Run after making React changes to catch issues early. Use when reviewing code, finishing a feature, or fixing bugs in a React project.
Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用.
Edits and compiles very large Markdown research reports using surgical patches, structure JSON, and legal‑grade citation rules.
Operates and debugs the local stack (API/worker/frontend); focuses on observability, logs, and safe automation.
Load coding conventions and style guidelines when writing or reviewing code. Ensures consistency with project standards.
Angular 21+ standalone/Material/signal conventions for Perigon WebApp
Ultimate Bug Scanner - Pre-commit static analysis for AI coding workflows. 18 detection categories, 8 languages, 4-layer analysis engine. The AI agent's quality gate.
Database migration management for SQLAlchemy projects using Alembic
Named Tmux Manager - Multi-agent orchestration for Claude Code, Codex, and Gemini in tiled tmux panes.
Use when working with context management context restore
Integrate with Replicate AI for running models (image generation, LLMs, etc.).
Step-by-step tutorial for adding new CUDA kernels to FlashInfer
SSH remote access patterns and utilities. Connect to servers, manage keys, tunnels, and transfers.
List and get Linear issues via CLI (read-only operations)
Tutorial for debugging CUDA crashes using API logging
Run .NET architecture linter to check for MSBuild/CPM violations
Create and update Linear projects via CLI (write operations)
Guide for initializing and consolidating Daem0n-MCP across project structures
Create SEO-optimized MDX blog posts with proper frontmatter
Read and search GitHub repository documentation via gitmcp.io MCP service.
Generate an SVG of a user-requested image or scene
Gate Wallet market data and token info queries. K-line,
Create and manage mock API servers for development and testing.
oh-my-claudecode — Teams-first multi-agent orchestration layer for Claude Code. 32 specialized agents, smart model routing, persistent execution loops, and real-time HUD…
Guide to using Better Auth for client and server-side authentication.
查看/更新 GitHub Issue、PR（含评论与 diff），并按团队规范非交互创建或修改 PR；涉及 GitHub Issue/PR 的操作时使用。
Generate realistic test data for database development, testing, and demos.
Route any website you need to visit through markdown.new by prefixing the URL.
Create and update Linear issues via CLI (write operations)
Only to be triggered by explicit /parallel-task-spark commands.
Perigon ASP.NET Core + EF Core + Aspire conventions
Code quality standards, linting rules, and CI/CD principles.
Validate data against schemas, business rules, and data quality standards.
Simultaneous Launch Button - Two-person rule for destructive commands in multi-agent workflows. Risk-tiered classification, command hash binding, 5 execution gates, client-side…
Create visual assets (images, illustrations) using AI (OpenAI DALL-E).
Use when user specfically says 'plan harder'.
Beads Viewer - Graph-aware triage engine for Beads projects. Computes PageRank, betweenness, critical path, and cycles. Use --robot-* flags for AI agents.
List and get Linear projects via CLI (read-only operations)
Pointers for Copilot/agents to apply Perigon conventions
Interaction with NeonDB Postgres using Drizzle ORM.
Specialized ML model development, training, and deployment workflow
Only to be triggered by explicit /parallel-task commands.
为 Java 项目生成自动化单元测试（JUnit 5 + Mockito）。当用户要求编写单元测试、生成测试用例或提升测试覆盖率时使用。
Display Claude Router usage statistics and cost savings
Run PostgreSQL queries and meta-commands via CLI
Pre-deployment validation checklist and automated readiness assessment.
Manage and update application themes using shadcn and tweakcn.
Advanced Python Scheduler - Task scheduling and job queue system
创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。
Expert C4 Container-level documentation specialist. Synthesizes
Use when working with performance testing review multi agent review
JEO — Integrated AI agent orchestration skill. Plan with ralph+plannotator, execute with team/bmad, verify browser behavior with agent-browser, apply UI feedback with…
Automated code refactoring suggestions and implementation.
Decide how to complete a development branch: merge, PR, squash, or cleanup.
Recover session state from memory-keeper after context loss.
自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式，自动转换，一键创建知识库。
Manage SEO, sitemaps, and metadata for optimal search engine visibility
Domain knowledge for Physical AI, ROS 2, and Humanoid Robotics.
Clear the knowledge base and start fresh
SOLID object-oriented design principles for maintainable code