Iterative 3-phase workflow with peer review cycle for changes needing validation (15-30 min)
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 →Iterative 3-phase workflow with peer review cycle for changes needing validation (15-30 min)
Standard 5-phase workflow for most development tasks - bugs, small features, refactors (30-60 min)
Attach documents, screenshots, PDFs, and files to Jira issues and Confluence pages via REST API. Use when uploading evidence, documentation, or media to Atlassian products.
Use when querying Jira issues, searching Confluence pages, creating tickets, updating documentation, or integrating Atlassian tools via MCP protocol.
Search and retrieve information from Jira and Confluence using the atlassian-cli tool. Use this skill to find issues, search documentation, manage projects, and track sprints in Atlassian products.
>-
Create atomic components (atoms) - the fundamental building blocks of your UI with proper TypeScript interfaces and Tailwind v4 styling.
Expert Atomic Design decisions for iOS/tvOS: when component hierarchy adds value vs overkill, atom vs molecule boundary judgment, design token management trade-offs, and component reusability patterns. Use when structuring design systems, deciding component granularity, or organizing component libraries. Trigger keywords: Atomic Design, atoms, molecules, organisms, templates, component library, design system, design tokens, reusability, composition
Atomic Design component organization pattern for React Native mobile applications. Use when creating new components with proper accessibility and touch targets.
Atomic Design methodology for React component architecture. Use for structuring component libraries, organizing UI hierarchies, and creating scalable design systems. Triggers on requests for component organization, design system structure, UI hierarchy, or questions about Atoms/Molecules/Organisms/Templates/Pages.
Knowledge about attempt tracking and gating patterns for task execution
Use when wrong elements get attention, important content is missed, or visual hierarchy is broken by animation
Universal coding standards and best practices for TypeScript, JavaScript, React, and Node.js. Use when: writing code, reviewing code quality, establishing conventions. Focuses on modern patterns, explicit conventions, and rationale for best practices.
Expert in digital signal processing for audio applications. Validates biquad filter implementations, frequency response calculations, and audio algorithms. Use when modifying audio-math.ts, implementing new filter types, or adding spectral analysis features.
Create standard SuperCollider audio effects for Bice-Box (delays, reverbs, filters, distortions). Provides templates, ControlSpecs, common patterns, and MCP workflow for safely creating/updating effects.
Work with Leavn audio systems - TTS, sermon recording, guided mode audio, ambient sounds, voice profiles, audio orchestration
You are the audio fingerprinting and pattern detection specialist for Modcaster's content analysis.
Test Bob The Skull with virtual audio injection instead of speaking. Use when testing wake word detection, STT accuracy, full conversation pipeline, or automated testing. Covers setup, configuration, injection methods, and troubleshooting.
You are the on-device audio ML specialist for Modcaster's AI-driven audio processing.
Comprehensive security and code quality audit. Use for thorough security, vulnerability, and code quality analysis. Related: project-health-checker for quick diagnostic checks.
Aggregate and deduplicate findings from multiple audit reports
Scan codebase for bad coding practices that violate fail-fast principles
Run a single-session code review audit on the codebase
Run all 7 domain audits in staged waves and aggregate results
Orchestrates comprehensive audits of Claude Code customizations using specialized auditors. Use when auditing multiple components, asking about naming/organization best practices, or needing thorough validation before deployment.
Audit codebase for performance bottlenecks and thread-safety issues
Run a single-session performance audit on the codebase
Prepare your codebase for security review using Trail of Bits' checklist. Helps set review goals, runs static analysis tools, increases test coverage, removes dead code, ensures accessibility, and generates comprehensive documentation (flowcharts, user stories, inline comments). (project, gitignored)
Run a single-session refactoring audit on the codebase
Template and formatting guidelines for security audit reports. Provides consistent structure for findings, severity classification, ASVS mapping, and remediation recommendations.
Comprehensive audit capabilities for security, code quality, module structure, compliance, and performance analysis. Use this skill when performing security audits, code reviews, vulnerability assessments, module structure validation, or generating audit reports.
Audit a checkpoint specification for realism and design decision forcing. Reviews specs to remove hand-holding, hidden corner cases, and architectural giveaways. Invoke with /audit-spec <problem> <checkpoint>.
使用 squirrelscan CLI(squirrel)对网站进行审计,覆盖 SEO、技术、内容、性能、安全等 140+ 规则。当需要分析网站健康、排查技术 SEO、检查死链、校验 meta 与结构化数据、生成站点审计报告、对比改版前后,或提到「网站审计」「audit website」「squirrel」「站点健康检查」时使用。
Audits deep link contracts and routing behavior. Use when validating
Auditing and updating npm dependencies to prevent security vulnerabilities in TypeScript projects
Audits notification permission request flows. Use when reviewing or improving permission prompts, settings paths, or denial handling.
<objective>
Use this skill when auditing websites for SEO, analyzing search performance, checking technical SEO issues, or optimizing sites for search engines. Performs comprehensive SEO audits covering technical, on-page, and off-page factors. Invoke for SEO analysis, search optimization, keyword research, or improving search rankings.
>
>
Review and analyze authentication and authorization patterns for security vulnerabilities.
Adds BetterAuth authentication to Apso backends. Handles entity setup, code generation, auto-fixes, and verification. Triggers when user needs to add authentication, setup auth, or integrate BetterAuth.
Pre-built and custom Clerk authentication component templates with theming and customization patterns. Use when building authentication UI, creating sign-in/sign-up pages, customizing Clerk components, implementing user buttons, theming auth flows, or when user mentions Clerk components, SignIn, SignUp, UserButton, auth UI, appearance customization, or authentication theming.
auth-js
This skill should be used when the user requests to audit, check, or generate authentication and authorization protection for Next.js routes, server components, API routes, and server actions. It analyzes existing routes for missing auth checks and generates protection logic based on user roles and permissions. Trigger terms include auth check, route protection, protect routes, secure endpoints, auth middleware, role-based routes, authorization check, api security, server action security, protect pages.
OAuth 2.1, JWT (RFC 8725), encryption, and authentication security expert. Enforces 2026 security standards.
Comprehensive security review of authentication systems.
auth-shield
Write like a human, not a language model. This skill eliminates the telltale patterns that make AI writing detectable.
Manages authentication flow for MutuaPIX (Laravel Sanctum + Next.js), handles mock mode security, and validates environment configurations