发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
contact-center/web
Zoom Contact Center SDK for Web. Use for web chat/video/campaign embeds, engagement event handling, app-context integrations, and Smart Embed postMessage workflows.
naiba-openai-managers
ChatGPT use cases and prompts for managers | Part of naiba-openai-work-assistant
agency-quick
60-Second Agency Snapshot — a rapid five-dimension assessment without subagents that outputs a compact scorecard
recruit-onboard
30/60/90 Day Onboarding Plan — Day 1 setup, Week 1 ramp, Month 1 milestones, Month 2 contributions, Month 3 evaluation criteria
recruit-score
Deep Single-Candidate Scoring — evaluate one candidate across 5 dimensions (skills match, experience relevance, culture fit signals, growth potential, red flags) with final 0–100 score and hire/no-hire signal
yonyou-pptx
Yonyou high-end BG solution PPT design specification (PPTX version). Invoked when generating Yonyou-branded PPTs; includes standards for color palette, fonts, layout, and decorative elements. Suitable for scenarios such as enterprise AI bootcamp proposals, solution briefings, and customer case presentations.
axe-ios-simulator
iOS Simulator automation using AXe CLI for touch gestures, text input, hardware buttons, screenshots, video recording, and accessibility inspection. Use when automating iOS Simulator interactions, writing UI tests, capturing screenshots/video, or inspecting accessibility elements. Triggers on iOS Simulator automation, AXe CLI usage, simulator tap/swipe/gesture commands, or accessibility testing tasks.
doc-comment-adder
Batch-add or fill documentation comments for code files or directories, supporting Rust and TypeScript. When a user requests actions like “add documentation comments to this file” or “add documentation comments to every file in this directory”, it generates consistent, readable doc comments that follow the language conventions.
verification-contract
Use when defining done, acceptance criteria, proof of completion, ticket sign-off, PRD verification, or the evidence needed before claiming work is complete.
multi-agent-workflows
Orchestrate parallel local agents across Docker, Kubernetes, CI runners, and SSH. Use when decomposing work into independent subtasks, fan-out analysis or refactoring, test sharding, multi-phase pipelines with dependency graphs, or aggregating results from concurrent agents. Triggers include "parallelize this", "run multiple agents", "fan out", "distribute tasks", "orchestrate agents", "run N agents in parallel", "shard tests", or "DAG of agent tasks". Do NOT use for single-shot tasks, `/orchestrate`-suitable jobs, or cloud-managed runs (use `oz agent run-cloud`).
cost-tracking
Tracks and reports Claude Code token usage, spending, and budgets from a local cost-tracking database. Use it to ask about costs, spending, usage, tokens, budgets, or cost breakdowns by project, tool, session, or date.
bdpan-storage
百度网盘文件管理 Skill。支持上传、下载、转存、分享、列表查询、搜索、移动、复制、重命名、创建文件夹。当用户提及"百度网盘"/"bdpan"/"网盘"并涉及文件操作(上传/下载/转存/分享/查看/搜索/移动/复制/重命名/新建文件夹/登录/注销)时触发。用户说"上传到网盘"、"从百度网盘下载"、"转存到网盘"、"分享文件到网盘"、"查看网盘文件"、"搜索网盘文件"、"移动网盘文件"、"复制网盘文件"、"重命名网盘文件"、"在网盘创建文件夹"、"登录百度网盘"等均应触发此 Skill。
prompt_optimizer
Optimizes programming prompts using the Antigravity Framework to eliminate boilerplate and architectural debt. Use this skill BEFORE writing code when the user provides a high-level requirement or if the user explicitly asks to "optimize prompt" or "apply antigravity".
terraform-module-library
Build reusable Terraform modules for AWS, Azure, and GCP infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.
performance-engineer
Expert in system optimization, profiling, and scalability. Specializes in eBPF, Flamegraphs, and kernel-level tuning.
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
skill-management
Install, uninstall, and list agent skills. Handles NTFS hardlinks for auto-sync with source repos.
UI Mockups
Guidance on producing UI wireframes and concept mockups using text, markdown, and diagrams.
audit-sampling-calculator
Statistical and non-statistical audit sampling skill with sample size determination and evaluation
cross-env-setup
Configure cross-env for cross-platform environment variable setting in npm scripts and CLI commands.
ddmrp-buffer-manager
Demand-Driven MRP buffer positioning and management skill with dynamic adjustment
forward-rendering
Forward+ and clustered rendering skill for transparency handling.
gas-optimization
Advanced gas optimization techniques for EVM smart contracts. Covers storage packing, memory vs calldata optimization, assembly/Yul, efficient data structures, batch operations, and benchmark-driven optimization strategies.
interview-questions
Generate competency-based and behavioral interview questions with legal compliance validation