Prompts

research

by ScientiaCapital

"Market intelligence, competitive analysis, technical evaluations, and technology decisions. Use when researching companies, analyzing competitors, evaluating frameworks, or making tech stack decisions."

langgraph-agents

by ScientiaCapital

"Multi-agent systems with LangGraph - supervisor/swarm patterns, state coordination, multi-provider routing. Use when building multi-agent workflows, coordinating agents, or need cost-optimized orchestration. Uses Claude, DeepSeek, Gemini (no OpenAI)."

ljg-skill-roundtable

by lijigang

结构化圆桌讨论 - Claude Code Skill，以求真为目标的多人物辩证对话框架

graph-engineering

by Jamie-BitFlight

Teaches an agent graph engineering — both halves. Knowledge graphs (ontology design, entity/relation/event extraction, fusion, GraphRAG/memory serving; distilled and translated from Southeast University's graduate Knowledge Graph course, npubird/KnowledgeGraphCourse, 4.4K stars) and task graphs (agent orchestration — parallel fan-out, verifier separation, the stop rule, human gates). Use when asked to build a knowledge graph, extract entities/relations from text, design an ontology, dedupe/merge entities, add graph memory or GraphRAG to an agent, orchestrate multi-agent workflows as a graph, or LEARN graph engineering — in teaching mode the agent explains each stage with worked examples and generates visual diagram artifacts.

claude-mem

by enuno

Persistent memory compression system for Claude Code enabling context preservation across sessions with automatic observations, semantic search, and privacy controls

Umbraco Extension Template

by umbraco

kubecon-llm-k8s

by rebyteai-template

Slidev presentation about taming dependency chaos for LLM in Kubernetes.

prompt-architect

by samhvw8

"Create and enhance prompts, system instructions, and principle files. Capabilities: transform verbose prompts, add patterns/heuristics, optimize token usage, structure CLAUDE.md principles, improve agent/persona definitions, apply prompt engineering techniques (CoT, few-shot, ReAct). Actions: create, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, system prompt, CLAUDE.md, principle files, instruction optimization, agent prompt, persona prompt, token efficiency, prompt structure, workflow prompts, rules, constraints, few-shot, chain-of-thought, soul, tensions, dialectic. Use when: creating new prompts, enhancing principle files, improving system instructions, optimizing CLAUDE.md, restructuring verbose prompts, adding patterns to workflows, defining agent behaviors."

custom-local-skills-guidance

by EdanStarfire

Guide to the 6 custom injection points available for extending dev-setup workflows with project-specific behavior.

claude-prompting

by duyet

Prompt engineering guidance for Claude (Anthropic) model. Use when crafting prompts for Claude to leverage XML-style tags, long-context capabilities, extended thinking, and strong instruction following.

planning

by samhvw8

"Universal planning for technical and non-technical projects. Domains: software implementation, business, personal, creative, academic, events. Capabilities: feature planning, system architecture, goal setting, milestone planning, requirement breakdown, trade-off analysis, resource allocation, risk assessment. Actions: plan, architect, design, evaluate, breakdown, structure projects. Keywords: implementation plan, technical design, architecture, roadmap, project plan, strategy, goal setting, milestones, timeline, action plan, SMART goals, sprint planning, task breakdown, OKRs. Use when: planning features, designing architecture, creating roadmaps, setting goals, organizing projects, breaking down requirements."

claude-ecosystem

by samhvw8

"Claude Code ecosystem expertise. Modules: CLI tool (setup, slash commands, MCP servers, hooks, plugins, CI/CD), extensibility (agents, skills, output styles creation), CLAUDE.md (project instructions, optimization). Actions: configure, troubleshoot, create, deploy, integrate, optimize Claude Code. Keywords: Claude Code, Anthropic, CLI tool, slash command, MCP server, Agent Skill, hook, plugin, CI/CD, enterprise, CLAUDE.md, agentic coding, agent, skill, output-style, SKILL.md, subagent, Task tool, project instructions, token optimization. Use when: learning Claude Code features, configuring settings, creating skills/agents/hooks, setting up MCP servers, troubleshooting issues, CI/CD integration, initializing or optimizing CLAUDE.md files."

grok-prompting

by duyet

Prompt engineering guidance for Grok (xAI) model. Use when crafting prompts for Grok to leverage its conversational style, real-time knowledge access, and less-constrained responses.

ask-many-models

by HartreeWorks

This skill should be used when the user asks to "ask many models", "query multiple AI models", "get opinions from different AIs", "compare AI responses", "ask GPT and Gemini", "ask several models", or mentions wanting to send the same prompt to multiple AI models and synthesise the results.

orchestrating-swarms

by Jamie-BitFlight

Master multi-agent orchestration using Claude Code's swarm system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns. This facade loads specialist skills for primitives, spawning, operations, and patterns.

add-new-feature

by Jamie-BitFlight

SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feature, or convert an idea into an executable SAM plan.

certifications-training

by pluginagentmarketplace

Professional certifications, CTF competitions, and training resources for AI security practitioners

testing-methodologies

by pluginagentmarketplace

Structured approaches for AI security testing including threat modeling, penetration testing, and red team operations

loop-engineering

by chadqiu

"通用 loop engineering（MEA 管理-执行-审计循环）。硬判据——凡满足任一条必须用本循环、禁止主会话直接动手：① 需要修改任何文件/代码/配置/状态（修复、实现、重构）；② 排查/诊断/根因分析/「为什么报错」类请求且证据链≥3步（查日志→读代码→比对数据的多跳验证）；③ 结论需要独立验证（影响决策的根因判断、数据链路问题）。systematic-debugging 等调试方法论不废弃，但由 lh-executor 子代理在轮内使用，主会话不得直接开诊断流程。触发词：/loop、排查、诊断、根因、为什么报错、报错分析、bug修复、修一下、debug、loop engineering、MEA循环、审计循环。任务状态外置 .loop/ 目录，跨会话可恢复。MEA manage-execute-audit loop for Claude Code: long-running tasks as independently-audited state transitions, with lh-executor/lh-auditor subagents."

setup-matt-pocock-skills

by lirtual

"Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills."

system-prompt-engineering

by Eitanvinokur12345

"Customizing AI behavior, improving AI performance, replicating specific AI functionalities."

prompt-engineering-uncertainty

by Eitanvinokur12345

"Improving reliability and trustworthiness of AI outputs."

orchestrate

by acedergren

Coordinate parallel agent teams to execute multi-task implementation plans. Use when running phase tasks from the task plan, parallelizing independent implementation work, or executing custom plan files. Supports interactive (in-session TeamCreate agents) and headless (claude -p fire-and-forget processes) execution modes with task ledger tracking, heartbeat monitoring, budget control, and wave-based quality gates.

ce-agent-native-audit

by KingInYellows

Run comprehensive agent-native architecture review with scored principles