Creates custom React hooks for SideDish. Use when the user asks to create a new hook, extract shared logic into a hook, or refactor component logic into reusable hooks. Includes TypeScript interfaces, memoization patterns, and index.ts export.
Manage Gitea wiki pages. Use when working with wiki content, creating documentation, or updating wiki pages.
Validate SPEC.md format - run after editing to catch parser issues
Knowledge retrieval from multiple sources. Search docs, web, and code with intelligent routing.
Copywriting dla bloga portfolio Pawla Lipowczana (pawellipowczan.pl). Uzyj przy tworzeniu nowych artykulow na blog, generowaniu tresci SEO, pisaniu case studies. Zawiera styl pisania autora (bezposredni, praktyczny, osobisty), strukture artykulow (front matter YAML, hierarchia H1-H3), kategorie (Automatyzacja/No-Code/AI), wytyczne SEO, szablony artykulow. Skill generuje artykuly zgodne z tonem i formatem istniejacych publikacji na blogu.
Unified memory substrate. Store facts, patterns, and context. Query with remember, consult, and stats commands.
Code quality and CI requirements. Auto-triggered when discussing commits, PRs, or quality.
Visual design for Guitar Tone Shootout - design tokens, colors, typography, component patterns, and aesthetic principles. Use for UI decisions and styling.
Development hot reload behavior. Auto-triggered when discussing file watching, rebuilds, or dev server.
Comprehensive UI/UX design principles for web applications based on Sociomedia Human Interface Guidelines (SHIG). Use when Claude needs to design or review web application interfaces, evaluate UI/UX decisions and patterns, create user-friendly forms and navigation, build accessible and consistent interfaces, apply object-oriented UI design principles, or optimize user workflows and reduce cognitive load.
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
Automated verification and extraction of race event dates from official websites to ensure data accuracy and freshness.
Generates and displays Kubernetes Gateway API topology diagrams showing GatewayClasses, Gateways, Routes, and backend Services in Mermaid format
Golang backend architecture expert. Use when designing Go services with Gin, implementing layered architecture, configuring sqlc with PostgreSQL/Supabase, or building API authentication.
TypeScript language expert specializing in type system, generics, conditional types, and advanced patterns. Use when writing complex types, debugging type errors, or designing type-safe APIs.
Cloud architecture expert for Kubernetes, Helm, Terraform, and AWS EKS. Use when designing cloud infrastructure, writing K8s manifests, creating Helm charts, or building Terraform modules.
Senior Backend Engineer for Hono/Supabase. Use when designing APIs, writing SQL, optimizing queries, or implementing business logic. Focuses on security, data integrity, and performance.
Guidelines for implementing tables in Datacapt frontend using the DatacTable component. Use this skill when building table interfaces to ensure consistent pagination setup, column definitions, and data fetching patterns.
Google Agent Development Kit (ADK) Python development guide. Build, evaluate, and deploy AI agents with Gemini models. Covers agents (LLM, Workflow, Custom, Multi-agent), tools (built-in, custom, MCP), runtime, deployment, observability, evaluation, sessions, memory, callbacks, artifacts, events, streaming, A2A protocol, and grounding. Keywords: google-adk, adk-python, agent, gemini, tool, workflow, multi-agent, deployment, evaluation, streaming, a2a, grounding
CRITICAL: Use for Makepad DSL syntax and inheritance. Triggers on: makepad dsl, live_design, makepad inheritance, makepad prototype, "<Widget>", "Foo = { }", makepad object, makepad property, makepad DSL 语法, makepad 继承, makepad 原型, 如何定义 makepad 组件
Build LLM agents with LangGraph. Use for: ReAct agents, multi-agent (supervisor/swarm), stateful workflows, human-in-the-loop. Always fetch latest docs via URLs provided.
Use OpenRouter API with LangChain. Covers: ChatOpenAI with OpenRouter, model variants (nitro/floor/free/online/thinking), provider routing, streaming, structured output, tool binding. Always fetch latest docs via URLs provided.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Set up, check status, or use the Telegram integration for Claude Code. Use this skill when the user mentions Telegram, wants to send messages to Telegram, check Telegram status, or troubleshoot Telegram connectivity. This skill should be active for ALL sessions in this project.
変更内容を分析し、Conventional Commits形式でコミットを作成する
Look up Microsoft API references, find working code samples, and verify SDK code is correct. Use when working with Azure SDKs, .NET libraries, or Microsoft APIs—to find the right method, check parameters, get working examples, or troubleshoot errors. Catches hallucinated methods, wrong signatures, and deprecated patterns by querying official docs.
Interact with artifact containers via HTTP API for paper evaluation tasks. Execute commands, read files, and list directories in remote artifact environments.
Claude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a reusable Skill (SKILL.md + references/scripts/assets), and refactor existing Skills for clarity, activation reliability, and quality gates.
Better Auth expert for Next.js App Router and Node/TypeScript projects. Use when implementing authentication/authorization with Better Auth for: (1) creating the Better Auth instance (providers, plugins, security options), (2) wiring Next.js route handlers (`/api/auth/[...all]`), (3) reading sessions in Server Components/Route Handlers, (4) protecting routes via middleware (cookie-only or full session validation with Node runtime), (5) using database adapters (especially Prisma) and schema setup, and (6) troubleshooting cookies/CSRF/trusted origins/baseURL and callback URL issues.
Skill(SKILL.md)の保守・更新・新規作成を対話で行い、整合性と検証手順を維持したまま反映する。Skill更新、skill update、Skillメンテナンス、Skill追加を依頼されたときに使用する。
Comprehensive guide for using Valchecker in your projects. Use this skill when implementing validation with valchecker - defining schemas, handling errors, type inference, async validation, and integration patterns.
Comprehensive guide for developing and contributing to the Valchecker validation library. Use this skill when working on the valchecker codebase itself - adding new steps, fixing bugs, or improving core functionality.
VMware vSphere architecture and design expertise for enterprise virtualization. Use when working with vSphere/ESXi for capacity planning, resource management, performance tuning, or infrastructure design. Covers CPU oversubscription, memory management, storage architecture, DRS, HA, networking, and best practices for enterprise deployments. Commands: - /vcpu-ratio - Explain vCPU:pCPU ratios and CPU oversubscription - /memory-mgmt - Memory management techniques and optimization - /storage-design - Storage architecture patterns and best practices - /drs-rules - DRS configuration and affinity/anti-affinity rules - /ha-design - High availability and fault tolerance design - /capacity-plan - Capacity planning methodology and ratios - /perf-troubleshoot - Performance troubleshooting with esxtop metrics
FHIR API development guide for building healthcare endpoints. Use when: (1) Creating FHIR REST endpoints (Patient, Observation, Encounter, Condition, MedicationRequest), (2) Validating FHIR resources and returning proper HTTP status codes and error responses, (3) Implementing SMART on FHIR authorization and OAuth scopes, (4) Working with Bundles, transactions, batch operations, or search pagination. Covers FHIR R4 resource structures, required fields, value sets (status codes, gender, intent), coding systems (LOINC, SNOMED, RxNorm, ICD-10), and OperationOutcome error handling.
Generate kinetic typography video shorts from text
設計タスクをするときに発動。方針・仕様を決め、実装に必要な決定事項を揃える。Planの作成や、実装に着手する前に使用するようにしてください。
Troubleshoot OmniScript parsing errors, validation failures, and export problems. Use when users encounter OSF syntax errors, document validation issues, or export failures.
Export OmniScript document to PDF
Export OmniScript document to PowerPoint (PPTX)
Validate OmniScript syntax and report errors
Export OmniScript document to Excel (XLSX)
Export OmniScript document to Word (DOCX)
Manage git operations safely. Includes stale state detection, branch/commit management. Never pushes without explicit user confirmation.
Conduct structured interviews with the user. Use when multiple decisions need user input: ask ONE question at a time, wait for response, record answer, then proceed to next question.
Create clean git branches from feature work, excluding agent-ops files. Use for PR preparation.
Manage Git worktrees for isolated parallel development. Use when reviewing PRs, working on
Run RALPH autonomous development loop to implement features from the PRD.
Work with Jira and Atlassian for the GLCP project using Atlassian MCP server tools. Use when (1) querying Jira issues, sprints, or boards, (2) creating or updating GLCP stories, (3) accessing Green Team or Magenta Team boards, (4) working with GLCP project issues, or (5) any Jira/Confluence operations for GLCP.
Quick reference for SD/SIC (Sustainability Dashboard/Sustainability Insight Center) repositories. Use when answering questions about (1) which repositories are SD/SIC repos, (2) which repos are ADS apps, (3) where repositories are located locally or remotely, (4) repository categorization, (5) SD terminology equivalence, (6) management scripts in SD directory, or (7) deployment/Kubernetes information for SD applications.
Czech electronic signature API integration for DigiSign. Use when the user needs to create, send, and manage digital signature envelopes, upload documents for signing, track signature status, or integrate embedded signing flows. Supports multiple signature types, webhooks for status tracking, and Czech Bank iD verification. Triggers on mentions of DigiSign, elektronicky podpis, digital signatures, envelope signing, or document signing workflows.
Testing and evaluation patterns for LLM applications using DeepEval and RAGAS. Use for formal evaluation before deployment, after prompt changes, or model updates.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Diagnose NixOS black/blank screen, display output loss, or suspend/resume wake failures on this system. Use when collecting logs around an incident, analyzing KDE/Wayland/X11/GPU power events, proposing mitigations in this repo, or maintaining a running troubleshooting log.
This skill should be used when reviewing GitHub Pull Requests to provide comprehensive code quality, security, and architecture analysis with optional JIRA ticket integration.
This skill should be used when transforming, refactoring, or replacing code patterns across multiple files. Use for renaming functions/classes/variables, migrating API usage patterns, modernizing syntax, or performing bulk code transformations. Prefer ast-grep over sed/awk for syntax-aware replacements that understand language structure.
Manage Coolify deployments, applications, databases, and services via the Coolify API. Use when the user wants to deploy, start, stop, restart, or manage applications hosted on Coolify.
Search and query labeled entities including exchanges, funds, protocols, and whales. Get entity categories, search for labeled addresses, and retrieve entity information. Use when user asks about exchange wallets, fund tracking, or labeled addresses.
Deploy and debug Eve-compatible apps via CLI, including local tag workflows, ingress URLs, and failure diagnosis. Use when deployments fail or behavior does not match expectations.
Work tracking with Beads - setup, maintenance, task breakdown, and finding work
Construção de workflows de automação n8n. Gera arquivos JSON prontos para importar no n8n. Usar quando o usuário pedir para criar fluxos, automações, integrações ou workflows no n8n. Exemplos de triggers: crie um fluxo n8n, monte uma automação, gere um workflow para, integração n8n entre X e Y, automatize com n8n.
Manage Kapso workflows, functions, and project databases; use for workflow graph edits, triggers, executions, function nodes, and D1 table CRUD.
Kapso Platform API overview with authentication, base URLs, customer onboarding, setup links, phone number provisioning, and connection detection workflows.
Act as a Frontend Engineer for this repo, specializing in TypeScript + React + Tailwind. Use when implementing UI from design artifacts, integrating API contracts, and producing frontend build/run notes.
This skill should be used when creating commits or pull requests, enforcing a human-written PR structure, intent capture, and evidence in agentic workflows.
Act as Product Manager for this repo. Use when defining product scope, assumptions, functional requirements, user stories, or non-functional requirements, based on CTO boundaries and governance artifacts.
Act as UI Designer for this repo. Use when translating requirements into interaction design, navigation flows, and ASCII wireframes, informed by available data contracts.
Act as System Architect for this repo. Use when defining system-level design, components, APIs, or data models based on requirements and CTO decisions.
Activate for content strategy, editorial calendars, content pillar mapping, blog planning, and content audit. Use when planning content programs, creating editorial workflows, or building topic clusters.
Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy
Activate for brand voice, visual identity, messaging frameworks, asset management, and brand consistency. Use when creating branded content, establishing tone of voice, managing marketing assets, validating brand compliance, or maintaining brand standards across marketing materials.
Exa CLI tool for intelligent web search, content extraction, and code context retrieval.
Use when implementing backend features with NextJS API routes, MongoDB integration, or server-side logic. This skill covers route handlers, database patterns, authentication flows, and API design for NextJS applications.
Build and prototype RawDrive UI components with bundling support. Use for creating standalone component demos, prototyping new features, or building shareable HTML previews.
Input validation and JSON schema validation for game state and moves. Use when handling user input, validating move files, or processing state.json. Critical for GitHub Actions validation logic.
Clean up Russian vocabulary CSV exports from Language Reactor (YouTube subtitle learning extension). Use when the user asks to process or clean up a Language Reactor CSV file.
Guidelines for writing Convex backend functions, schemas, and queries. Use when writing or modifying any code in the convex/ directory, creating Convex functions (queries, mutations, actions), defining schemas, or working with Convex validators and database operations.
Use the sheet-filler MCP server to safely auto-fill tabular data.
Notion workspace integration. Use when user wants to read/write Notion pages, search databases, create tasks, or sync content with Notion.
Release the screenpipe monorepo. Bumps versions, triggers GitHub Actions for app, CLI, MCP, and JS packages.
Interactive Archon integration for knowledge base and project management via REST API. On first use, asks for Archon host URL. Use when searching documentation, managing projects/tasks, or querying indexed knowledge. Provides RAG-powered semantic search, website crawling, document upload, hierarchical project/task management, and document versioning. Always try Archon first for external documentation and knowledge retrieval before using other sources.
Automate ticket creation from customer backlog to internal backlog with AI translation (JA ↔ VI) and dynamic task templates
Plan and design feature implementations with structured task breakdown and acceptance criteria. Use when user wants to plan a feature, design an implementation, create an epic with tasks, or turn an idea into actionable work items. Creates epics and tasks in .flow/ directory.
Scan existing epics to find dependencies and relationships for a new plan. Use when planning a new feature to identify if it depends on or conflicts with existing work.
Find the most relevant framework and library documentation pages for implementing a feature correctly. Use when you need official API references, version-specific guidance, or examples from documentation.
Scan repository to find existing patterns, conventions, and related code paths for a feature or change. Use when you need to understand codebase conventions, find similar implementations, or identify reusable code before planning or implementation.
Configure security scanning hooks for vulnerability detection and secrets scanning. Uses semgrep, bandit, and gitleaks for automated security analysis on code changes.
Configure Claude Code PostToolUse hooks for real-time auto-linting. Automatically runs linters after Edit/Write operations for immediate code quality feedback.
Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.
Motion animation library for React - essential patterns for components, transitions, gestures, and performance. Trigger: When animating React components, motion, whileHover, whileTap, layout animations, transitions.
Real-time meeting transcription and summarization with speaker diarization, action item extraction, and hierarchical summaries. Optimized for medical research meetings with MedCPT embeddings.
Create new Agent Kit skills from templates and sync them to supported CLIs.
Summarize GitHub pull request activity. Use when asked about recent PRs, work summary, what was accomplished, or weekly updates. Supports custom time ranges, repos, and authors.
Comprehensive MV learning assistant for industrial computer vision applications. Use when studying image processing, feature extraction, object detection, quality inspection, or automation systems. Helps with (1) concept explanation with real-world examples, (2) OpenCV code analysis and debugging, (3) homework guidance without direct answers, (4) lab experiment setup and troubleshooting, (5) quiz generation for self-assessment, (6) knowledge summarization and review materials, (7) vision system design and optimization, (8) research paper reading and comprehension.
Scrape course materials from Brightspace LMS. Use when (1) need to download course content (slides, labs, assignments), (2) organize course materials locally, (3) filter specific module types, (4) batch download from multiple courses.
Comprehensive RL learning assistant for coursework and self-study. Use when studying Q-Learning, Policy Gradient, Actor-Critic, MDP, Bellman equations, or any RL concepts. Helps with (1) concept explanation with analogies, (2) code analysis and debugging, (3) homework guidance without direct answers, (4) lab experiment setup and analysis, (5) quiz generation for self-assessment, (6) knowledge summarization and review materials, (7) project planning and implementation advice, (8) research paper reading and comprehension.
Download a YouTube video transcript and fully process it into the knowledge base
基于恒生聚源数据库,为用户查询指定A股或A股公募ETF的数据,让用户可以基于数据学习上市公司的分析理论,不提供投资建议。知识库内容包括:财务、资金、量价、估值、股东、产业、事件影响、宏观影响分析。
Use when implementing new features, fixing bugs, or making behavior changes. Enforces RED-GREEN-REFACTOR cycle.
Brief-specific code patterns and conventions