Найдите подходящую возможность для вашего агента.
Generate images using Google Gemini NanoBanana via browser automation. Use this skill for general-purpose AI image generation from text prompts. Includes persistent authentication, automatic environment setup, and reference image support for style matching.
Diagnoses and resolves common Model Context Protocol (MCP) server connection issues with OpenAI Agents SDK
Mine AI research insights and generate professional LaTeX reports for creta.mx (Center for Research on Economics and Technology Applications). Triggers on "CRETA", "research insights", "LaTeX report", or economics/technology documentation requests.
Interactive clarification mode for uncertain situations. Use only when user invokes with --askme flag.
SuperClaude 增强层 Skill，为其他 Skills 提供 SuperClaude 能力增强。 支持前置分析、后置审查、智能建议等增强模式。
Provide a repeatable decision workflow to choose the right Codex primitive (Skill vs Custom Prompt vs Agent/automation) for any requested capability.. Use when Use this skill when the task matches its description and triggers..
[23] UNDERSTAND. Consult external AI models when internal sources are exhausted. Build quality prompts using Prompt150 formula (Context + Query + Method + Style). Use when Loop150 exhausts internal sources, need real-world precedents, confidence <75%, or require reasoning from specialized AI models.
Provides Chinese technical documentation writing guidelines. Use when creating new technical guides, editing existing docs to follow standards, or reviewing document format and structure.
Generates new agent skills following the official Agent Skills specification. Use when you need to teach the AI a new capability, create reusable workflows, or document best practices in a structured format.
This skill should be used when creating or refactoring Claude Code skills, guiding an interactive questionnaire, selecting an archetype (workflow/tool/domain), scaffolding from templates, and validating the result. Triggers include "create skill", "new skill", "scaffold skill", "bootstrap skill".
Deterministic multi-agent orchestration system for LMStudio enabling constraint-driven agent composition, semantic field navigation, and thermodynamic resource allocation. Use when orchestrating local LLM swarms, building multi-agent systems with validation, implementing constraint-based configurations, or requiring deterministic agent composition from discovered model states.
This skill helps create React chat widgets using the ChatKit React library, following best practices for floating chat interfaces with thread persistence and proper configuration.
This skill should be used when the user asks about "build trigger", "webhook trigger", "poll trigger", "dynamic webhook", "static webhook", "hybrid trigger", "dedup", "trigger_limit", "closure", or needs to implement triggers for a Workato custom connector.
Use this skill when editing files in ai/ or .claude/ folders.
Gemini expert consultation for architecture design, second opinions, and code review. Use when: user requests Gemini, need alternative perspective, or get independent review. Gemini 是与 Claude 同等级别的顶级 AI 专家，按需调用。 **注意：前端/UI 任务应使用专门的 Frontend 代理！**
Claude Code Commands system, workflow orchestration, and command-line interface patterns. Use when creating custom commands, managing workflows, or implementing CLI interfaces.
