智能体
Agent 规划、多步流程与编排
ai-prompting-related-resources
vamseeachanta
'Sub-skill of ai-prompting: Related Resources.'
geo-infer-econ
ActiveInferenceInstitute
Geospatial economics and bioregional market modeling. Use when analyzing spatial economic patterns, bioregional markets, location-based pricing, call auctions, or supply-demand modeling with geographic context.
agent-usage-optimizer-usage
vamseeachanta
'Sub-skill of agent-usage-optimizer: Usage.'
langchain-2-agent-with-tools
vamseeachanta
'Sub-skill of langchain: 2. Agent with Tools.'
solo-setup
fortunto2
Auto-generate project workflow config (docs/workflow.md) from existing PRD and CLAUDE.md with zero questions. Use when user says "set up workflow", "configure TDD", "wire up dev workflow", or after running /scaffold before /plan. Do NOT use for founder setup (use /init) or project scaffolding (use /scaffold).
create-agent-skills
glittercowboy
Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
langchain-rate-limit-errors
vamseeachanta
'Sub-skill of langchain: Rate Limit Errors (+2).'
geo-infer-agent
ActiveInferenceInstitute
Multi-agent geospatial systems with Active Inference. Use when building spatial agents, implementing perception-action loops, managing agent telemetry, or coordinating multi-agent spatial exploration.
agent-usage-optimizer-step-5-work-queue-integration
vamseeachanta
"Sub-skill of agent-usage-optimizer: Step 5 \u2014 Work Queue Integration."
prompt-engineering
liyecom
提示工程技术与 Agent 设计模式
pi
knoopx
Configures pi coding agent with skills, templates, extensions, packages, and models. Use for composable development workflows, custom agents, and project-specific configurations.
self-improve
knoopx
Analyzes Pi sessions to discover repeating patterns and tool failures, then improves agent behavior through skills, templates, guardrails, and hooks.
deepagents-implementation
existential-birds
Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.
Google ADK Python Skill
mrgoonie
Remember: ADK treats agent development like traditional software engineering - use version control, write tests, and follow engineering best practices.
session-memory
humanplane
Maintains awareness across sessions. Spawns observer agent on start, loads context, notifies of evolution opportunities.
web-article-translator
zephyrwang6
翻译在线文章为中文并保存为 Markdown 格式。当用户需要翻译网页文章、博客文章时使用此技能，例如："翻译这篇文章 https://example.com/article"、"把这个 URL 的文章翻译成中文并保存"。
ai-writing-assistant
zephyrwang6
AI-powered writing assistant for social media content creation. Provides 6 structured writing methods: conversational writing, outline-based writing, completion-style writing, inspiration generation, revision optimization, and material integration. Use when users need help with: (1) Writing social media posts, articles, or content, (2) Overcoming writer's block or difficulty expressing ideas, (3) Structuring thoughts and improving writing quality, (4) Integrating multiple sources into coherent content.
youtube-feed
zephyrwang6
获取关注的 YouTube 博主/播客的最新更新。列出最近两天的新视频，包含标题、发布时间和简要描述。 触发词："获取播客更新"、"最近有什么新播客"、"YouTube 更新"、"播客更新"、"有什么新的播客"。 用于每日检查关注的 AI/科技播客是否有新内容更新。
doc-coauthoring
zephyrwang6
Guide users through a structured workflow for co-authoring documentation, articles, or long-form content. Use when user wants to write documentation, proposals, articles, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting articles, or using "co-authoring" workflow.
stock-research-executor
liangdabiao
股票投资调研执行引擎，执行8阶段投资尽调流程。接收stock-question-refiner生成的结构化调研指令，部署多智能体并行研究，生成带引用的投资尽调报告。覆盖：公司事实底座、行业周期、业务拆解、财务质量、股权治理、市场分歧、估值护城河、综合报告。当用户需要进行股票投资研究、基本面分析、投资尽调时使用此技能。
topic-agent
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。
musepi-help
MuseLinn
MusePi 产品使用帮助——回答"怎么用/是什么/出问题怎么办"类问题（TUI/CLI/桌面 GUI/看板/widget/配置/扩展/许可）。触发：任何关于 MusePi 本身的使用、功能、配置、故障问题。
semantic-compression
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.
agents-md-pro
alexander-danilenko
Create, optimize, update, and validate AGENTS.md files with maximum token efficiency. Use when the user asks to (1) create new AGENTS.md files for any repository, (2) optimize/condense existing AGENTS.md to reduce token count, (3) update/refresh AGENTS.md to sync with codebase changes, (4) validate AGENTS.md quality and completeness, or (5) improve AGENTS.md files to be more effective for AI agents. Always generates token-efficient, condensed output focused on actionable commands and patterns while maintaining model-agnostic language.