WordPress backend performance optimization — profiling, queries, object cache, autoload, cron, and remote HTTP. Always-active rules when investigating slowness issues.
PHP 8.x migration guide for WordPress — covers PHP 8.0 through 8.3 features, breaking changes, backward compatibility patterns, dynamic properties fixes, and step-by-step…
Use when you need a deterministic inspection of a WordPress repository (plugin/theme/block theme/WP core/Gutenberg/full site) including tooling/tests/version hints, and a…
Manages WordPress theme.json design tokens including color palettes, typography presets, and spacing scales.
Analyze and fix WPF applications for high DPI support, per-monitor DPI awareness, and scaling issues
Close a session — summarize what was done, persist state for the next session, clean up the display pool, stop running loops, write to memory if there's a learning worth keeping.
Run Claude Code, Codex, Cursor, or similar local agent CLIs inside a host-local sandbox that learns required access and blocks everything else by default.
Lets an agent install or build a harness around an existing tool so the tool becomes callable through a predictable CLI surface.
End-of-session cleanup after PR merge: refresh repo, run quick retrospective, clean gone branches, and generate a follow-up session prompt.
Track per-character segments so wrapped or truncated text keeps its original colors and emphasis.
Generate a Wren MDL project by exploring a database with available tools (SQLAlchemy, database drivers, MCP connectors, or raw SQL).
Onboard a user to Wren Engine end-to-end. Walks through environment checks, project scaffolding, connection configuration via .env, and first query.
Wren Engine CLI workflow guide for AI agents. Answer data questions end-to-end using the wren CLI: gather schema context, recall past queries, write SQL through the MDL semantic…
Wrike integration. Manage Users, Organizations, Projects, Tasks, Folders, Spaces and more. Use when the user wants to interact with Wrike data.
Automate Wrike project management via Rube MCP (Composio): create tasks/folders, manage projects, assign work, and track progress. Always search tools first for current schemas.
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Usar para documentar decisiones arquitectónicas como ADR. Activar cuando el usuario quiera documentar por qué se tomó una decisión, registrar alternativas descartadas, crear un…
Generates and updates the latest app changelog based on git history since the last version tag.
AIコーディングアシスタントにプロジェクト固有の指示を提供する効果的な CLAUDE.mdファイルを作成する。構造、一般的なセクション、すべきこと・ すべきでないパターン、MCPサーバーとエージェント定義との統合をカバー する。AIアシスタントを使用する新しいプロジェクトを始める場合、既存の…
Write a coding standards document for a project using the coding styles from the file(s) and/or folder(s) passed as arguments in the prompt.
Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.
Write a CONTINUE_HERE.md file capturing current session state so a fresh Claude Code session can pick up where this one left off.
Collaborative document authoring workflow for proposals, technical specs, decision docs, README sections, ADRs, and long-form prose that must work for fresh readers.
Generate Playwright E2E tests from codebase analysis. Discovers routes, scores user flows by criticality, generates .spec.ts with page objects and quality gates.
Draft replayable runx harness fixtures for a proposed skill package or composite execution plan.
Writing and maintaining GitHub issues and pull requests for cedanl repositories. Use when creating new issues, editing issue titles/bodies, creating PRs, or cleaning up issue…
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance,…
발표 유형(TYPE A/B/C/D)에 맞는 나레이션 스타일로 슬라이드별 대본을 작성합니다. TTS에 적합한 구어체로 변환하고 fragmentScripts 구간 분할까지 수행합니다. 사용 시점: NarrationAgent가 슬라이드별 대본을 작성할 때 호출합니다.
Write short, high-stakes emails that sound like a competent human. Covers professors, admins, founders, alumni, organizers, and follow-ups.
Generate engaging, high-energy release notes for a given version tag. Fetches the release from GitHub, retrieves every linked PR's title and description, then synthesizes all…
Escribir documentación roxygen2 para funciones, conjuntos de datos y clases de paquetes R. Cubre todas las etiquetas estándar, referencias cruzadas, ejemplos y generación de…
Escreve uma especificação técnica para implementar uma feature com arquitetura, dados, contratos, riscos, testes e plano de rollout.
Use when the user wants help composing a tweet on X (Twitter). Generates tweet ideas, drafts, algorithm-optimized variants, and scores tweets for engagement.
Redactar documentación de validación IQ/OQ/PQ para sistemas informatizados en entornos regulados. Cubre protocolos, informes, scripts de prueba, gestión de desviaciones y flujos…
R MarkdownまたはQuartoを使用してRパッケージのビネットを作成する。 ビネットのセットアップ、YAML設定、コードチャンクオプション、ビルドとテスト、 ビネットのCRAN要件を網羅。「はじめに」チュートリアルの追加、複数の関数にまたがる 複雑なワークフローの文書化、ドメイン固有のガイド作成、またはCRAN投稿で…
Write or update duplojs-utils JSDoc documentation files under jsDoc/{namespace}/{function}/, including index.md structure, @example includes, and example.ts usage patterns…
How to write Claude Code agents — standard format, 2-phase review, severity/confidence, dispatch patterns
Write a bot to continuously listen and respond to events on a public blockchain network.
Writes and improves checklist-based professional communications -- requests for action, handoffs, meeting agendas/follow-ups, and process runbooks.
Use when writing instructions that guide Claude behavior - skills, CLAUDE.md files, agent prompts, system prompts.
Use when creating or updating CLAUDE.md files for projects or subdirectories - covers top-level vs domain-level organization, capturing architectural intent and contracts, and…
Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text.
How to write Claude Code slash commands — orchestrator pattern, agent dispatch, auto-detection
Use after brainstorming completes - writes validated designs to docs/design-plans/ with structured format and discrete implementation phases required for creating detailed…
Expert at writing high-quality documentation for code, APIs, and projects. Auto-invokes when generating docstrings, creating README files, writing API documentation, adding code…
Rédige des emails professionnels ou personnels adaptés au contexte et à l'objectif. À utiliser quand l'utilisateur veut écrire un email important.
Help users with technical documentation writing. Invoke when user asks for documentation help, API docs, or technical content drafting.
Use when writing documentation, guides, API references, or technical content for developers - enforces clarity, conciseness, and authenticity while avoiding AI writing patterns…
Use when writing or editing Go code in cc-port — any change to a `**/*.go` file that adds, modifies, or removes implementation logic, signatures, or comments.
Use when writing or reviewing tests - covers test philosophy, condition-based waiting, mocking strategy, and test isolation
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories).
How to write Claude Code hooks — lifecycle events, exit codes, profile system, shell patterns, best practices
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths,…
새 Nova 스킬을 작성하거나 기존 스킬 description을 수정할 때. — MUST TRIGGER: skills/ 하위 신규 SKILL.md 생성, 기존 SKILL description 리팩터, 사용자가 'Nova 스킬 추가/수정' 요청 시.
Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context
Use when you have a spec or requirements for a multi-step task that may benefit from parallel team execution, before touching code.
Review and improve the clarity, tone, and impact of text files in your workspace.
Writes and reviews high-signal project status reports using RAG indicators, layered structure, and exception-based reporting.
Corrige et améliore un texte en français (grammaire, style, clarté, ton). À utiliser quand l'utilisateur veut relire, corriger ou améliorer un texte français.
Create markdown-based behavioral rules to prevent unwanted actions and block dangerous commands