Prompts
Prompt engineering and templates
buff
by SimHacker
Temporary effects system — curses are just shitty buffs
empathic-templates
by SimHacker
"Smart templates that understand semantic intent, not just string substitution"
ai-ml-development
by travisjneuman
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
auto-claude
by travisjneuman
Autonomous multi-agent coding with git worktree isolation, QA validation, and memory. Use for complex features requiring autonomous implementation.
Sensor Management Skill
by markus41
Energy energy kWh
Local LLM Integration Skill
by markus41
Timeout errors Increase client timeout, use streaming
specialist-subagents
by markus41
Designs specialist sub-agents with bounded scope, tools, and lifecycle.
CLI Yes Automation Skill
by snomiao
MIT - See project repository for details
request-analyzer
by smallnest
Proactively analyze user requests at the start of conversations to determine task type, assess prompt quality, and intelligently recommend which skills to activate. Should activate for ALL user requests to ensure optimal workflow. Evaluates clarity, specificity, and completeness to suggest prompt-optimizer when needed. Identifies UI design tasks for ui-analyzer and component requests for react-component-generator. Acts as intelligent skill coordinator.
pydantic-ai-agent-creation
by existential-birds
Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.
agent-teams
by travisjneuman
Team composition knowledge for Claude Code Agent Teams - when to suggest teams, optimal sizing, spawn prompt patterns
pydantic-ai-model-integration
by existential-birds
Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.
adr-writing
by existential-birds
Write Architectural Decision Records following MADR template. Applies Definition of Done criteria, marks gaps for later completion. Use when generating ADR documents from extracted decisions.
receive-feedback
by existential-birds
Process external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.
deepagents-architecture
by existential-birds
Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware approaches.
pydantic-ai-dependency-injection
by existential-birds
Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or any external resources.
reclaude
by brianlovin
Refactor CLAUDE.md files to follow progressive disclosure principles. Use when CLAUDE.md is too long or disorganized.
skill-creator
by brianlovin
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
core-workflow
by travisjneuman
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, testing strategy, and communication standards.
template-skill
by smallnest
Replace with description of the skill and when Claude should use it.
drama-creator
by GongLingRui
创作竖屏短剧剧本，包括宏观建构、剧本创作、精准优化、创意发想。适用于从零开始创作短剧、优化现有剧本、设计故事大纲和悬念钩子
llm-judge
by existential-birds
LLM-as-judge methodology for comparing code implementations across repositories. Scores implementations on functionality, security, test quality, overengineering, and dead code using weighted rubrics. Used by /beagle:llm-judge command.
advanced-evaluation
by shipshitdev
Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.
subagent
by jxnl
Delegate codebase exploration or scripted actions to a non-interactive Codex exec run (codex exec / codex e). Use when you want a subagent to read lots of code or take actions without human interaction, and you can accept CLI output and optional file changes as the result.