Prompts
Prompt engineering and templates
damage-control
by cfircoo
Install, configure, and manage Claude Code security hooks that block dangerous commands and protect sensitive files. Use when setting up security protection, blocking destructive commands (rm -rf, git reset --hard), protecting sensitive paths (.env, credentials), or managing PreToolUse hooks.
claude-code-usage
by 0xlayerghost
"[AUTO-INVOKE] MUST be invoked at the START of each new coding session. Covers context management, task strategies, and Foundry-specific workflows. Trigger: beginning of any new conversation or coding session in a Solidity/Foundry project."
svelte5-runes
by linehaul-ai
Svelte 5 runes guidance. Use for reactive state, props, and effects. Covers $state, $derived, $effect, $props, $bindable. Prevents mixing syntaxes and reactivity mistakes.
create-skill
by danielmiessler
Guide for creating new skills in Kai's personal AI infrastructure. Use when user wants to create, update, or structure a new skill that extends capabilities with specialized knowledge, workflows, or tool integrations. Follows both Anthropic skill standards and PAI-specific patterns.
pseo-llm-visibility
by lisbeth718
Optimize programmatic SEO pages for visibility and citation in AI-generated answers from ChatGPT, Perplexity, Google AI Overviews, and other LLM-powered search. Use when optimizing for LLM citation, implementing llms.txt, configuring AI crawler access, structuring content for AI extraction, or when the user asks about generative engine optimization (GEO), AI search visibility, or getting cited by AI.
agent-swarm
by lidpeng
创建和编排多智能体集群完成复杂任务。当用户需要将复杂任务拆解给多个专业智能体并行或串行执行时使用此技能。适用场景：(1) 复杂项目需要多角色协作（规划、调研、编码、写作、设计、分析、审核）(2) 需要并行执行多个独立子任务以提高效率 (3) 需要专业分工以优化成本和质量。关键词：多智能体、Agent集群、任务编排、并行执行、智能体团队。
claude-agent-sdk
by ovachiever
Build autonomous AI agents with Claude Agent SDK. Structured outputs (v0.1.45, Nov 2025) guarantee JSON schema validation, plugins system, hooks for event-driven workflows. Use when: building coding agents with validated JSON responses, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors.
tavus-cvi-interactions
by Tavus-Engineering
Control Tavus CVI conversations in real-time using the Interactions Protocol. Use when sending text for the replica to speak (echo), interrupting the replica, injecting context mid-conversation, handling tool calls, or listening to conversation events via WebRTC/Daily.
axolotl
by ovachiever
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
ai-sdk-core
by ovachiever
Build backend AI with Vercel AI SDK v5/v6. Covers v6 beta (Agent abstraction, tool approval, reranking), v4→v5 migration (breaking changes), latest models (GPT-5/5.1, Claude 4.x, Gemini 2.5), Workers startup fix, and 12 error solutions (AI_APICallError, AI_NoObjectGeneratedError, streamText silent errors). Use when: implementing AI SDK v5/v6, migrating v4→v5, troubleshooting errors, fixing Workers startup issues, or updating to latest models.
biomni
by ovachiever
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.
review-documentation
by Xexr
Use when documentation has been created or updated and the user has asked to review - MD files, beads issues, specs, or task lists
animation-review
by jaaaaaaaaaaack
Review web animations by recording the browser and sending video to Gemini for frame-level analysis
swarm run
by mj1618
```
prompt-engineering
by breethomas
Expert prompt optimization system for building production-ready AI features. Use when users request help improving prompts, want to create system prompts, need prompt review/critique, ask for prompt optimization strategies, want to analyze prompt effectiveness, mention prompt engineering best practices, request prompt templates, or need guidance on structuring AI instructions. Also use when users provide prompts and want suggestions for improvement.
build-judge
by breethomas
Build an LLM-as-Judge evaluator for one specific failure mode. Binary pass/fail only. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness) and cannot be checked with code. Do NOT use when the failure can be checked with regex, schema validation, or execution tests. Do NOT use before completing error analysis (/upgrade-evals).
upgrade-evals
by breethomas
Systematic error analysis on real AI traces. Read traces, judge pass/fail, let failure categories emerge from data, compute failure rates, decide what to fix. Use when you have 50+ test cases or are seeing production failures. Do NOT use when you have fewer than 20 test cases (use /start-evals first).
ai-cost-check
by breethomas
Calculate AI feature costs and challenge if you actually need it. Invokes ai-cost-analyzer agent for detailed economics modeling.
eval-rag
by breethomas
Evaluate RAG pipeline retrieval and generation quality separately. Measure Recall@k, Precision@k, MRR, NDCG@k for retrieval. Assess faithfulness and relevance for generation. Use when the AI feature uses retrieval (search, knowledge base, document QA). Do NOT use for non-RAG AI features.
assemblyai-streaming
by ratacat
This skill should be used when working with AssemblyAI’s Speech-to-Text and LLM Gateway APIs, especially for streaming/live transcription, meeting notetakers, and voice agents that need low-latency transcripts and audio analysis.
claude-md-authoring
by ratacat
Creates and reviews CLAUDE.md configuration files for Claude Code. Applies HumanLayer guidelines including instruction budgets (~50 user-level, ~100 project-level), WHAT/WHY/HOW framework, and progressive disclosure. Identifies anti-patterns like using Claude as a linter for style rules.
create-agent-skill
by ratacat
Create or edit Claude Code skills with expert guidance on structure and best practices
prompting-pattern-library
by Exploration-labs
Comprehensive library of proven prompting patterns, frameworks, and examples for different use cases. This skill should be used when creating prompting guides, analyzing prompt effectiveness, teaching prompting techniques, or troubleshooting prompting issues. Use when writing about prompting, explaining prompting concepts to others, or improving existing prompts.
agent-native-architecture
by ratacat
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.