Prompts
Prompt engineering and templates
mem-record
by zephyrwang6
AI个人记忆系统的记忆记录功能。自动从对话中提炼关键信息并记录到相应层级。使用场景：(1) 用户说"记录到记忆系统"、"记住这个"、"把这次对话记下来"时；(2) 检测到重要事件、决策、偏好表达时；(3) 用户完成重要任务或做出决策时。该skill会自动判断应该记录到L1情境层、L2行为层、L3认知层，还是建议更新L4核心层。
content-topic-generator
by zephyrwang6
从文章、推文、社交媒体内容生成多角度选题，包括推文选题（140字完整内容）和公众号选题（含详细大纲）。支持延伸、反驳、扩充、热点结合四种策略。当用户需要基于现有内容创作新选题、分析文章生成衍生内容、或进行内容再创作时使用。适用场景：(1) 分析推文/文章并生成选题，(2) 创建公众号/社交媒体内容策划，(3) 将长文拆解为多个传播点，(4) 内容营销和话题策划。
topic-agent
by zephyrwang6
选题系统主控Agent。协调热点采集、选题生成、选题审核三个环节，支持迭代直到产出合格选题。触发方式：(1)"开始今日选题"启动完整流程 (2)"今日AI热点"只采集热点不生成选题 (3)"我有一个选题"进入单个选题分析 (4)"推荐一些好的选题"直接输出推荐。输出保存到Obsidian选题库。
git-safety-hooks
by helderberto
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations or add git safety guardrails.
save-session
by blacktop
Save AI agent session information for later resumption. Use when: (1) Finishing a work session and want to save progress (2) User says "save session", "remember this session", or "save your session ID" (3) Before ending a long coding/debugging session (4) When user wants to be able to resume this conversation later Supports Claude, Codex, Gemini, Copilot, Cursor, and other AI agents.
obsidian
by Delphine-L
Integration with Obsidian vault for managing notes, tasks, and knowledge when working with Claude. Supports adding notes, creating tasks, and organizing project documentation.
mcp-server-orchestrator
by organvm-iv-taxis
Configure, deploy, and troubleshoot Model Context Protocol (MCP) servers for AI agent workflows. Use when setting up MCP servers, debugging connection issues, managing multi-server configurations, integrating with Claude Desktop/Code/Cowork, or designing custom tool servers. Triggers on MCP configuration, tool server development, Claude integration issues, or agent infrastructure setup.
narratological-algorithms
by organvm-iv-taxis
Distill artist/theorist narrative principles into formal, implementable algorithmic frameworks. Use when asked to extract, formalize, or systematize narrative techniques from any storytelling source—filmmakers, writers, theorists, game designers, showrunners. Triggers on requests involving narrative principle extraction, story structure analysis, craft methodology formalization, or creating implementable storytelling protocols.
semantic-compression
by MuseLinn
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making documentation token-efficient for LLM input; or rewriting text in compressed notation.
lsp-manager
by bahayonghang
Automatically detect programming languages, configure Language Server Protocol (LSP) servers, and troubleshoot LSP integration issues for Claude Code. Use when users request to set up LSP, configure code intelligence, add language support, troubleshoot LSP errors, or when working with projects that need real-time code diagnostics and navigation.
claude-collaboration
by Delphine-L
Best practices for using Claude Code in team environments. Covers skill management, knowledge capture, version control, and collaborative workflows.
tool-prompt-optimization
by MuseLinn
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool prompt vs what stays in code. Use when auditing, trimming, writing, or reviewing tool prompts, deciding what schema field descriptions already cover, or testing schema-vs-prompt overlap before deleting prompt lines.
orchestrate
by blacktop
Lead-developer workflow for orchestrating sub-tasks with Claude Code CLI (Opus 4.5/Sonnet) using structured handoffs, review loops, and role specialization. Use when Codex should act as lead/architect, plan architecture and file structure, break work into atomic tasks, delegate bulk boilerplate/docs to Claude, and verify/iterate on Claude output.
question-refiner
by liangdabiao
将原始研究问题细化为结构化的深度研究任务。通过提问澄清需求，生成符合 OpenAI/Google Deep Research 标准的结构化提示词，完全替代 ChatGPT 的问题细化功能。当用户提出研究问题、需要帮助定义研究范围、或想要生成结构化研究提示词时使用此技能。
continuous-learning-agent
by organvm-iv-taxis
Self-improvement patterns for AI agents to learn from feedback, errors, and successful patterns across sessions
handoff
by blacktop
Generate optimized handoff prompts for delegating tasks to LLM agents. Use when needing to hand off work to another agent (GPT-5.2/Codex, Claude Opus 4.5/Sonnet 4, or Gemini 3 Pro/Flash), whether for a sub-task/parallel task within the same project or a fresh start handoff to a new agent context. Triggers on requests like "create a handoff prompt", "delegate this task to another agent", "hand this off", or "prepare context for another agent".
mlops-engineer
by olehsvyrydov
Senior MLOps Engineer with 8+ years ML systems experience. Use when integrating LLM APIs (Gemini, OpenAI, Groq), building AI pipelines, managing prompts, setting up model serving, implementing AI cost optimization, or building training data pipelines.
claude-skill-management
by Delphine-L
Expert guide for managing Claude Code global skills and commands. Use when creating new skills, symlinking to projects, updating existing skills, or organizing the centralized skill repository.
securities-analysis-cn
by kingqiu
自动分析A股、港股、ETF基金，生成专业PDF深度分析报告（含AI买卖建议和互联网研究）。 支持单只分析和多只对比：输入证券代码（510300、600519、00700.HK）或名称（贵州茅台、腾讯控股）， 自动识别类型。多只输入时自动生成对比分析报告（含综合评分+说人话解读）。 使用场景：当用户要求"分析某只股票/基金"、"对比XX和YY"、"帮我看看XX的投资价值"时触发。 插件化架构：数据源、AI模型、搜索引擎均可通过 .env 配置切换。
code-fragment-extractor
by evanfang0054
仔细彻底阅读探索用户提供的代码目录/文件，分析拆解出对应的代码片段以供参考，颗粒度细到功能级别，只做片段提取不改变代码内容和页面布局结构，提取到./fragment-extractor目录下，按照指定模板格式生成代码片段模板文件，确保功能完整性和代码片段的实际性。
review-skill
by corygabrielsen
Review a skill document using specialized reviewers. Each reviewer finds specific issue types.
hr-service-delivery
by groeimetai
This skill should be used when the user asks to "HR case", "employee center", "onboarding", "offboarding", "HR service", "lifecycle event", "HR catalog", or any ServiceNow HR Service Delivery development.
chronicle
by PrakharMNNIT
"Personal journal intelligence that transforms raw, unorganized thoughts into structured diary entries with psychological analysis. Use when the user provides journal entries, diary text, stream-of-consciousness writing, voice memo transcriptions, or asks to process daily thoughts into a structured format. Produces narrative entries, gratitude extraction, multi-level psychological analysis (surface/medium/clinical), health pattern flags, therapeutic micro-actions, and bridge-to-tomorrow planning. Trigger phrases: 'journal entry', 'diary entry', 'process my thoughts', 'Chronicle', 'daily reflection', 'write up my day'."
document-management
by groeimetai
This skill should be used when the user asks to "attachment", "document", "file upload", "document template", "PDF generation", "document workflow", or any ServiceNow Document Management development.