MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
ZhiYuan Agent expert package lifecycle manager for the pi engine.
Install Zhiyuan Expert Manager
$ npx skills add rongxinzy/RongxinAI --skill zhiyuan-expert-manager -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install rongxinzy/RongxinAI zhiyuan-expert-manager --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/SKILLs/zhiyuan-expert-manager .claude/skills/zhiyuan-expert-manager && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "zhiyuan-expert-manager" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/SKILLs/zhiyuan-expert-manager into .claude/skills/zhiyuan-expert-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhiyuan-expert-manager", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/rongxinzy/RongxinAI/tree/main/SKILLs/zhiyuan-expert-managerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add rongxinzy/RongxinAI --skill zhiyuan-expert-manager -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install rongxinzy/RongxinAI zhiyuan-expert-manager --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .agents/skills && cp -r skills-src/SKILLs/zhiyuan-expert-manager .agents/skills/zhiyuan-expert-manager && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "zhiyuan-expert-manager" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/SKILLs/zhiyuan-expert-manager into .agents/skills/zhiyuan-expert-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhiyuan-expert-manager", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rongxinzy/RongxinAI --skill zhiyuan-expert-manager -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install rongxinzy/RongxinAI zhiyuan-expert-manager --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/SKILLs/zhiyuan-expert-manager .cursor/skills/zhiyuan-expert-manager && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "zhiyuan-expert-manager" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/SKILLs/zhiyuan-expert-manager into .cursor/skills/zhiyuan-expert-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhiyuan-expert-manager", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/rongxinzy/RongxinAI.git --path SKILLs/zhiyuan-expert-manager--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add rongxinzy/RongxinAI --skill zhiyuan-expert-manager -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install rongxinzy/RongxinAI zhiyuan-expert-manager --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/SKILLs/zhiyuan-expert-manager .gemini/skills/zhiyuan-expert-manager && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "zhiyuan-expert-manager" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/SKILLs/zhiyuan-expert-manager into .gemini/skills/zhiyuan-expert-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhiyuan-expert-manager", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install rongxinzy/RongxinAI zhiyuan-expert-managerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add rongxinzy/RongxinAI --skill zhiyuan-expert-manager -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .github/skills && cp -r skills-src/SKILLs/zhiyuan-expert-manager .github/skills/zhiyuan-expert-manager && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "zhiyuan-expert-manager" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/SKILLs/zhiyuan-expert-manager into .github/skills/zhiyuan-expert-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhiyuan-expert-manager", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rongxinzy/RongxinAI --skill zhiyuan-expert-manager -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install rongxinzy/RongxinAI zhiyuan-expert-manager --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/SKILLs/zhiyuan-expert-manager .opencode/skills/zhiyuan-expert-manager && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "zhiyuan-expert-manager" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/SKILLs/zhiyuan-expert-manager into .opencode/skills/zhiyuan-expert-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhiyuan-expert-manager", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
zhiyuan-expert-manager- GitHub stars
- 154
- Token cost
- ~1.9k tokens
- SKILL.md length
- 544 words
- Files
- 56 (incl. scripts, references)
- Skills in repo
- 94
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
ZhiYuan Agent expert package lifecycle manager for the pi engine.
- Works in 2 steps: 专家类型（expertType）：Agent 还是 Team？ → 专家领域：擅长什么？
- Words: 创建专家、创建专家团、导入专家、 生成专家包、expert manager、new expert
- SKILL.md covers 支持的专家类型, 关键展示字段对应关系, 一、工作流程 and 二、目录初始化, plus 9 more sections
- Calls node
What it does
Zhiyuan Expert Manager is an agent skill from rongxinzy/RongxinAI. ZhiYuan Agent expert package lifecycle manager for the pi engine. Helps users create, validate, and register single agents or multi-agent teams as ZhiYuan Agent Agent entries. Trigger words: 创建专家、创建专家团、导入专家、 生成专家包、expert manager、new expert.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 64 other files, including scripts and reference files (for example `presets/cad-engineering-expert/UPSTREAM.md`, `presets/cad-engineering-expert/agents/cad-engineering-expert.md` and `presets/cad-engineering-expert/plugin.json`).
It sits in Agent Workflows. The repository describes itself as: An all-in-one local AI Agent workspace with a fully self-developed stack. The licence is AGPL-3.0.
When your agent uses it
- Words: 创建专家、创建专家团、导入专家、 生成专家包、expert manager、new expert
Example prompts
- “/zhiyuan-expert-manager”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- 专家类型（expertType）：Agent 还是 Team？
- 专家领域：擅长什么？
What it can do on your machine
Read from SKILL.md and the folder at commit 31b424a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
node
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Zhiyuan Expert Manager loads about 1.9k tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 544 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from rongxinzy/RongxinAI at commit 31b424a, republished under its AGPL-3.0 licence (© rongxinzy). 544 words, ~1,894 tokens.
Download SKILL.mdSave it as
.claude/skills/zhiyuan-expert-manager/SKILL.md (or your agent's skills folder). This skill also uses 55 other files; get the full folder from GitHub.- name
- zhiyuan-expert-manager
- description
- ZhiYuan Agent expert package lifecycle manager for the pi engine. Helps users create, validate, and register single agents or multi-agent teams as ZhiYuan Agent Agent entries. Trigger words: 创建专家、创建专家团、导入专家、 生成专家包、expert manager、new expert.
ZhiYuan Agent 专家管理器
⚠️ 执行前必读：当需要使用本 skill 时，你必须先从头到尾完整阅读本 SKILL.md 全文并严格遵守（包括所有规则、流程、References 列表），然后再开始执行任务。禁止跳读或仅凭部分段落就开始行动。
你是 ZhiYuan Agent 专家管理器，帮助用户按照 ZhiYuan Agent 专家开发规范创建和维护完整的、可直接被 pi 内核消费的专家文件包。
ZhiYuan Agent 使用 pi 作为 Work、Chat、Channel 与 Cron 的唯一执行内核；频道 sidecar 仅负责传输。因此专家包格式与 other applications 不兼容：
- 不使用
TeamCreate/SendMessage协议 - Team 型专家团通过 pi 的
subagenttool 调度成员 - 专家注册后直接写入 ZhiYuan Agent 的 SQLite
agents表
支持的专家类型
- Agent 型（
expertType: "agent"）：单个 AI 专家 - Team 型（
expertType: "team"）：多角色协作团队，由主理人通过subagent调度
关键展示字段对应关系
| 展示 | 对应字段 | 变更规则 |
|---|---|---|
| 名字（职业） | profession（{en, zh}） | 卡片标题，应体现专家职业定位 |
| 花名 | displayName（{en, zh}） | 可根据用户要求自由修改 |
| 类型 | expertType | 单角色 = "agent"，多角色协作 = "team" |
| 行业分类 | categoryId | 必须从下方 12 个分类中选择，并向用户说明理由 |
| 能力介绍 | displayDescription（{en, zh}） | 中文 40-50 字，突出核心能力 |
| 擅长领域 | tags（{en, zh}[]，固定 3 个） | 已满 3 个时须提示替换或删除，禁止继续新增 |
| 试试这样问我 | quickPrompts（{en, zh}[]，固定 3 个） | 第一条同时作为 defaultInitPrompt |
一、工作流程
整体流程：
1. 收集信息（交互 or 资料转化）
2. 初始化目录 → node scripts/init_expert.js
3. AI 生成文件内容
4. 校验 → node scripts/validate_expert.js
5. 注册 → node scripts/register_expert.js
6. 提示用户在 Agent 列表中使用场景 A：交互模式
专家目录（固定）：%APPDATA%/ZhiYuanAgent/expert-packages/（Windows）或对应平台的用户数据目录。禁止生成到其他目录。
必须明确的信息：
- 专家类型（expertType）：Agent 还是 Team？
- 专家领域：擅长什么？
Agent 型还需要：
- 名字（中英文）、职业头衔（中英文）
- 详细能力描述（中英文，中文 40-50 字）
- 首次对话问候语（中英文）
- 行业分类（见下方列表）
- 擅长领域标签（固定 3 个，中英文）
- 推荐提示词（3 个，中英文，第一条同时作为 defaultInitPrompt）
- 是否需要附带 Skill
Team 型还需要：
- 团队名称（中英文）、团队职业头衔（中英文，须与团队名称一致）
- 主理人名字、职责
- 每个团员的名字、职业头衔、职责
- 团队 SOP 工作流程
- 首次对话问候语、行业分类、标签、推荐提示词
场景 B：资料转化模式
当用户提供文件路径或粘贴内容时：
- 读取分析 — 从资料中提取角色定义、核心能力、SOP、输出规范、约束、脚本、参考资料、角色分工
- 推断 expertType 和 categoryId — 按规则判断，向用户说明理由
- 确认补全 — 向用户确认推断结果，补全展示信息
- 生成 — 执行初始化 + 文件生成流程
场景 C：修改已有专家
- 在
%LOCALAPPDATA%/ZhiYuan Agent/expert-packages/下找到目标专家目录 - 读取
plugin.json和agents/*.md了解现有内容 - 仅修改用户要求变更的部分
- 执行
validate_expert.js+register_expert.js
严禁修改以下标识字段：
plugin.json中的name字段plugin.json中的agentName字段- 专家目录名
agents/目录下的.md文件名- 如需改名，必须重新创建专家
二、目录初始化
node scripts/init_expert.js <expert-name> --type agent|team生成的模板文件带 [TODO] 占位符，由 AI 填充实际内容。
三、生成文件内容
参考：
@references/plugin-json-spec.md— plugin.json 字段规范和模板@references/agent-md-spec.md— Agent MD frontmatter 和正文结构@references/team-spec.md— Team 型协作铁律、成员命名、SOP 编排
⚠️ 关键：命令式 > 描述式。 Agent MD 正文必须写成行动指令（other applications 风格），不能写成简历（CV 风格）。
- ✅ "你是文案创作专家，你必须遵循标准工作流完成所有任务。"
- ✅ "## 工作流路由（CRITICAL — 收到请求时首先判断）"
- ✅ "## 严禁行为" + ❌ 标记
- ✅ "## 当你收到请求时" → 1、2、3 具体行动步骤
- ❌ 避免 "精通..." "擅长..." 等被动描述
四、校验
node scripts/validate_expert.js <path/to/expert-dir>五、注册
node scripts/register_expert.js <path/to/expert-dir>注册脚本会：
- 再次校验关键字段
- 将专家写入 SQLite
agents表 - 把
plugin.skills复制到%APPDATA%/ZhiYuanAgent/SKILLs/ - 写入
expert-packages/registry.json
内置预设与用户包：两条生命线
- 内置预设（仓库内
SKILLs/zhiyuan-expert-manager/presets/）：与普通技能一样文件即真源——直接修改预设文件即可生效，无需注册；下次会话读取磁盘快照。CI 会以 strict 模式校验全部内置预设。 - 用户导入包：走本节的 init → validate → register 流程，写入
agents表与registry.json。
校验硬门禁（validate_expert.js）
displayDescription.zh长度必须为 40-50 字- 主文件（单 Agent 主文件、拥有 Skill 的 Team 主理人）必须包含完整「Skill 使用协议（CRITICAL）」段（五项语义）；Team 普通成员豁免
- 禁止引用
production_loop/commit_plan/update_plan_item/skip_workflow（这些工具已移除）；按任务需要使用简短计划或检查清单 - 最终用户验收归 Workbench 所有。专家 Prompt 不得引用
work_acceptance，也不得使用模型发起的问题作为最终验收门禁。 - 半角破折号（
CRITICAL -）为格式问题：内置预设 strict 模式报错，用户包仅警告
六、行业分类（categoryId）
判定优先级：
- 专家的 主要输出物 属于哪个领域
- 专家的 服务对象 是谁
- 跨领域时选择 最核心 的一个
| categoryId | 分类名称 | 适用场景举例 |
|---|---|---|
| 01-ProductDesign | 产品设计 | UI/UX 设计、产品规划、原型设计、交互设计 |
| 02-Engineering | 技术工程 | 编程开发、架构设计、DevOps、技术选型 |
| 03-GameSpatial | 游戏空间 | 游戏开发、3D 建模、虚拟现实、游戏设计 |
| 04-DataAI | 数据智能 | 数据分析、机器学习、大模型应用、BI |
| 05-MarketingGrowth | 营销增长 | 品牌营销、用户增长、广告投放、SEO |
| 06-ContentCreative | 内容创作 | 文案写作、视频脚本、创意策划、翻译 |
| 07-SalesCommerce | 销售商务 | 销售策略、商务谈判、客户管理、电商 |
| 08-FinanceInvestment | 金融投资 | 投资分析、财务管理、风控、量化交易 |
| 09-OperationsHR | 运营人力 | 项目运营、人力资源、组织管理、培训 |
| 10-ProjectQuality | 项目质量 | 项目管理、质量保障、测试、流程优化 |
| 11-SecurityCompliance | 法务安全 | 信息安全、合规审查、法务咨询、隐私保护 |
| 12-IndustryConsultant | 行业顾问 | 跨行业咨询、战略规划、不属于以上明确分类的 |
Show full SKILL.md (194 more words)Show less
七、资料转化策略
| 资料中的内容 | 转化为 | 放在哪里 |
|---|---|---|
| 角色描述、专家人设 | Agent MD 的角色定义和核心能力 | agents/{name}.md |
| 工作流程、操作步骤 | Agent MD 的工作流程章节 | agents/{name}.md |
| 输出格式要求 | Agent MD 的输出规范章节 | agents/{name}.md |
| API 文档、字段定义 | SKILL.md + references/ | skills/{name}/ |
| 可执行脚本代码 | scripts/ | skills/{name}/scripts/ |
| 多角色分工描述 | Team 型主理人 + 各团员 MD | agents/ 多个 MD |
| SOP/阶段性流程 | 主理人 MD 的 SOP 章节 | agents/{team}-team-lead.md |
| 示例对话 | quickPrompts + defaultInitPrompt | plugin.json |
八、关键规则（铁律）
- name 字段 kebab-case：如
my-expert - agentName = MD 文件名：如
design-expert→agents/design-expert.md - agents 字段是路径数组：如
["./agents/my-expert.md"] - tags 固定且只能 3 个、quickPrompts 固定 3 个：新增前必须检查数量，超过 3 个必须提示用户替换或删除，第一条 quickPrompt = defaultInitPrompt
- displayDescription 中文 40-50 字
- Agent MD frontmatter 中不声明 tools 字段
- Team 型主理人文件名必须加团队前缀：如
trading-team-lead.md - Team 型 members 数组含主理人（role=lead），teamInfo.memberAgents 不含主理人
- Team 型 profession 须与 displayName 一致
- 同名专家已存在时必须重新校验 + 注册
- 批量创建必须遵循标准流程：每个专家完整串行经过
init → validate → register
九、Team 型协作规范（pi 版）
ZhiYuan Agent 的 pi 内核没有 TeamCreate / SendMessage，Team 型专家团通过 subagent tool 实现。
主理人 prompt 中必须包含：
- 可用成员列表：Agent ID、名字、职责
- 调度方式：调用
subagent工具，参数name/task/mode - 标准 SOP：Phase 编排
- 铁律：
- 禁止跳过
subagent工具，自己写出成员产出 - 禁止成员互相直连通信，所有信息必须经主理人中转
- 每完成一个 Phase 向用户简要通报进度
- 禁止跳过
成员 prompt 中必须包含：
- 角色定义
- 擅长领域
- 分析框架/工作流程
- 输出格式要求
- 结果返回给主理人（pi subagent 的 tool result 会自动返回）
十、收尾提醒
生成并注册完毕后告知用户：
- ✅ 专家已注册到 ZhiYuan Agent，可在 Agent 列表中找到
- 📦 如需分享，可打包目录：
node scripts/package_expert.js <expert-dir> - 📋 请核对内容是否准确
References
references/plugin-json-spec.md— plugin.json 完整字段规范和模板references/agent-md-spec.md— Agent MD 结构模板references/team-spec.md— Team 型协作规范
© rongxinzy, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 55 other files (scripts, references) in SKILLs/zhiyuan-expert-manager of rongxinzy/RongxinAI.
- SKILL.md
- presets/cad-engineering-expert/UPSTREAM.md
- presets/cad-engineering-expert/agents/cad-engineering-expert.md
- presets/cad-engineering-expert/plugin.json
- presets/cad-engineering-expert/skills
- presets/content-writer/agents/content-writer.md
- presets/content-writer/plugin.json
- presets/content-writer/skills
- presets/daily-report-expert/agents/daily-report-expert.md
- presets/daily-report-expert/plugin.json
- presets/data-analyst/agents/data-analyst.md
- presets/data-analyst/plugin.json
- … and 44 more
Open the folder on GitHubat commit 31b424a
Compare with similar skills
Zhiyuan Expert Manager next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Zhiyuan Expert Manager this skillrongxinzy/RongxinAI | 154 | — | ~1.9k | Automated safety check: Pass | AGPL-3.0 | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 36 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 796 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
- Official
Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
- Official
Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
More from rongxinzy/RongxinAI
All 94 skills in this repoSaaS Metrics Coach
rongxinzy/RongxinAI
SaaS financial health advisor. An agent skill from rongxinzy/RongxinAI.
Churn Prevention
rongxinzy/RongxinAI
Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences.
Presentation Studio
rongxinzy/RongxinAI
The only skill for creating a new PowerPoint deck. An agent skill from rongxinzy/RongxinAI.
Ziwei Doushu
rongxinzy/RongxinAI
Professional Ziwei Doushu consultation skill with an offline calculation engine.
Lark Mail
rongxinzy/RongxinAI
飞书邮箱：Use when user mentions 起草邮件、写邮件、草稿、发送/回复/转发邮件、查阅邮件、看邮件、搜索邮件、邮件文件夹、邮件标签、邮件联系人、监听新邮件、邮件收信规则等；use for mail/email intent only.
Cantian Bazi
rongxinzy/RongxinAI
以命理场景为主的八字排盘、黄历查询与大运/流年/流月/流日/流时区间查询技能。用于用户请求“算八字”“四柱排盘”“阳历/农历转八字”“查黄历/宜忌”“查未来10年流年”“查下个月流日/流时”等场景；关键词包括：八字、四柱、命理、大运、流年、流月、流日、流时、时辰、阳历转八字、农历转八字、黄历、宜忌、干支日期。真太阳时换算属于辅助能力，仅在需要校时定盘时使用。
Related
Categories
Questions about Zhiyuan Expert Manager
What does Zhiyuan Expert Manager do?
ZhiYuan Agent expert package lifecycle manager for the pi engine. Zhiyuan Expert Manager is an agent skill from rongxinzy/RongxinAI. ZhiYuan Agent expert package lifecycle manager for the pi engine.
When should I use Zhiyuan Expert Manager?
Zhiyuan Expert Manager fits situations like: words: 创建专家、创建专家团、导入专家、 生成专家包、expert manager、new expert.
How do I install Zhiyuan Expert Manager in Claude Code?
Run `npx skills add rongxinzy/RongxinAI --skill zhiyuan-expert-manager -a claude-code`. Or copy the skill folder (SKILLs/zhiyuan-expert-manager in rongxinzy/RongxinAI) into .claude/skills/zhiyuan-expert-manager in your project. Claude Code loads it when a task matches its description.
How do I install Zhiyuan Expert Manager in Codex?
Run `npx skills add rongxinzy/RongxinAI --skill zhiyuan-expert-manager -a codex`. Or copy the skill folder (SKILLs/zhiyuan-expert-manager in rongxinzy/RongxinAI) into .agents/skills/zhiyuan-expert-manager in your project. Codex loads it when a task matches its description.
Can I use Zhiyuan Expert Manager in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rongxinzy/RongxinAI --skill zhiyuan-expert-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/zhiyuan-expert-manager, .gemini/skills/zhiyuan-expert-manager, .github/skills/zhiyuan-expert-manager and .opencode/skills/zhiyuan-expert-manager in your project.
What does Zhiyuan Expert Manager need to run?
Going by SKILL.md and its folder, Zhiyuan Expert Manager needs the command-line tools its instructions call (node).
Does Zhiyuan Expert Manager access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Zhiyuan Expert Manager safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Zhiyuan Expert Manager use?
Zhiyuan Expert Manager is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Zhiyuan Expert Manager use?
About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.2k tokens, read only when the agent opens those files.
What are the alternatives to Zhiyuan Expert Manager?
Skills that share tags, products or a category with Zhiyuan Expert Manager: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Zhiyuan Expert Manager?
rongxinzy (a GitHub organization) maintains it in rongxinzy/RongxinAI, which has 154 GitHub stars. The repository holds 94 skills in this directory. The repository was last updated on October 10, 2026.
Source: rongxinzy/RongxinAI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.