skill-architect
The master skill for analyzing, designing, and standardizing the creation of new AI skills (Skill 72).
发现 devops llm ai 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
The master skill for analyzing, designing, and standardizing the creation of new AI skills (Skill 72).
Protecting personal and sensitive data throughout the machine learning lifecycle, from training to inference.
Design patterns for building autonomous AI agents that can reason, plan, and execute tasks.
Checklist สำหรับตรวจสอบและกำจัด bloat ใน context, prompt, และ response เพื่อลด token cost และเพิ่ม signal-to-noise ratio
Comprehensive guide to evaluating Retrieval-Augmented Generation systems including retrieval metrics, generation quality, faithfulness, and end-to-end evaluation frameworks
Comprehensive guide to sandboxing AI agents including code execution isolation, resource limits, security boundaries, and safe tool execution
Interactive skill for adapting BMAD path references and enhancing skill content. Reviews skills for {project-root} references and prompts for handling choices.
Bootstrap and install BMAD-METHOD skills for Claude Code, Cursor, Antigravity, and other tools.
Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, Gemini, and Opencode backends with file references (@syntax) and structured output.
Searches Canva's Glean knowledge base for internal documentation, policies, how-tos, Slack threads, and company information. Use when asked about Canva processes, internal docs, Slack conversations, or company...
Apply Reflective Thought Composition (RTC) for deep analysis of complex problems. Use when facing complex tasks requiring structured reasoning.
Discover and analyze Claude Code session logs from ~/.claude/projects, including finding the current session and extracting tool calls, user messages, and conversation history
Use when you need to generate game art - sprites, textures, 3D model concepts. Uses FREE HuggingFace AI models.
Generate production-ready Workscript workflow JSON files for the Workscript Agentic Workflow Engine with built-in defensive guards and complexity detection. Use when asked to create workflows, automations, data...
Analyze user feedback and edit existing skills to perfection by applying targeted enhancements. Use when users want to improve, refine, iterate on, or perfect an existing skill based on specific feedback. Trigg...
Generate comprehensive {node_name}.example.json files that showcase real-world usage of Workscript workflow nodes. Use when asked to document a node, create node documentation, generate node examples, or produc...
Use when generating email replies for Michael, drafting emails, or tuning email response style. Provides Michael's email communication patterns and style guide.
Use when generating WhatsApp replies for Michael, auto-replying to messages, or tuning message response style. Provides Michael's communication patterns and style guide.
Use when working with clawdbot, configuring messaging bindings, WhatsApp/iMessage/Telegram channels, or managing agent identities. Auto-load when user mentions clawdbot, messaging bots, or channel configuration...
Use when generating multiple presentation slide images, creating slide decks with AI-generated visuals, or iterating on slide designs with image generation.
"Transform service catalog into high-ticket portfolio assets with progressive complexity: basic workflow or advanced Claude Code 2.1.0 features with agent coordination"
This skill should be used when the user asks to "create admin interfaces", "build self-service tools", "generate debugging tools", "create monitoring dashboards", "automate troubleshooting", or needs comprehens...
"Advanced portfolio development with Claude Code 2.1.0 agent lifecycle management, hot-reloadable skills, and parallel processing optimization"
This skill should be used when coordinating "multiple specialized agents", "complex workflow orchestration", "autonomous development teams", "agent collaboration", "distributed task management", or when managin...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。