions are discovered. Use when asked to document a repo, extract project purpose, write overview/behavior docs, review an existing codebase, or capture architecture decisions from source.
Creates or updates docs/overview.md — the project's purpose and background. Load when starting a new project, when the project's goals or context have changed, or when docs/overview.md does not exist. Covers what to write, what to omit, and how to keep the document agent-friendly.
Creates or updates docs/spec.md — the project's functional requirements. Load when defining new features, when requirements have changed, or when docs/spec.md does not exist. Covers what to write, what to omit, and how to express requirements in a way that is verifiable and agent-friendly.
Creates a new Architecture Decision Record in docs/adr/. Load when making a significant architectural decision, choosing between technical approaches, establishing a new pattern, or recording why an alternative was rejected. Covers ADR format, status lifecycle, and what qualifies as an ADR.
TypeScript coding patterns and implementation standards. Load when structuring logic, defining boundaries, handling errors, or deciding what belongs in a route, feature, or shared module.
Bootstraps project documentation for an existing repository by reading the codebase, README, tests, and package metadata, then creates or updates docs/overview.md, docs/behavior.md, and ADRs when significant architectural decisions are discovered. Use when asked to document a repo, extract project purpose, write overview/behavior docs, review an existing codebase, or capture architecture decisions from source.
Manages GitHub Issues using gh CLI — creation, decomposition, update, and close. Load when asked to create a new issue, break down a large task into issues, update issue status or labels, or close an issue after a PR is merged. Human decides whether to create an issue. Agent handles all gh CLI operations.
Creates or updates docs/overview.md — the project's purpose and background. Load when starting a new project, when the project's goals or context have changed, or when docs/overview.md does not exist. Covers what to write, what to omit, and how to keep the document agent-friendly.
Bootstraps project documentation for an existing repository by reading the codebase, README, tests, and package metadata, then creates or updates docs/overview.md, docs/spec.md, and ADRs when significant architectural decisions are discovered. Use when asked to document a repo, extract project purpose, write overview/spec docs, review an existing codebase, or capture architecture decisions from source.
TypeScript coding patterns and implementation standards. Load when structuring logic, defining boundaries, handling errors, or deciding what belongs in a route, feature, or shared module.
Core Skill. Save and recall reusable project knowledge across sessions. Result must be in Japanese.
Core Skill. Save and recall reusable project knowledge across sessions. Result must be in Japanese.
Testing implementation guidance for application code. Load when deciding what to test, how to split tests across layers, or how to avoid redundant tests.
Creates or updates docs/behavior.md — a lightweight summary of expected behavior per feature or page. Load when adding a new feature, clarifying intent of an existing one, or aligning behavior with test coverage. Assumes code and tests are the source of truth; this document is supplementary.
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
Manages GitHub Issues using gh CLI — creation, decomposition, update, and close. Load when asked to create a new issue, break down a large task into issues, update issue status or labels, or close an issue after a PR is merged. Human decides whether to create an issue. Agent handles all gh CLI operations.
Core Skill. Save and recall reusable project knowledge across sessions. Result must be in Japanese.
Drives a repository change through a docs-first workflow. Load when a task must be recorded in project docs before implementation, may be implemented by the agent or the user, and must be validated and reconciled back into docs at the end.
Design system setup and UI implementation guidance for this project. Load when building new UI components, setting up design tokens, implementing animations or visual effects, or making aesthetic and layout decisions. Covers Tailwind CSS v4 @theme token structure, typography, color, motion, and visual design direction.
Creates or updates docs/overview.md — the project's purpose and background. Load when starting a new project, when the project's goals or context have changed, or when docs/overview.md does not exist. Covers what to write, what to omit, and how to keep the document agent-friendly.
Creates or updates docs/spec.md — the project's functional requirements. Load when defining new features, when requirements have changed, or when docs/spec.md does not exist. Covers what to write, what to omit, and how to express requirements in a way that is verifiable and agent-friendly.
Bootstraps project documentation for an existing repository by reading the codebase, README, tests, and package metadata, then creates or updates docs/overview.md, docs/behavior.md, and ADRs when significant architectural decisions are discovered. Use when asked to document a repo, extract project purpose, write overview/behavior docs, review an existing codebase, or capture architecture decisions from source.
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
When creating or refining ideas, ask the user detailed questions until a shared understanding is reached, and work through each branch of the decision tree one by one. Use this approach if you want to be rigorously questioned about an idea, or if you’ve specifically asked to be “grill me.”.
Implements a new feature using docs-first delivery, boundary-driven structure, and skeleton-first execution. Load when adding a route, feature, or new user-visible behavior.
Implements a new feature using docs-first delivery, boundary-driven structure, and skeleton-first execution. Load when adding a route, feature, or new user-visible behavior.
Design system setup and UI implementation guidance for this project. Load when building new UI components, setting up design tokens, implementing animations or visual effects, or making aesthetic and layout decisions. Covers Tailwind CSS v4 @theme token structure, typography, color, motion, and visual design direction.
TypeScript coding patterns and implementation standards. Load when structuring logic, defining boundaries, handling errors, or deciding what belongs in a route, feature, or shared module.
Creates or updates docs/behavior.md — a lightweight summary of expected behavior per feature or page. Load when adding a new feature, clarifying intent of an existing one, or aligning behavior with test coverage. Assumes code and tests are the source of truth; this document is supplementary.
Manages GitHub Issues using gh CLI — creation, decomposition, update, and close. Load when asked to create a new issue, break down a large task into issues, update issue status or labels, or close an issue after a PR is merged. Human decides whether to create an issue. Agent handles all gh CLI operations.
Testing implementation guidance for application code. Load when deciding what to test, how to split tests across layers, or how to avoid redundant tests.
Creates or updates docs/overview.md — the project's purpose and background. Load when starting a new project, when the project's goals or context have changed, or when docs/overview.md does not exist. Covers what to write, what to omit, and how to keep the document agent-friendly.
Implements a new feature using docs-first delivery, boundary-driven structure, and skeleton-first execution. Load when adding a route, feature, or new user-visible behavior.
Design system setup and UI implementation guidance for this project. Load when building new UI components, setting up design tokens, implementing animations or visual effects, or making aesthetic and layout decisions. Covers Tailwind CSS v4 @theme token structure, typography, color, motion, and visual design direction.
Creates a new Architecture Decision Record in docs/adr/. Load when making a significant architectural decision, choosing between technical approaches, establishing a new pattern, or recording why an alternative was rejected. Covers ADR format, status lifecycle, and what qualifies as an ADR.
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
Testing implementation guidance for application code. Load when deciding what to test, how to split tests across layers, or how to avoid redundant tests.
Creates a new Architecture Decision Record in docs/adr/. Load when making a significant architectural decision, choosing between technical approaches, establishing a new pattern, or recording why an alternative was rejected. Covers ADR format, status lifecycle, and what qualifies as an ADR.