Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Conduct comprehensive Helm chart security and quality audits with automated checks for security contexts, resource limits, and production readiness. Use when reviewing pull requests with Helm chart changes, conducting pre-release chart audits, security scanning Helm manifests, validating chart structure and best practices, or preparing charts for production deployment.
Audits Helm charts for anti-patterns, security issues, and best practice violations. Use when asked to audit, review, or check Helm chart quality. Generates a comprehensive report under reports/YYYY-MM-DD/helm-charts-audit.md. (project)
Conduct heuristic evaluations - Nielsen's 10 heuristics, severity ratings, expert review methodology, cognitive walkthrough, and usability inspection.
Reviews code architecture for hexagonal patterns, checks dependency directions, and suggests improvements for ports and adapters separation. Activates when users work with services, repositories, or architectural patterns.
Design, implement, and maintain applications using hexagonal architecture (ports and adapters). Use when (1) designing new systems requiring clear separation between domain logic and infrastructure, (2) refactoring monolithic or tightly-coupled codebases toward cleaner boundaries, (3) reviewing architecture for dependency rule violations or layer leakage, (4) establishing testing strategies that isolate domain logic, or (5) evaluating whether hexagonal architecture suits a given problem domain.
Specifies the format for ending responses, including a summary of requirements, code written, source tree, and next task, applying to all files.
Implement human-in-the-loop approval flows. Use when adding Slack approvals, dashboard review queues, action gating, or trust-based auto-approval.
Operate a Home Assistant instance via the official REST/WebSocket APIs and backups, with safe plan/apply workflows for bulk, reviewable changes.
Behavioral guideline for providing brutally honest feedback. Use always - this skill defines core interaction expectations for code review and technical discussions.
Audits Claude Code hooks for correctness, safety, and performance. Use when reviewing, validating, or debugging hooks, checking exit codes, error handling, or learning hook best practices.
Guide Hook creation with mandatory security review checklist, event selection, and safety validation. Hooks execute arbitrary commands automatically and require careful security consideration. Use when creating Hooks, implementing pre-commit hooks, post-command hooks, automatic execution, event-driven workflows, or when users want to run commands automatically.
Strategic policy deployment system for automotive manufacturing. Cascades Group-level targets to shop floor through X-Matrix, catchball process, and bowling chart tracking. USE WHEN user says 'hoshin', 'x-matrix', 'catchball', 'bowling chart', 'strategy deployment', 'cascade objectives', 'breakthrough objectives', 'strategic planning', 'policy deployment', or requests help with annual planning integration. Integrates with IATF 16949 quality systems and AutomotiveManufacturing skill for work instruction cascade.
Check Hive test progress, update documentation, and commit with standardized message.
Use when creating mouse hover effects - button highlights, card lifts, link underlines, image zooms, or any pointer-triggered animation.
Guidelines for using Zen MCP tools effectively in this repo. Use for complex multi-model tasks, architectural decisions, or when cross-model validation adds value.
Rules specific to HTML files, focusing on accessibility and Tailwind styling.
HTMX expert including hypermedia patterns, Django/Flask integration
Use when writing HubSpot integration code in Nango - HubSpot-specific guidance on Search API for incremental syncs, property name variations, rate limits, and OAuth introspection
UX/UI specialist auditing Hugo layouts, components, navigation, and interactions against the Tone & Voice Guide. Ensures designs embody intimacy, consent-forward principles, mystery, sensuality, and inclusive accessibility.
hydrological-modeller
hydromet-sysadmin
Analyze code for internationalization issues, understanding the UI context and user impact before flagging problems. Use when reviewing code for global readiness.
Ensure all user-facing text is translatable via ngx-translate. Use when adding text to UI components, checking for hardcoded strings, or when the user asks about translations.
Your role is to act as a **Senior DevOps Engineer** specializing in Infrastructure as Code. Your goal is to understand a user's request, write the necessary code, and present a **safe, clear execution
Review infrastructure-as-code changes for safety and correctness. Use when a mid-level developer needs a second look on IaC.
Use this skill AFTER a terraform plan has been generated. This skill audits a terraform plan file for security vulnerabilities (using tfsec/checkov) and company compliance policies. It either APPROVES or REJECTS the plan.
Use when working in mm-ibkr-gateway to access market data, account summary, positions, PnL, or orders via the REST API (FastAPI). Covers starting the API server, required env and safety settings, authentication with X-API-Key, and market/account/order endpoints for quote, historical bars, preview, place, status, cancel, and open orders.
Use when working in mm-ibkr-gateway to access market data, account summary, positions, PnL, or orders directly in Python via ibkr_core. Covers connecting with IBKRClient, using market/account/order helpers, and safety rules for preview, place, cancel, and status.
Generate IC10 code from natural language descriptions. Use when user wants to create new IC10 code, asks for automation scripts, or needs IC10 implementation for devices like vents, furnaces, sensors, or any Stationeers automation.
Review test cases for ID Token validation. Covers ID Token structure, required/conditional claims, signature validation (RS256), and all validation rules per OIDC Core 1.0 Section 2 and 3.1.3.7.
**v1.0 AGENTIC PIPELINE**: 6단계 에이전틱 아이디어 팩토리! 프로젝트분석→카테고리분류→아이디어기획(병렬)→기획팀장→PRD개발팀장→CTO최종결정. 4team-review 통합, 상위 0.001% 전문가 수준 기획문서 자동 생성.
Idiomatic Go patterns review. Use when checking Go-specific idioms, interface design, or pointer usage. Ensures code follows Go conventions and best practices.
Idiomatic Rust patterns for pikru C port. Use when writing or reviewing Rust code ported from C. Don't write C in Rust - the goal is correct behavior, not line-by-line translation.
Rules for optimizing images within React components to improve performance.
Validate images against tacosdedatos illustration style guide. Use this skill when reviewing generated images, checking uploaded images for brand consistency, providing quality feedback on visual assets, or deciding if an image is ready for publication. Returns pass/fail with specific actionable feedback.
Imagine (Idea Intake) — Start or refine an idea. If given free-form text, create a new IDEA-XXXX folder, ask clarifying questions, draft idea.md, then (after user review) save to inputs/idea.md and log the run.
Unified shipping + TRACE self-review protocol (beads, proof, PR). Explicit-only.
Implements new TCL builtin commands or subcommands in feather. Use when adding new TCL commands like lrepeat, or new subcommands to existing commands like namespace.
'Single-agent implementation: executes plans in-place without subagents. Use /implement (default) for complex features; use this for simpler tasks or when subagent overhead is unwanted.'
Add comprehensive type hints to Python/TypeScript code to improve IDE support, catch errors early, and enable better AI code understanding
Use when preparing to implement instructions by reviewing documentation and TODO.md so the actual work starts with a shared plan.
Implement a feature using the written implementation plan. Use when you have a fully-formed written implementation plan to execute in a separate session with review checkpoints
Use after implementing a plan to verify completeness, correctness, and merge safety - the post-implementation gate
Loads plan, reviews critically, executes each batch, and reports for review between batches. Use when implementing a plan from a plan file.
This skill helps AI agents create a transparent log of implicit technical decisions made during implementation. The goal is to capture specific, non-obvious choices that could be valuable for later re
CSV and OFX transaction import parsing. Use when working on files in src/lib/import/.
Improve UI copy using proven frameworks (JTBD, benefit-first, error patterns). Use when a designer wants to improve button text, error messages, empty states, or audit copy in a component. Supports interactive walkthrough mode for reviewing changes one-by-one, or batch mode for quick fixes.
Complete continuous improvement cycle orchestrating review, analysis, learning extraction, systematic updates, and validation. Sequential workflow from comprehensive review through pattern analysis and learning extraction to improvement application and re-validation. Use when continuously improving skills, applying review findings, implementing systematic enhancements, or executing complete improvement cycles.
Refactor and improve code quality. Use for code refactoring, performance optimization, and quality improvements. Includes Context7 refactoring patterns lookup.