发现 Skills

Comprehensive security review workflow for identifying vulnerabilities

Industrial-strength NLP with spaCy 3.x for text processing and custom classifier training. Use when "installing spaCy", "selecting model for nlp" (en_core_web_sm/md/lg/trf), "tokenization", "POS tagging", "named entity recognition" (NER), "dependency parsing", "training TextCategorizer models", "troubleshooting spaCy errors" (E050/E941 model errors, E927 version mismatch, memory issues), "batch processing with nlp.pipe", or "deploying nlp models to production". Includes data preparation scripts, config templates, and FastAPI serving examples.

Using Arquero in Observable Framework for data transformation and analysis.

15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with a 14-week timeline.

Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot

Platform APIs for model management, pricing, and usage tracking

Generate workflow JSON files for chaining AI models

Segmenting home networks into VLANs for IoT, guest, trusted, and server traffic using UniFi, pfSense/OPNsense, and MikroTik — including switch trunk config, firewall rules, and wireless SSID mapping.

WireGuard VPN server setup, peer configuration, key generation, split tunneling vs full tunnel routing, and remote access to a home network from mobile and laptop clients.

Implement "Sign in with SSO" in native Android/Kotlin applications using SSOJet OIDC with AppAuth.

Build AI agents that call StackOne-linked accounts using TypeScript SDK, Python SDK, MCP server, or A2A protocol. Use when user asks to "add StackOne tools to my agent", "set up MCP with StackOne", "list employees from BambooHR in my agent", "integrate StackOne with OpenAI", "build a multi-tenant agent", or "use StackOne with LangChain". Supports OpenAI, Vercel AI SDK, Claude, LangChain, CrewAI, PydanticAI. Do NOT use for account linking setup (use stackone-connect) or platform management (use stackone-platform).

Pick up open GitHub issues from collaborators and create PRs to solve them. Use when triaging and resolving reported bugs or feature requests.

Use when a user wants to visualize or present Shipkit content as HTML. Triggers: 'create presentation', 'visualize this', 'HTML report'.

Create new MARVIN skills on request. Use when user says "give yourself the ability to X" or "create a skill for Y". Generates proper skill structure with SKILL.md.

Use when approved parallel implementation across agents or sessions needs separate git branches/worktrees; overlap also needs an integration strategy before editing.

Use this skill when working with the cool-mysql library for Go. This skill provides comprehensive guidance on using cool-mysql's MySQL helper functions, including dual connection pools, named parameters, template syntax, caching strategies, and advanced query patterns. Apply when writing database code, optimizing queries, setting up caching, or migrating from database/sql.

Scaffold a new slash command markdown file by collecting parameters and executing the scaffolding script. Use this skill when the user wants to "create a slash command", "add a custom command", "build a /command", or "scaffold a command". It walks through collecting the command name, description, scope (project or user), optional tool restrictions, model override, argument hints, namespace, bash context blocks, and file references, then generates a spec-compliant .md file in the correct .claude/commands/ location. Do not use this for creating skills, agents, hooks, or MCP servers.

Write integration tests for CLI commands with Vitest

Use when the user gives a coding task that should run in parallel, asks to create an agent, says "run an agent", "do it in a separate branch", "agent new", or when multiple independent tasks need parallel execution. Manages coding agents via tmux + git worktree + claude -p.

Pythonコードのリーダブルコード原則に基づくレビュー・改善・リファクタリングを行う際に使用。「コードレビュー」「コードを読みやすくして」「リーダブルコードの観点でチェック」「命名を改善して」「保守性を向上」「可読性を改善」「リファクタリング」「ベストプラクティスを適用」という依頼で起動。AI駆動開発時代における「理解速度最大化」を重視し、命名・制御フロー・コメント・構造・責務分離の改善を提案。

归档实验性工作流中已完成的变更。当用户想要在实现完成后最终确定并归档变更时使用。

Search patterns for RepoQL - semantic search, scoping, boost/penalize.

Full URL analysis and extraction

Analyze, audit, and update project dependencies for security, licensing, and freshness. Use when managing package updates or reviewing dependency health.