Updated 1w ago
by virgo777
buddyme
Lightweight agent framework with layered personality evolution, three-tier skill loading and heartbeat memory system.
68 GitHub stars (68)
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | −234 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 28 skills (28 skills found in its SKILL.md files)
- 8 forks (8 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add virgo777/buddyme
Asks which skills and agents to install. Just one: npx skills add virgo777/buddyme --skill buddyme-genimg — add -g for every project.
Claude Code
git clone https://github.com/virgo777/buddymecp -r "buddyme/skills/buddyme-genimg" ~/.claude/skills/
Copies the buddyme-genimg skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add virgo777/buddyme
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
buddyme-genimg
专业的 Agent 制图服务:BuddyMe 生图基于 GPT-Image-2.5(1K/1:1/一次一张),低中高三档质量(各扣 1/2/3 点额度),支持 ≤4 张参考图(图一/图二指示),为 Agent 工作流提供按需出图能力;图片永久直链、失败不扣额度,每日 10 点免费额度(同 IP 合计 20 点)。需 bk- 站点 Key。/ Professional image generation for AI Agents: GPT-Image-2.5 (1K/1:1/one per call), low-medium-high tiers (1/2/3 credits), ≤4 reference images (图一/图二 addressing) for on-demand imagery in Agent workflows; permanent image URLs, fai…
skills/buddyme-genimg/SKILL.md on GitHub (opens in a new tab) -
buddyme-search-content
专业的 Agent 全文聚合服务:BuddyMe 聚合搜索为 AI Agent 抓取多来源正文,BM25 词面 + 语义向量双确认精选(≤4000 字,原文直出不总结、逐段注明来源),开箱即喂 LLM 做后续推理,服务端缓存 10 分钟。免费注册即用,需 bk- 站点 Key。/ Professional full-text aggregation for AI Agents: multi-source fetch with BM25 + semantic dual-confirmation selection (≤4000 chars, original text with no summarization, per-segment citations), ready to feed LLM reasoning; 10-min server cache. Free with signu…
skills/buddyme-search-content/SKILL.md on GitHub (opens in a new tab) -
buddyme-search-list
专业的 Agent 检索基础设施:BuddyMe 普通搜索为 AI Agent 提供生产级多引擎聚合搜索——聚合 Google/Bing/Brave/Wikipedia 等主流引擎,秒级响应、垃圾结果门控、稳定 JSON 契约,供 Agent 在任务中即时检索网络信息。免费注册即用,bk- 站点 Key 鉴权调用计入使用统计。/ Professional retrieval infrastructure for AI Agents: production-grade multi-engine aggregated web search (Google/Bing/Brave/Wikipedia, second-level response, junk-gated, stable JSON contract) for Agents to fetch web info mid-task. Fr…
skills/buddyme-search-list/SKILL.md on GitHub (opens in a new tab) -
api-design
生产级 API 的 REST API 设计模式,包括资源命名、状态码、分页、过滤、错误响应、版本控制和速率限制。
buddyMe/skill_library/skills/api-design/SKILL.md on GitHub (opens in a new tab) -
article-writing
编写文章、指南、博客帖子、教程、新闻通讯(newsletter)以及其他长篇内容。这些内容具有从提供的示例或品牌指南中提取出的独特语气。当用户需要比段落更长的精美文案,且对语气一致性、结构和可信度有要求时,请使用此技能(Skill)。
buddyMe/skill_library/skills/article-writing/SKILL.md on GitHub (opens in a new tab) -
autonomous-loops
自主运行 Claude Code 循环的模式与架构 —— 从简单的顺序流水线到 RFC 驱动的多智能体 DAG 系统。
buddyMe/skill_library/skills/autonomous-loops/SKILL.md on GitHub (opens in a new tab) -
backend-patterns
后端架构模式、API 设计、数据库优化以及针对 Node.js、Express 和 Next.js API 路由的服务端最佳实践。
buddyMe/skill_library/skills/backend-patterns/SKILL.md on GitHub (opens in a new tab) -
coding-standards
适用于 TypeScript、JavaScript、React 和 Node.js 开发的通用编码标准、最佳实践和模式。
buddyMe/skill_library/skills/coding-standards/SKILL.md on GitHub (opens in a new tab) -
configure-ecc
Everything Claude Code 的交互式安装程序 —— 引导用户选择并将技能(Skills)和规则(Rules)安装到用户级或项目级目录,验证路径,并可选地优化已安装的文件。
buddyMe/skill_library/skills/configure-ecc/SKILL.md on GitHub (opens in a new tab) -
content-hash-cache-pattern
使用 SHA-256 内容哈希缓存高昂的文件处理结果 —— 与路径无关、自动失效且服务层分离。
buddyMe/skill_library/skills/content-hash-cache-pattern/SKILL.md on GitHub (opens in a new tab) -
continuous-learning
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
buddyMe/skill_library/skills/continuous-learning/SKILL.md on GitHub (opens in a new tab) -
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.
buddyMe/skill_library/skills/deployment-patterns/SKILL.md on GitHub (opens in a new tab) -
eval-harness
为 Claude Code 会话提供的正式评测框架,实现了评测驱动开发(EDD)原则
buddyMe/skill_library/skills/eval-harness/SKILL.md on GitHub (opens in a new tab) -
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
buddyMe/skill_library/skills/frontend-design/SKILL.md on GitHub (opens in a new tab) -
frontend-patterns
针对 React、Next.js、状态管理、性能优化及 UI 最佳实践的前端开发模式。
buddyMe/skill_library/skills/frontend-patterns/SKILL.md on GitHub (opens in a new tab) -
frontend-slides
从头开始创建令人惊叹、动画丰富的 HTML 演示文稿,或通过转换 PowerPoint 文件生成。当用户想要构建演示文稿、将 PPT/PPTX 转换为网页版,或为演讲/路演创建幻灯片时使用。帮助非设计师通过视觉探索而非抽象选择来发现他们的审美。
buddyMe/skill_library/skills/frontend-slides/SKILL.md on GitHub (opens in a new tab) -
iterative-retrieval
逐步优化上下文检索以解决子智能体(subagent)上下文问题的模式。
buddyMe/skill_library/skills/iterative-retrieval/SKILL.md on GitHub (opens in a new tab) -
market-research
执行市场研究(market research)、竞争分析、投资者尽职调查和行业情报,提供来源引用及面向决策的摘要。当用户需要市场规模估算、竞品对比、基金研究、技术扫描或为业务决策提供支持的研究时,请使用此技能。
buddyMe/skill_library/skills/market-research/SKILL.md on GitHub (opens in a new tab) -
markitdown-skill
OpenClaw agent skill for converting documents to Markdown. Documentation and utilities for Microsoft's MarkItDown library. Supports PDF, Word, PowerPoint, Excel, images (OCR), audio (transcription), HTML, YouTube.
buddyMe/skill_library/skills/markitdown-skill-1.0.1/SKILL.md on GitHub (opens in a new tab) -
plankton-code-quality
使用 Plankton 实现编写时代码质量强制执行 —— 通过钩子在每次文件编辑时进行自动格式化、代码检查,并由 Claude 驱动自动修复。
buddyMe/skill_library/skills/plankton-code-quality/SKILL.md on GitHub (opens in a new tab) -
project-guidelines-example
基于真实生产应用程序的项目特定技能(Skill)模板示例。
buddyMe/skill_library/skills/project-guidelines-example/SKILL.md on GitHub (opens in a new tab) -
python-patterns
构建健壮、高效且易于维护的 Python 应用程序的 Python 惯用法(Pythonic idioms)、PEP 8 标准、类型提示(Type hints)以及最佳实践。
buddyMe/skill_library/skills/python-patterns/SKILL.md on GitHub (opens in a new tab) -
python-testing
使用 pytest、TDD 方法论、测试夹具(Fixtures)、模拟(Mocking)、参数化(Parametrization)以及覆盖率要求的 Python 测试策略。
buddyMe/skill_library/skills/python-testing/SKILL.md on GitHub (opens in a new tab) -
qqmail
Manage QQ Mail (QQ邮箱) via IMAP/SMTP. Use when the user wants to read, send, search, or manage emails from their QQ mailbox. Supports reading inbox, sending emails with attachments, searching by subject/sender/date, and listing folders.
buddyMe/skill_library/skills/qqmail-1.0.0/SKILL.md on GitHub (opens in a new tab) -
search-first
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.
buddyMe/skill_library/skills/search-first/SKILL.md on GitHub (opens in a new tab) -
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
buddyMe/skill_library/skills/strategic-compact/SKILL.md on GitHub (opens in a new tab) -
verification-loop
Claude Code 会话的全方位验证系统。
buddyMe/skill_library/skills/verification-loop/SKILL.md on GitHub (opens in a new tab) -
weather-skill
用于查询国内城市实时天气,当用户询问天气相关问题时自动触发
buddyMe/skill_library/skills/weather-skill/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.