搜索结果
全部能力
找到 17783 个相关结果
软件工程 / 诊断修复
incident-response-smart-fix
incident-response-smart-fix
[Extended thinking: This workflow implements a sophisticated debugging and resolution pipeline that leverages AI-assisted debugging tools and observability…
软件工程 / 诊断修复
mantine-dev
mantine-dev
Mantine UI library for React: 100+ components, hooks, forms, theming, dark mode, CSS modules, and Vite/TypeScript setup. Use when building React applications…
通用助手 / 编排推荐
manic-trading-benchmark-skill
manic-trading-benchmark-skill
Run a standardized benchmark to evaluate AI trading agent capabilities on the Manic Trade platform. Use this skill when a user wants to benchmark their trading…
设计与产品 / 审核评估
multi-cloud-architecture
multi-cloud-architecture
Decision framework and patterns for architecting applications across AWS, Azure, and GCP.
通用助手 / 编排推荐
nestjs-queue-architect
nestjs-queue-architect
Queue job management patterns, processors, and async workflows for video/image processing
通用助手 / 编排推荐
mysql
mysql
Execute read-only SQL queries against multiple MySQL databases. Use when: (1) querying MySQL databases, (2) exploring database schemas/tables, (3) running…
软件工程 / 诊断修复
framer-motion-best-practices
framer-motion-best-practices
Framer Motion performance optimization guidelines. This skill should be used when writing, reviewing, or refactoring React animations with Framer Motion to…
软件工程 / 诊断修复
framework-migration-deps-upgrade
framework-migration-deps-upgrade
You are a dependency management expert specializing in safe, incremental upgrades of project dependencies. Plan and execute dependency updates with minimal…
软件工程 / 诊断修复
composio-connect
composio-connect
Universal fallback for executing actions across 1,000+ apps when no other skill is available. Use this skill ONLY when user requests an action on an…
设计与产品 / 审核评估
frontend-design
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or…
研究学习 / 检索整理
godot-debugging
godot-debugging
Expert knowledge of Godot debugging, error interpretation, common bugs, and troubleshooting techniques. Use when helping fix Godot errors, crashes, or…
通用助手 / 编排推荐
hindsight-local
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user)
软件工程 / 诊断修复
feedback-mastery
feedback-mastery
Navigate difficult conversations and deliver constructive feedback using structured frameworks. Covers the Preparation-Delivery-Follow-up model and…
软件工程 / 部署发布
contextual-commit
contextual-commit
Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.
软件工程 / 诊断修复
emotional-narrative
emotional-narrative
Use when animation needs to convey feeling, tell a story, or connect emotionally—character moments, dramatic beats, or any motion that should make the audience…
软件工程 / 部署发布
github-actions-creator
github-actions-creator
Use when the user wants to create, generate, or set up a GitHub Actions workflow. Handles CI/CD pipelines, testing, deployment, linting, security scanning,…
通用助手 / 编排推荐
test-coverage-improver
test-coverage-improver
Improve test coverage in the OpenAI Agents Python repository: run `make coverage`, inspect coverage artifacts, identify low-coverage files, propose high-impact…
软件工程 / 诊断修复
axiom-foundation-models
axiom-foundation-models
Use when implementing on-device AI with Apple's Foundation Models framework — prevents context overflow, blocking UI, wrong model use cases, and manual JSON…
软件工程 / 诊断修复
axiom-accessibility
axiom-accessibility
Use when fixing or auditing ANY accessibility issue — VoiceOver, Dynamic Type, color contrast, touch targets, WCAG compliance, App Store accessibility review.
软件工程 / 诊断修复
autonomous-skill
autonomous-skill
Execute long-running, multi-session tasks autonomously using Claude Code headless mode or in-session hook-based loops. Supports structured task decomposition (for complex projects) and lightweight Ralph-style iteration (for TDD, bug fixing, refactoring). Use this skill whenever the user says "autonomous", "long-running task", "multi-session", "run this in the background", "keep working on this", "batch process", "iterate until done", "ralph loop", or wants any task that requires sustained, unattended execution.