Skill Creator
majiayu000
6838 published skills · 19,665 GitHub stars across the catalog. View on GitHub ↗
software-designing
技術設計書(design.md)を作成・編集します。アーキテクチャ設計、コンポーネント定義、API設計、データベーススキーマの文書化が必要な場合に使用してください。requirements.mdが存在する場合は整合性を確認します。
linq-optimization-patterns
Master LINQ and EF Core query optimization including N+1 prevention, eager loading, projections, and performance patterns. Use when: (1) fixing N+1 queries, (2) optimizing slow queries, (3) implementing efficient data access, (4) reducing database load.
debugging-react-native
Use PROACTIVELY when debugging React Native apps. Reads console logs and executes JavaScript in running apps via Metro bundler. Invoke for: app crashes, state inspection, API debugging, error investigation, or running diagnostic code. Requires Metro running (port 8081).
pmc-planning
Update planning docs from PRD files or discrepancies report. Use this skill to update roadmap and dependencies without creating tickets. Works directly with PRD documents and/or 99-discrepancies.md when available.
better-auth-python
Better Auth JWT verification for Python/FastAPI backends. Use when integrating Python APIs with a Better Auth TypeScript server via JWT tokens. Covers JWKS verification, FastAPI dependencies, SQLModel/SQLAlchemy integration, and protected routes.
chat2blog
将 AI 聊天记录、对话内容转换为 VuePress 格式的技术博客文章。当用户说"把对话整理成博客"、"写成文章"、"转换成 blog"、"生成博客",或提供聊天记录、技术讨论、问题解决过程需要整理时使用。输出包含 frontmatter 的完整 Markdown 文章。
kantra-analyze
Utilize Kantra, a CLI that unifies analysis and transformation capabilities of Konveyor, to analyze the source code of an application for violations.
n8n-workflow-builder
Build n8n automation workflows using MCP tools. Use when creating workflows, configuring nodes, validating configurations, deploying templates, or integrating n8n with Rails apps. Supports Israeli market (Hebrew, WhatsApp Business, NIS payments).
git-worktrees
Manage git worktrees for parallel branch development and PR reviews.Use when asked about: worktrees, working on multiple branches, parallel development,PR review without switching, testing without committing, multiple features simultaneously,long-running builds, comparing branches side-by-side.Integrates with: feature workflow, Azure DevOps work items, GitHub PRs.
capture
Parse and structure information from screenshots, meeting notes, or text, then save to Second Brain Supabase database. Extracts contacts, tasks, and ideas automatically. Use when user wants to save information for later.
pal-secaudit
Comprehensive security audit with OWASP Top 10 analysis, compliance evaluation, and threat modeling using PAL MCP. Use for security reviews, vulnerability assessment, or compliance checks. Triggers on security audit requests, vulnerability scanning, or compliance reviews.
react
Comprehensive React best practices for building scalable web applications with feature-based architecture, TypeScript, state management patterns, performance optimization, and testing guidelines. Use when creating React/Next.js UIs, components, features, or applications. This skill provides official React documentation guidance, 2025 community best practices, folder structure recommendations, and component patterns.
jwt-config-generator
Generate JWT authentication configuration and utilities for API security. Triggers on "create jwt config", "generate jwt authentication", "jwt setup", "token auth config".
ai-check
Detect AI/LLM-generated text patterns in research writing. Use when: (1) Reviewing manuscript drafts before submission, (2) Pre-commit validation of documentation, (3) Quality assurance checks on research artifacts, (4) Ensuring natural academic writing style, (5) Tracking writing authenticity over time. Analyzes grammar perfection, sentence uniformity, paragraph structure, word frequency (AI-typical words like 'delve', 'leverage', 'robust'), punctuation patterns, and transition word overuse.
guardian
Automatic quality gate and session health monitor. Spawns focused Haiku agents for code review and task planning when degradation detected. Validates suggestions against Oracle knowledge. Learns from user feedback to adjust sensitivity. Uses minimal context passing. Integrates with oracle and evaluator.
pr-agent
PRAgent スキル - Pull Request自動作成・Conventional Commits準拠・Draft PR自動生成。コード実装完了後、GitHub PRを自動作成し、レビュワー割り当て・説明文生成・関連Issue紐付けを実行。Use when:- Pull Requestを作成する時- Conventional Commits形式のタイトルが必要な時- レビュワーの自動割り当てが必要な時- 関連Issueの紐付けが必要な時- "PR作成", "プルリクエスト", "マージ" がキーワードに含まれる時
skill-export
Export Claude skills. Use to generate documentation of all available Claude Skills.
summary-generator
Generates session summaries and resume prompts for multi-session work. Use when completing features, before context limits (~50% capacity), or when user says "summary", "wrap up", "save progress", "end session". Creates markdown in docs/summaries/ with completed work, files modified, and restart instructions.
insightpulse-superset-user-enablement
Create onboarding, training, documentation, and enablement flows for admins, data teams, and business users of the InsightPulse Superset Data Lab.
sync-mcp-config
Synchronize MCP (Model Context Protocol) server settings across different Agent tools. Use when you want to copy, apply, or sync MCP settings between multiple Agent environments like Claude Code, VSCode, Claude Desktop, Codex, and Gemini CLI.
notion-auto-logger
Automatically logs every user prompt and AI output to datewise Notion pages. Use this skill to create a comprehensive archive of all AI interactions, track research progress, maintain conversation history, and build a searchable knowledge base. The skill creates one JSON file per day with all interactions and can export them to Notion in a structured format.
leap-year-analyzer
Analyze leap year calculations, calendar systems, and date validation logic. Use this when the user asks about leap year rules, calendar types (Gregorian, Julian, Hebrew, Chinese), year range validation (1582-9999), mathematical formulas, or needs to understand the core leap year detection algorithms.
benchmark-report-creator
Use PROACTIVELY when creating research reports, experiment writeups, technical whitepapers, or empirical study documentation. Orchestrates the complete benchmark report pipeline with structure, diagrams, hi-res PNG capture, and PDF export. Provides working scripts, CSS templates, and complete command sequences for publication-quality AI/ML benchmark reports. Not for slides, blog posts, or simple README files.
strix-halo-setup
Complete setup for AMD Strix Halo (Ryzen AI MAX+ 395) PyTorch environments. Handles ROCm installation verification, PyTorch community builds (official wheels don't work with gfx1151), GTT memory configuration, and environment setup. Creates ready-to-use ML workspaces for running 30B parameter models.