搜索结果
全部能力
找到 17783 个相关结果
软件工程 / 诊断修复
accessibility
accessibility
Expert in web accessibility (WCAG 2.1 AA compliance) for React/Next.js applications, ensuring all projects are usable by everyone
软件工程 / 部署发布
agent-skill-deploy
agent-skill-deploy
Deploys agent skill collections from any GitHub repository with a /skills folder to one or more distribution surfaces: GitHub releases, Claude Code marketplace, VS Code plugin marketplace, and Copilot CLI plugin marketplace. Handles pre-flight validation, conventional commit analysis, version bumping across surface configs, and surface-specific publishing with dry-run support. Use when releasing, publishing, or deploying a skills collection to any supported marketplace or creating a GitHub release for a skills repository. Don't use for deploying non-skill packages, npm modules, Docker images, or Azure resources.
通用助手 / 编排推荐
claude-cookbooks
claude-cookbooks
Claude AI cookbooks - code examples, tutorials, and best practices for using Claude API. Use when learning Claude API integration, building Claude-powered…
软件工程 / 诊断修复
pict-test-designer
pict-test-designer
Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT…
通用助手 / 编排推荐
ai-agent-design
ai-agent-design
Use this skill when designing AI agent architectures, implementing tool use, building multi-agent systems, or creating agent memory. Triggers on AI agents, tool calling, agent loops, ReAct pattern, multi-agent orchestration, agent memory, planning strategies, agent evaluation, and any task requiring autonomous AI agent design.
通用助手 / 编排推荐
ai-llm-inference
ai-llm-inference
LLM inference patterns — latency budgeting, caching, batching, quantization, and parallelism. Use when optimizing serving cost or tail latency.
设计与产品 / 审核评估
add-navigation
add-navigation
Wires the Navigation component from @cognite/dune-industrial-components/navigation into a Dune app. Use when adding a navigation header, top nav bar, sticky…
安全与治理 / 审核评估
speakeasy
speakeasy
|
通用助手 / 编排推荐
accessibility
accessibility
Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader…
软件工程 / 诊断修复
clawflows
clawflows
OpenClaw workflow automation: multi-step task chains, conditional logic, triggers, schedule
通用助手 / 编排推荐
f1-test-drive
f1-test-drive
Orchestrate F1 test drives to validate the Cyrus agent system end-to-end across issue-tracker, EdgeWorker, and activity rendering.
通用助手 / 编排推荐
base
base
Placeholder for Base skill.
通用助手 / 编排推荐
cta-writing
cta-writing
Master the art of calls-to-action that convert. Direct CTAs, transitional CTAs, button copy, and microcopy that turns readers into customers. Use when: Writing…
通用助手 / 编排推荐
marketing-paid-advertising
marketing-paid-advertising
Paid advertising strategy for Google, Meta, TikTok, LinkedIn - campaign structure, bidding, audiences, creative, measurement, budget allocation, unit economics…
软件工程 / 诊断修复
imessage-query
imessage-query
Query macOS iMessage database (chat.db) via SQLite. Decode NSAttributedString messages, handle tapbacks, search conversations.
自动化与集成 / 自动执行
prisma
prisma
Prisma integration. Manage data, records, and automate workflows. Use when the user wants to interact with Prisma data.
通用助手 / 编排推荐
session-documenter
session-documenter
Document session work to .agents/SESSIONS/YYYY-MM-DD.md. Use when user says 'document session', 'save session', 'what did we do', or when invoked by…
软件工程 / 诊断修复
market-sizer
market-sizer
Use this skill when users need to calculate market size (TAM/SAM/SOM), assess market opportunity, validate market potential, or determine if a market is big…
软件工程 / 部署发布
mongodb-atlas-checker
mongodb-atlas-checker
Verify MongoDB Atlas setup and configuration for backend applications. Checks connection strings, environment variables, connection pooling, and ensures proper…
通用助手 / 编排推荐
prompt-enhancer
prompt-enhancer
Knowledge for transforming poor or overly simple user prompts with expert-level framing. Triggers include: user explicitly asking to improve/refine/rewrite their prompt or user requesting help framing a request for another AI system.