ๅฐ้AIใจใผใธใงใณใใใผใ ใ็ตฑๆฌใใใชใผใฑในใใฌใผใฟใผใ่ฆๆฑใๅ่งฃใใๆๅฐใฎใจใผใธใงใณใใใงใผใณใ่จญ่จใใAUTORUNใขใผใใงใฏๅใจใผใธใงใณใๅฝนใๅ ้จๅฎ่กใใฆๆ็ตใขใฆใใใใใพใง่ชๅ้ฒ่กใใใ
Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis
Tools and frameworks for AI red teaming including PyRIT, garak, Counterfit, and custom attack automation
Finetune LLMs to speak Slipstream natively - complete guide with GLM-4-9B
AIDA pipeline orchestration with Task tool multi-agent delegation. Manages 5-phase workflow with Leader/Player subagents.
This skill should be used when the user asks about "training loop", "Learner", "metrics", "dataset", "dataloader", "checkpointing", "optimizer", "learning rate scheduler", "custom training", or Burn training workflows.
Enables TimeGPT model fine-tuning on custom datasets with Nixtla SDK. Guides dataset preparation, job submission, status monitoring, model comparison, and accuracy benchmarking. Activates when user needs TimeGPT fine-tuning, custom model training, domain-specific optimization, or zero-shot vs fine-tuned comparison.
This skill should be used when the user asks "what is agent-runtime", "why use agent-runtime", "what does this repo do", "agent runtime architecture", "how does agent-runtime work", or needs to understand the purpose, value proposition, and high-level architecture of the @hhopkins/agent-runtime monorepo.
Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.
SOP for creating new Claude Code skills. Use when adding a new skill to any project or globally.
Use when an agent encounters a blocking decision or when proceeding without user input could lead to wasted work - helps Claude determine when to block and request user input versus making reasonable assumptions
Synthesize consensus implementation plan from multi-agent debate reports using external AI review
ๅๅปบๆฐ็ Agent Skill ๆไผๅ็ฐๆ Skillใๅฝ็จๆท้่ฆ็ผๅ SKILL.mdใๅฎกๆฅ Skill ่ดจ้ใๆน่ฟ Skill ็ปๆใๆๅญฆไน Skill ๆไฝณๅฎ่ทตๆถไฝฟ็จใๆ นๆฎๅฎๆนๅไฝๆๅ่ชๅจ็ๆ็ฌฆๅ่ง่็ Skill ๆไปถใ
Generate AI images using Google Gemini via OpenRouter. Use when the user wants to create images, generate pictures, make AI art, edit images, or transform photos. Supports both text-to-image and image-to-image generation.
Explains result schema classes for Synapse plugin actions. Use when the user mentions "TrainResult", "InferenceResult", "ExportResult", "UploadResult", "WeightsResult", "MetricsResult", "result_model", "result schema", or needs help with action return type validation.
้ซๆskillๅๅปบๆๅใๅฝ็จๆทๅธๆๅๅปบๆฐ็skill๏ผๆๆดๆฐ็ฐๆskill๏ผ๏ผไปฅ้่ฟไธไธ็ฅ่ฏใ็นๅฎๅทฅไฝๆตๆๅทฅๅ ท้ๆๆฅๆฉๅฑ Claude ็่ฝๅๆถ๏ผๅบไฝฟ็จๆญค้กนๆ่ฝใ
Extract and read Claude conversation JSONL files with composable filters (discovery: rubber-duck). Evaluate at rubber-duck or at any point in the sesssion when task requires reading conversation history, verifying tool outputs, or auditing session behavior. Use instead of raw Read/grep on ~/.claude/projects/*.jsonl files.
Self-learning capability for agents. Captures execution traces, extracts insights, and adapts agent behavior. Use after completing complex tasks, when agents encounter recurring issues, or to optimize workflows over time. Critical for multi-agent systems like orchestrator, worker, and reviewer.
Analyze and transform code for TimeGPT-1 to TimeGPT-2 migration. Use when upgrading TimeGPT version. Trigger with 'migrate to TimeGPT-2' or 'upgrade TimeGPT'.
Educational AI system with personalized learning, curriculum design, and adaptive mentorship
Clean up oversized ~/.claude.json file to prevent token limit errors. Use when Read tool fails with 'exceeds maximum allowed tokens' or to maintain Claude config performance.
Expert-level AI implementation, deployment, LLM integration, and production AI systems
Produzir auditoria de colapso semantico em RAG, taxonomia hierarquica e schema de Graph-RAG para sistemas de recuperacao. Usar quando o usuario pede diagnostico de alucinacao/queda de precisao em vector stores, arquitetura RAG hierarquica ou grafo de conhecimento.
