Prompts
Prompt engineering and templates
claude-code-plugin
by miles990
Claude Code Plugin 開發、發布、安裝、更新與 Marketplace 管理完整指南
tmux-agent
by ssiumha
Automates tmux pane/window orchestration for Claude instances. Use when running dev servers in separate panes, monitoring logs across panes, checking process status, sending commands to other panes, or when background tasks need persistent terminal output instead of run_in_background.
agent-creator
by ssiumha
Creates and manages custom Claude Code sub-agents. Use when automating workflows as dedicated agents, delegating recurring tasks, or modifying .claude/agents/ files.
init-config
by FradSer
Generate $HOME/.claude/CLAUDE.md with AI-driven environment detection and advanced configuration options
template-skill
by guanyang
Replace with description of the skill and when Claude should use it.
technical-articles
by EpicenterHQ
Writing technical articles and blog posts. Use when creating articles in docs/articles/ or blog content explaining patterns, techniques, or lessons learned.
context-degradation
by guanyang
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
advanced-evaluation
by guanyang
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
community-building
by dmend3z
This skill helps you build and manage a thriving online community. Use it when you need to define your community's purpose, create engaging content, foster authentic communication, and empower brand advocates.
gaming-metaverse-advertising
by dmend3z
This skill enables Claude to act as a specialist in gaming and metaverse advertising. It should be used when a user needs to create, manage, or optimize advertising campaigns within gaming environments or metaverse platforms. It is triggered by keywords like 'gaming ads', 'metaverse marketing', 'in-game advertising', 'Roblox', or 'virtual worlds'.
ln-111-root-docs-creator
by levnikolaevich
Creates 4 root documentation files (CLAUDE.md, docs/README.md, documentation_standards.md, principles.md). L3 Worker invoked by ln-110-project-docs-coordinator.
implement-plan
by mhylle
Orchestrate the execution of complete implementation plans, delegating each phase to implement-phase skill. This skill manages the full plan lifecycle including phase sequencing, user confirmation between phases, and overall progress tracking. Triggers on "implement the plan", "execute the implementation plan", or when given a path to a plan file.
prompt-engineering
by vamseeachanta
Comprehensive prompting techniques including chain-of-thought, few-shot, zero-shot, system prompts, persona design, and evaluation patterns
dspy
by vamseeachanta
Compile prompts into self-improving pipelines with signatures, modules, optimizers, and programmatic prompt engineering
langchain
by vamseeachanta
Build production-ready LLM applications with chains, agents, memory, tools, and RAG pipelines using the LangChain framework
pandasai
by vamseeachanta
Conversational data analysis using natural language queries on DataFrames. Chat with your data using LLMs to generate insights, create visualizations, and explain code.
agenta
by vamseeachanta
LLM prompt management and evaluation platform. Version prompts, run A/B tests, evaluate with metrics, and deploy with confidence using Agenta's self-hosted solution.
resolver-query
by mycelium-hq
'Use when an operator asks which rule or policy governs a question — pricing exceptions, deploys, refunds, hiring — or wants to look up the matching rule in Meta/RESOLVER.md without reading the whole index by hand. Triggers: /resolver-query <question>, "which rule applies", "what''s our policy on X", "does a rule cover this". Not for writing or editing rules (read-only) and not for rebuilding RESOLVER.md (use resolver-build.py).'
health-context
by mycelium-hq
'Use when a host skill that benefits from biometric context runs: daily-journal (/journal), coaching, advisory-panel (/panel), patterns, or insights (/weekly, /monthly). Also use when the user asks how HRV, sleep, recovery, resting heart rate, steps, or workouts relate to a journal entry, coaching window, decision, pattern, or weekly review. Companion layer, never standalone. Setup: health-setup. Data import: ingest-health. Sync diagnostics: health-doctor.'
boss
by echoVic
BMAD 全自动研发流水线编排器。编排 9 个专业 Agent（PM、架构师、UI 设计师、Tech Lead、Scrum Master、开发者、QA、DevOps）从需求到部署一气呵成。 Triggers: 'boss mode', '/boss', '全自动开发', '从需求到部署', '帮我做一个', 'build this', 'ship it', '全流程', '自动化开发', '一键开发', 'start a project', 'new feature' Does NOT trigger: - 单文件修改或简单 bug 修复（直接编辑即可） - 纯代码阅读或解释（使用 read 工具） - 已有 pipeline 正在运行时的重复启动 Output: 完整项目代码 + PRD/架构/UI/测试/部署文档，写入 .boss/<feature>/ 目录
prompt-engineering
by cosmix
Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples. Covers instruction design, prompt security, chain-of-thought reasoning, and in-context learning for orchestrated AI agents. Trigger keywords: prompt, LLM, GPT, Claude, AI, system prompt, user prompt, few-shot, chain of thought, CoT, in-context learning, prompt template, prompt injection, jailbreak prevention, agent signal, agent instruction, agent orchestration, reasoning, instruction tuning.
prompt-engineering
by lv416e
"Use when designing, testing, or deploying LLM prompts for applications - systematic prompt design methodology (pattern selection, structured output, evaluation, versioning) ensuring every prompt is tested against ground truth before production LLMプロンプトの設計、テスト、デプロイ時に使用 - 体系的なプロンプト設計手法（パターン選択、構造化出力、評価、バージョン管理）により、すべてのプロンプトが本番前にグランドトゥルースに対してテスト済みであることを保証"
customaize-agent:thought-based-reasoning
by NeoLabHQ
Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive guide to Chain-of-Thought and related prompting techniques (Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, Reflexion) with templates, decision matrices, and research-backed patterns
customaize-agent:prompt-engineering
by NeoLabHQ
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.