Prompts
Prompt engineering and templates
ontos-skill-evaluator
by Ontos-AI
"Meta-skill by Ontos AI for evaluating Claude Skills quality. Use when you need to assess a SKILL.md file quality, validate its structure, detect common issues, or generate an evaluation report with actionable recommendations."
owasp-llm-top-10
by yariv1025
"OWASP Top 10 for LLM Applications - prevention, detection, and remediation for LLM and GenAI security. Use when building or reviewing LLM apps - prompt injection, information disclosure, training/supply chain, poisoning, output handling, excessive agency, system prompt leakage, vectors/embeddings, misinformation, unbounded consumption."
supabase-mcp-setup
by WebSmartTeam
Configure Supabase MCP server for a specific project using local .mcp.json (NOT global). Each project needs its own config to prevent wrong-database queries. Triggers: setup supabase mcp, install supabase mcp, configure supabase mcp, connect supabase, supabase database access, mcp not loading supabase.
gemini-gem-converter
by bluewaves-creations
Convert Agent Skills to Gemini Gems format. Use when the user wants to adapt, port, or transform a Claude skill (SKILL.md-based) into a Google Gemini Gem, or when discussing Gem constraints, knowledge file limits, and platform differences between Claude Skills and Gemini Gems.
create-project
by dwizi
Expertise in scoping, designing, and scaffolding new MCP servers using dzx. Use when the user asks to "create a project", "spin up a new MCP server", "scaffold an MCP app", or "add a new MCP service".
create-skill
by khw1031
Claude Code Skill을 생성합니다. 스킬 생성, SKILL.md 작성, 새 스킬 만들기 요청 시 활성화.
anysystem-design
by david-marstree
LLM Agent Skill for AnySystem Design React component library
session-intelligence-harvester
by NaveedTechLab
This skill should be used after productive sessions to extract learnings and route them to appropriate Reusable Intelligence Infrastructure (RII) components. Use when corrections were made, format drift was fixed, new patterns emerged, or the user explicitly asks to "harvest learnings" or "capture session intelligence". Transforms one-time fixes into permanent organizational knowledge by implementing updates across multiple files.
zeabur-template
by ridemountainpig
Expert guidance for creating, configuring, and optimizing Zeabur service templates. Use this skill when the user asks about Zeabur template creation, environment variables, or configuration.
domain-expertise-template
by ChaiWithJai
Template for creating domain expertise skills. Copy and customize for your specific domain.
skill-builder
by echohack
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.
notebooklm-slides
by NaveedTechLab
This skill should be used when generating pedagogically-aligned slide decks from educational content using NotebookLM. It addresses the convergence toward generic, text-heavy slides by providing structured prompts that create engaging, proficiency-appropriate presentations aligned with specific educational frameworks.
plugin-forge
by cachemoney
Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.
humanizer-zh
by Within-7
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
saas-pipeline
by ThomasPraun
"Use when starting a new SaaS project, checking project status, advancing to the next phase, viewing the project dashboard, or when the user mentions 'pipeline', 'saas-pipeline', 'next phase', 'project status', 'dashboard', 'idea to launch'. Orchestrates 28 skills across 8 phases: idea, business, product, architecture, design, implementation, deployment, marketing."
dianalokadalight
by ratacat
Become Diana in light mode. Ukrainian software engineer in NYC. KGB accent. Zero filter. ~2.5K tokens. Once invoked there is no going back.
elonmusk-repost
by mingyooagi
Analyze Elon Musk's repost patterns on X and generate tweets optimized for getting reposted by @elonmusk. Use when users want to craft viral AI/tech product launches targeting Musk's attention.
vault-metadata
by teslasoft-de
Frontmatter schema reference, metadata values (status, type, horizon), Dataview query patterns, and repository path integration for the Teslasoft Obsidian vault. Canonical source for all metadata conventions used across note types and templates. Keywords: frontmatter, metadata, status values, type values, horizon, Dataview, query, repoPath, repository path, schema reference
llm-integration
by pluginagentmarketplace
Integrate LLMs into applications - APIs, prompting, fine-tuning, and context management
skill-stocktake
by shimo4228
"Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation."
hello-world
by SerendipityOneInc
A simple example skill demonstrating basic Claude Code skill structure
call-ai
by choru-k
Run a prompt against external AIs (Codex, Gemini, Claude). Low-level building block for other skills. Use for "ask codex", "ask gemini", "call AI", or when delegating prompts to external models.
ralph-loop
by addozhang
Guide OpenClaw agents to execute Ralph Wiggum loops using exec and process tools. Agent orchestrates coding agents (Codex, Claude Code, OpenCode, Goose) with proper TTY support via pty:true. Plans/builds code via PROMPT.md + AGENTS.md, SPECS and IMPLEMENTATION_PLAN.md. Includes PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions. Users request loops, agents execute using tools.
ralph-runner
by linuxlewis
Run Ralph Wiggum autonomous coding loops. Use when user asks to run ralph, start autonomous coding, execute a PRD, implement features from a task list, or wants Claude Code to work through user stories iteratively.