工具
開發工具、實用程式和生產力輔助
17720 skills in this category
repo-facts
Summarize an arbitrary code repo (git or non-git) into a small, high-signal facts packet: languages, build/test tooling clues, notable paths, and size stats.
start-issue
Set up a GitHub issue for development with branch, worktree, and planning doc. Use when user says "start issue", "work on issue
whop-expert
Comprehensive Whop platform expert with access to 212 official documentation files covering memberships, payments, products, courses, experiences, forums, webhooks, and app development. Invoke when user mentions Whop, digital products, memberships, course platforms, or community monetization.
jira-projects
Manage Jira projects. Use when listing projects, getting project configuration, retrieving issue types, or managing components and versions.
create-subagents
Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.
git-sync-checker-enhanced
Git 仓库同步状态检查工具。检查本地与远程仓库的同步状态、预测潜在冲突、检测敏感文件和大文件。当用户提到"检查同步状态"、"检查冲突"、"批量检查仓库"、"检查 gitignore"或类似的 Git 状态分析需求时使用此技能。
ic-migrate
Migrate old IC10 code to work with current Stationeers version. Use when user has legacy IC10 scripts that don't work due to game updates or breaking changes.
lambda-invoke
This skill provides utilities to invoke Lambda functions using the AWS Lambda MCP Server (awslabs.lambda-tool-mcp-server).
1password
Securely retrieve secrets from 1Password using the 'op' CLI tool without displaying sensitive information. Use when working with API keys, tokens, passwords, SSH keys, database credentials, or any secrets stored in 1Password. All secret values are stored only in environment variables and NEVER displayed in output or context.
mcp-response-optimization
Prevent massive MCP responses from WordPress, Playwright, Notion, and other MCPs that can kill conversations on first call. Sophisticated token management for all MCP tool usage.
shopify-expert
Comprehensive Shopify development expert with access to 24 official documentation files covering APIs (GraphQL Admin, Storefront, REST), app development, themes, Liquid, Hydrogen, checkout, extensions, webhooks, Functions, CLI, subscriptions, payments, and all platform features. Invoke when user mentions Shopify, e-commerce, online store, product management, orders, checkout, themes, or headless commerce.
agent-design
This skill should be used when the user asks to "configure agent profile", "add skills to agent", "set up MCP servers", "configure agent tools", "write system prompt", "create agent workflow", "define agent commands", "add subagents", or needs to define what capabilities an agent has and how to orchestrate complex workflows in the runtime.
vector-search
Semantic search using vector embeddings and similarity metrics. Apply when implementing search with embeddings (OpenAI, Sentence Transformers) or distance-based ranking. Covers cosine similarity, Euclidean distance, dot product, and threshold selection.
td-logistic-regression
Logistic regression for binary and multinomial classification
game-dev-script-processing
游戏开发剧本处理技能 - 指导Claude Code使用游戏开发剧本处理器插件将剧本文件转换为游戏配置文件
troubleshooting
Debug event flows systematically from EventSource to Workflow. Use diagnostic commands and logging levels to isolate failures in production event systems.
phenoml-workflow
Create and execute PhenoML workflows for healthcare data processing, including condition creation from clinical notes and patient registration with deduplication
github-copilot-pr-review
Review and apply GitHub Copilot suggestions on pull requests. Trigger when reviewing PRs with Copilot suggestions.
design-brief
Creates contextual design briefs before any visual work begins. Establishes product purpose, user specificity, design principles, and anti-goals. Prevents generic "template" design by requiring specific context.
prompt-optimizer
Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system behaviors.