funsloth-hfjobs
Training manager for Hugging Face Jobs - launch fine-tuning on HF cloud GPUs with optional WandB monitoring
发现 content media 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。
Training manager for Hugging Face Jobs - launch fine-tuning on HF cloud GPUs with optional WandB monitoring
Training manager for RunPod GPU instances - configure pods, launch training, monitor progress, retrieve checkpoints
Generate comprehensive model cards and upload fine-tuned models to Hugging Face Hub with professional documentation
Generate Unsloth training notebooks and scripts. Use when the user wants to create a training notebook, configure fine-tuning parameters, or set up SFT/DPO/GRPO training.
Deep expertise for documentation content creation. Templates, platform formatting guides, and style principles. Auto-loads for doc-writer agent.
LLMが外部サービスと対話するための適切に設計されたツールを通じて、高品質なMCP (Model Context Protocol) サーバーを作成するためのガイド。Python (FastMCP)、Node/TypeScript (MCP SDK)、Rust (Tokio)で、外部APIやサービ...
Universal debugger skill that diagnoses workflow issues and proposes solutions using a persistent knowledge base
Generates implementation specifications from conversation context optionally enriched with GitHub issue data
Searches logs by content keywords, patterns, and filters with context extraction
Delegate coding tasks to Codex CLI (OpenAI gpt-5-codex via JetBrains AI). Use when a task involves repetitive code generation, refactoring, or analysis that can be offloaded.
This skill should be used when the user asks to "create a slash command", "write a command file", "add command to plugin", "create /command", "write command frontmatter", "add command arguments", "configure com...
Research-backed skill creation workflow with automated firecrawl research gathering, multi-tier validation, and comprehensive auditing. Use when "create skills with research automation", "build research-backed...
This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction pa...
This skill should be used when the user asks to "create a hook", "write hook config", "add hooks.json", "configure event hooks", "create PreToolUse hook", "add SessionStart hook", "implement hook validation", "...
Comprehensive Three.js and React Three Fiber skill for creating 3D scenes, characters, NPCs, procedural generation, animation retargeting, and interactive experiences. Use when user asks to "create Three.js sce...
Orchestrate parallel CLI agents (Claude Code, Codex, Gemini) for competitive evaluation. Use when user says "run multi-agent", "compare agents", "launch competitive evaluation", "use parallel agents", or comple...
Use when user says "resume session", "what did I work on", or "find conversation about [topic]". Automatically searches, resumes, and analyzes Claude Code sessions. Handles session discovery, content search, an...
Create/improve self-healing Claude Code skills with Knowledge Framework and version tracking. Use when user says "create skill", "improve skill", "update skill", "fix skill error", "создай скил", "улучши скил",...
Generates production-ready BAML applications from natural language requirements. Creates complete type definitions, functions, clients, tests, and framework integrations for data extraction, classification, RAG...
Use when starting any conversation - establishes mandatory workflows for finding and using ZenPowers skills, including using Read tool before announcing usage, following brainstorming before coding, and creatin...
Comprehensive guide for creating Claude Code plugins with commands, agents, skills, hooks, and MCP servers. Use when users want to create, modify, or understand plugins, marketplaces, or any plugin components.
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation,...
Helps execute Frank's daily workflow using the FRANKX-SUPERINTELLIGENT-AGENT-SYSTEM, Starlight Intelligence, and productivity methodologies for conscious creation
ChatGPT-style deep research strategy with problem decomposition, multi-query generation (3-5 variations per sub-question), evidence synthesis with source ranking, numbered citations, and iterative refinement. U...
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。