Найдите подходящую возможность для вашего агента.
Automatically find relevant context from knowledge graph and code relationships while coding. Detects when context would be helpful (new files, unfamiliar code, architectural decisions) and surfaces related entities, prior decisions, and code dependencies.
Extract readable transcripts from Claude Code and Codex CLI session JSONL files
將提示詞和程式碼從 Claude Sonnet 4.0、Sonnet 4.5 或 Opus 4.1 遷移至 Opus 4.5。當使用者想要更新其程式碼庫、提示詞或 API 呼叫以使用 Opus 4.5 時使用。處理模型字串更新和針對已知 Opus 4.5 行為差異的提示詞調整。不會遷移 Haiku 4.5。
Advanced intent interpretation system using cognitive science principles and probabilistic intent mapping
Creates new Claude Code slash commands following best practices. Guides through command structure, naming, arguments, and frontmatter. Use when user wants to create a command, build a slash command, or asks about command best practices.
Integrate Replicate AI models with background processing, S3 storage, and credit systems
Provides guidance on Cursor ↔ Claude Code 2-agent workflow. Use when user mentions ワークフローについて, Cursorとの連携, 作業の流れ, 2-agent workflow, collaboration. Do NOT load for: 実装作業, ワークフロー設定, ハンドオフ実行.
Build ChatGPT Apps using the Apps SDK and MCP. Use when users want to: (1) Evaluate if their product should become a ChatGPT App (2) Design and implement MCP servers with widgets (3) Test apps locally and in ChatGPT (4) Prepare for App Store submission Triggers: "ChatGPT app", "Apps SDK", "build for ChatGPT", "ChatGPT integration", "MCP server for ChatGPT", "submit to ChatGPT"
Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Create a FiftyOne dataset from a directory of media files (images, videos, point clouds), optionally import labels in common formats (COCO, YOLO, VOC), run model inference, and store predictions. Use when users want to load local files into FiftyOne, apply ML models for detection, classification, or segmentation, or build end-to-end inference pipelines.
Monitors Claude's responses for struggle signals and suggests escalation to deep-thinking agents when complexity exceeds comfortable reasoning capacity.
TOON (Token-Oriented Object Notation) encoding for LLM-efficient data representation. 30-60% token savings vs JSON for structured data.
Use this skill when user asks to "review code", "check for issues", "analyze code quality", "find bugs", or wants feedback on code implementation.
Auto-invoke after task completion to extract interview-ready STAR stories from completed work.
Creates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .claude-flow, combined with evidence-based prompting techniques and Claude Agent SDK implementation. Use this skill when creating production-ready agents for specific domains, workflows, or tasks requiring consistent high-quality performance with deeply embedded domain knowledge.
Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimization, and real examples
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.
Prevents 30+ critical AI/ML mistakes including data leakage, evaluation errors, training pitfalls, and deployment issues. Use when working with ML training, testing, model evaluation, or deployment.
