发现 tools 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。
Debug detection and routing misclassifications in OpenEvent-AI (LLM vs regex, qna_types, confirmations, OOC drops, site-visit triggers). Use when intent seems wrong, Q&A is ignored, confirmations route to the w...
Apply Jesse's confident-but-vulnerable voice to all content. Use when writing service pages, blog posts, CTAs, emails, or checking if content sounds like Jesse. Reference: /docs/branding/voice/BRAND-VOICE.md
Generate FAQ sections with proper FAQPage schema markup for therapy pages. Creates 10-12 therapy-specific questions, 50-100 word answers, and valid JSON-LD schema. Optimized for Google rich snippets (health web...
Master coordinator for NextStep Therapy's 12 skills. Diagnoses what the user needs, routes to appropriate skills, manages state across sessions, and handles context handoffs with Context Paradox awareness. Use...
Orchestrates complete feature discovery and planning by running specs-writer, frontend-architect, frontend-reviewer, backend-architect, and backend-reviewer agents sequentially to generate comprehensive, rule-c...
Creates a new skill for the Antigravity agent environment based on user requirements. Use when the user wants to create a new skill or standardize an existing one.
Test and verify AI orchestrator features using CLI runner, unit tests, and E2E tests. ALWAYS use this skill when: implementing new features, fixing bugs, making changes to agents/orchestrator/TUI, or when asked...
Propose PR-style improvements to advisor skills based on session feedback. Use at end of advisor flow or when friction/corrections occur.
Generate coherent stack candidates based on requirements. Use when user needs stack options, technology recommendations, or architecture patterns for their project.
Global hooks for logging Claude Code conversation events to markdown files. Tracks prompts, tool usage, and responses across all sessions. Useful for debugging, auditing, and providing conversation context to C...
Expert guidance for creating, building, and using Opencode sub-agents and the `delegate_to_agent` tool. Use when working with sub-agents, setting up agent configurations, understanding how agents work, or using...
Expert guidance for creating, configuring, and using Opencode hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding ho...
Expert guidance for creating, writing, building, and refining Opencode Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best pr...
Create optimized prompts for Agent-to-Agent pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage work...
Expert guidance for creating Opencode slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML configuration.
Create hierarchical project plans optimized for solo agentic development. Use when planning projects, phases, or tasks that the agent will execute. Produces agent-executable plans with verification criteria, no...
Advance a VibeDev workflow from chat. Use when the user types `$vd-next` / says “vd next” and wants the agent to fetch the next compiled step prompt from the VibeDev MCP HTTP server (`vibedev-mcp serve`) and ha...
Create or refine a VibeDev Studio UnifiedWorkflow graph via tool calls. Use when the user says `$vd-create`, asks the model to “build the workflow graph”, “set up Research/Planning/Execution/Review steps”, or w...
Automatically analyze tasks and route to optimal agent(s). Use when receiving complex requests to determine which agents to spawn.
Coordinate simultaneous agent execution for independent tasks. Use when multiple tasks can run in parallel without dependencies.
Adaptive teaching skill that frames explanations in student's interest domain and uses their preferred learning style. Auto-invoked when teaching programming concepts, creating problems, or providing feedback.
Expert Python engineering for code review, quality improvement, and debugging. Use when reviewing Python code for best practices, refactoring for cleaner code, debugging errors, improving type safety with type...
從公開新聞、法說會摘要中識別公司在 AI 伺服器或車用供應鏈中的具體地位與合作品牌。
Generate personalized post-call landing pages from voice transcripts using the Brutalist Confidence design system.
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。