Prompts
Prompt engineering and templates
synth-api
by synth-laboratories
Use the Synth AI API end-to-end (SDK + HTTP) for eval + GEPA
ai-era-architecture-principles
by shimo4228
"Framework adoption decision matrix: custom vs large frameworks in the Claude Code era. Use when evaluating whether to adopt a large framework or build custom with AI."
ref-tracker
by cadrianmae
DEPRECATED in v2.0 - Replaced by hooks-based tracking. This skill is no longer needed. Use /track:init to enable automatic hooks-based tracking instead.
portkey-python-sdk
by Portkey-AI
Complete reference for the Portkey AI Gateway Python SDK with unified API access to 200+ LLMs, automatic fallbacks, caching, and full observability. Use when building Python applications that need LLM integration with production-grade reliability.
validate-skill
by plaited
Validate skill directories against AgentSkills spec
pandoc
by cadrianmae
Automatically assist with Pandoc document conversions when user mentions converting markdown to PDF/DOCX/HTML or other formats. Validate YAML frontmatter, check dependencies (bibliography, images), and provide format-specific conversion guidance. Use when user asks about citations, academic papers, presentations, or document generation from markdown.
skill-stocktaking-process
by shimo4228
"Use when learned skills exceed 10 per location or need consolidation. 4-step stocktaking with character budget awareness."
team-creator
by Pysuper
交互式 Claude Code Teams 配置生成器。通过问答式引导快速创建专业的团队配置文件，支持模板选择、角色定制、工作流构建、智能推荐和多格式输出。适用于需要创建或更新 Claude Code Teams 配置的场景。
叙事 2.0
by mtldxwz
叙事不是解释世界，是发明理解世界的新方式。
requirements-analysis
by xmx0632
分析业务需求并创建完整的软件需求规格说明书。在项目启动、新增功能或需求变更时使用。该技能会引导你完成需求收集、分析和文档化过程，确保需求清晰、完整且可验证。
progressive-disclosure
by khw1031
LLM 컨텍스트 윈도우를 효율적으로 사용하는 3단계 정보 로드 원칙. Skills, Agents, Prompts 작성 시 참조. SKILL.md, AGENT.md 작성, 프롬프트 설계, 컨텍스트 최적화 시 활성화.
check-claude-md
by Howell5
检查本次对话的改动是否需要更新项目 CLAUDE.md。分析代码变更，识别新模式和约定，建议更新内容。
cjk-aware-text-metrics
by shimo4228
"CJK/Latin weighted token estimation for multilingual LLM pipelines. Use when processing Japanese/Chinese/Korean text with fixed chars-per-token constants."
prh-hyphen-regex-escape
by shimo4228
"Use when adding hyphenated terms to prh spelling dictionaries on Node.js 20+. Unicode regex flag incompatibility."
building-agent-team-prompts
by frontboat
Provides a prompt template and best practices for building Claude Code agent teams. Covers team composition, teammate spawn prompts, task breakdown, file ownership, communication protocols, and delegate mode. Use when creating an agent team, spawning teammates, parallelizing work across multiple Claude Code instances, or deciding whether an agent team is the right approach.
web-frontend
by WebSmartTeam
Apply frontend development standards for React/Next.js/Tailwind projects. Covers colour extraction from logos, avoiding AI-slop aesthetics, performance targets (LCP <2.5s), and modern CSS patterns. Triggers: component, responsive, accessibility, styling, UI, colours, Tailwind, layout, hover states, buttons, frontend.
ai-prompt-mastery
by AtesOyuncuymus
讓 AI 發揮極致潛力的通用方法論。使用情境：(1) 覺得 AI 回答太籠統或不夠好， (2) 想要 AI 用專家級標準回答，(3) 不知道怎麼問才能得到好答案， (4) 想分享給別人讓他們也能把 AI 用好。包含即貼即用的 Prompt + 五大技巧。
receive
by cadrianmae
Receive context from parent, child, or sibling session
mcp-builder
by mcp-use
Build Model Context Protocol (MCP) servers with mcp-use framework. Use when creating MCP servers, defining tools/resources/prompts, working with mcp-use, bootstrapping MCP projects, deploying MCP servers, or when user mentions MCP development, MCP tools, MCP resources, or MCP prompts.
recursive-handoff
by SebastiaanWouters
"Execute the same task repeatedly with clean context via handoff. Triggers on: recursive loop, repeat until, keep doing until, loop until done. REQUIRES a finish condition to stop."
/fal-generate
by vorbei
/fal-setup - Configure API key
llm-caching
by RSHVR
Optimize LLM costs and latency through KV caching and prompt caching. Use when (1) structuring prompts for cache hits, (2) configuring API cache_control for Anthropic/Cohere/OpenAI/Gemini, (3) setting up self-hosted inference with vLLM/SGLang/Ollama, (4) building agentic workflows with prefix reuse, (5) designing batch processing pipelines, or (6) understanding cache pricing and tradeoffs.
loop-page-creator
by Kang-chen
Creates Loop Page documents following company SOP standards. Use when user wants to create a new Loop page, meeting record, project document, or any documentation following company's Loop workspace conventions. Triggers on keywords like "Loop", "SOP", "create document", "meeting record", "project doc", or when user needs team documentation.
directory-structure-enforcement-hooks
by shimo4228
"Use when Claude Code creates files in wrong locations despite CLAUDE.md rules. PreToolUse + Stop hook 3-layer defense."