Cc Sdd New Agent
gotalab/cc-sdd
Add or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end.
XAgent是一个智能跨域分析助手,基于SOP驱动的规划、多工具协调和多层次数据分析框架,提供专业的商业智能和数据分析能力。当用户需要进行数据分析、业务分析、生成报告或需要结构化的问题解决方案时使用。
$ npx skills add xiaoyuge886/aigc --skill xagent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install xiaoyuge886/aigc xagent --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/xiaoyuge886/aigc.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/x_agent_skill .claude/skills/xagent && 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 "xagent" agent skill from https://github.com/xiaoyuge886/aigc/tree/main/.claude/skills/x_agent_skill into .claude/skills/xagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xagent", 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/xiaoyuge886/aigc/tree/main/.claude/skills/x_agent_skillType 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 xiaoyuge886/aigc --skill xagent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install xiaoyuge886/aigc xagent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xiaoyuge886/aigc.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/x_agent_skill .agents/skills/xagent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "xagent" agent skill from https://github.com/xiaoyuge886/aigc/tree/main/.claude/skills/x_agent_skill into .agents/skills/xagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xagent", 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 xiaoyuge886/aigc --skill xagent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install xiaoyuge886/aigc xagent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xiaoyuge886/aigc.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/x_agent_skill .cursor/skills/xagent && 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 "xagent" agent skill from https://github.com/xiaoyuge886/aigc/tree/main/.claude/skills/x_agent_skill into .cursor/skills/xagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xagent", 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/xiaoyuge886/aigc.git --path .claude/skills/x_agent_skill--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 xiaoyuge886/aigc --skill xagent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install xiaoyuge886/aigc xagent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xiaoyuge886/aigc.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/x_agent_skill .gemini/skills/xagent && 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 "xagent" agent skill from https://github.com/xiaoyuge886/aigc/tree/main/.claude/skills/x_agent_skill into .gemini/skills/xagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xagent", 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 xiaoyuge886/aigc xagentInstalls 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 xiaoyuge886/aigc --skill xagent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/xiaoyuge886/aigc.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/x_agent_skill .github/skills/xagent && 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 "xagent" agent skill from https://github.com/xiaoyuge886/aigc/tree/main/.claude/skills/x_agent_skill into .github/skills/xagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xagent", 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 xiaoyuge886/aigc --skill xagent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install xiaoyuge886/aigc xagent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xiaoyuge886/aigc.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/x_agent_skill .opencode/skills/xagent && 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 "xagent" agent skill from https://github.com/xiaoyuge886/aigc/tree/main/.claude/skills/x_agent_skill into .opencode/skills/xagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xagent", 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.
xagentXAgent是一个智能跨域分析助手,基于SOP驱动的规划、多工具协调和多层次数据分析框架,提供专业的商业智能和数据分析能力。当用户需要进行数据分析、业务分析、生成报告或需要结构化的问题解决方案时使用。
Xagent is an agent skill from xiaoyuge886/aigc. XAgent是一个智能跨域分析助手,基于SOP驱动的规划、多工具协调和多层次数据分析框架,提供专业的商业智能和数据分析能力。当用户需要进行数据分析、业务分析、生成报告或需要结构化的问题解决方案时使用。
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 30 other files, including reference files (for example `PROJECT_STRUCTURE.md`, `README.md` and `core/file_system_loader.py`).
It sits in Business, Finance & HR, covering Operations and SOPs. The repository describes itself as: AIGC 智能 Agent 平台是一个强大的 AI 应用框架,通过集成 Claude AI 模型和丰富的技能生态系统,为用户提供智能化、场景化的 AI 解决方案。平台采用前后端分离架构,支持多租户、会话管理、技能扩展等企业级特性。 The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e970014. It shows what the files ask for, not the result of running them.
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.
Ships script files (Python, from the files we listed), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Xagent loads about 2.1k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 27 tokens; SKILL.md has 202 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.
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); files beside SKILL.md are not scanned.
The full file from xiaoyuge886/aigc at commit e970014, republished under its MIT licence (© xiaoyuge886). 202 words, ~2,114 tokens.
.claude/skills/xagent/SKILL.md (or your agent's skills folder). This skill also uses 24 other files; get the full folder from GitHub.一个全面的Claude技能,实现XAgent的智能跨域分析能力,以SOP驱动的规划、多工具协调和多层次数据分析为特色。
XAgent是一个精密的跨域智能助手,在各个领域提供结构化、高质量的分析。它使用标准作业程序(SOP)确保一致的、高质量的输出,并协调多个工具高效完成复杂任务。
该技能是自包含的,除了Python 3.8+外不需要任何外部依赖。所有组件都包含在包中。
from xagent_skill import XAgent, XAgentConfig
# 使用默认配置初始化
agent = XAgent()
# 处理用户查询
result = agent.process_request(
query="分析销售数据趋势并识别增长机会",
user_id="user_001"
)
if result['guidance_prompt']:
print(f"生成了专业指导prompt,长度: {len(result['guidance_prompt'])}字符")
print(f"推荐的工具: {result['recommended_tools']}")
print(f"包含多层次规划: {result['metadata']['has_hierarchical_planning']}")
if result['hierarchical_plan']:
print(f"预计工时: {result['hierarchical_plan']['estimated_timeline']['total_estimated_hours']}小时")from xagent_skill import XAgent, XAgentConfig
# 自定义配置
config = XAgentConfig(
enable_sop_guidance=True,
enable_hierarchical_planning=True,
enable_tool_coordination=True,
enable_domain_expertise=True,
enable_analysis_guidance=True,
prompt_language="zh-CN",
detail_level="comprehensive"
)
agent = XAgent(config)
# 多轮对话示例
session_id = "analysis_session"
# 第一次查询
result1 = agent.process_request(
query="分析Q3销售业绩",
user_id="analyst_001",
session_id=session_id
)
# 后续查询,带上下文
result2 = agent.process_request(
query="重点关注表现不佳的区域并提出改进建议",
user_id="analyst_001",
session_id=session_id
)
# 复杂报告写作
result3 = agent.process_request(
query="基于以上分析,撰写一份完整的季度业绩分析报告",
user_id="analyst_001",
session_id=session_id
)SOPPlanningSkill)使用标准作业程序生成结构化执行计划。
特性:
from joyagent_skill import SOPPlanningSkill
planner = SOPPlanningSkill()
plan = planner.plan("分析客户流失模式")
print(f"生成了{len(plan.steps)}个步骤")
print(f"模式: {plan.mode.value}")TaskExecutionSkill)使用并行处理能力执行结构化计划。
特性:
from joyagent_skill import TaskExecutionSkill
executor = TaskExecutionSkill(max_parallel_tasks=3)
results = executor.execute(plan, context={'data': sales_data})PromptEngine)管理复杂的prompt模板和链,确保AI行为一致。
特性:
from joyagent_skill import prompt_engine
# 获取复杂分析的最优prompt
prompt = prompt_engine.get_optimal_prompt(
'complex_analysis',
{'query': '分析市场趋势'}
)MultiToolCoordinator)智能选择和协调多个分析工具。
特性:
from joyagent_skill import MultiToolCoordinator
coordinator = MultiToolCoordinator()
tools = coordinator.select_tools("全面数据分析")
plan = coordinator.create_execution_plan(tools)DataAnalysisSkill)实现专业的四阶段数据分析框架。
特性:
from joyagent_skill import DataAnalysisSkill
analyzer = DataAnalysisSkill()
results = analyzer.analyze(sales_data, "分析销售业绩")
report = analyzer.generate_analysis_report(results)ConversationManager)管理多轮对话和上下文记忆。
特性:
from joyagent_skill import ConversationManager
manager = ConversationManager()
conv_id = manager.start_conversation("user_001", "session_001", "初始查询")
manager.add_message(conv_id, MessageRole.USER, "后续问题")config = JoyAgentConfig(
enable_sop_planning=True, # 启用SOP规划
enable_multi_tool_coordination=True, # 启用工具协调
enable_conversation_memory=True, # 启用对话上下文
enable_data_analysis=True, # 启用数据分析框架
max_parallel_tools=3, # 最大并行工具数
max_conversation_history=50, # 最大对话消息存储数
auto_optimization=True # 启用性能优化
)planner.update_thresholds(
high=0.9, # 高置信度SOP匹配阈值
low=0.4 # 无SOP模式阈值
)from joyagent_skill import JoyAgent
agent = JoyAgent()
result = agent.process_request(
query="分析2023年销售数据,识别增长趋势并提出改进策略",
user_id="sales_manager"
)
# 输出包括:
# - 详细销售趋势分析
# - 增长机会识别
# - 战略建议
# - 支持数据可视化result = agent.process_request(
query="分析客户流失模式,识别关键风险因素并提出保留策略",
user_id="customer_success"
)
# 输出包括:
# - 流失率分析
# - 风险因素识别
# - 客户细分分析
# - 保留策略建议# 初始广泛分析
result1 = agent.process_request(
query="提供Q3绩效指标概览",
user_id="analyst",
session_id="quarterly_review"
)
# 深入特定领域
result2 = agent.process_request(
query="专注于利润率最高的产品线并分析客户满意度",
user_id="analyst",
session_id="quarterly_review"
)
# 生成最终报告
result3 = agent.process_request(
query="创建包含可行建议的综合执行摘要",
user_id="analyst",
session_id="quarterly_review"
){
"plan_id": "plan_1234567890",
"title": "销售数据分析计划",
"mode": "HIGH_MODE",
"steps": [
{
"step_order": 1,
"title": "数据收集和验证",
"description": "收集和清洗销售数据",
"tools": ["data_analysis"],
"expected_output": "已验证的数据集"
}
],
"confidence": 0.95
}# 销售数据分析报告
## 执行摘要
- 总销售额:¥X.XM(同比增长Y%)
- 关键发现:[最重要的洞察]
## 详细分析
### 1. 描述性分析
- 销售趋势和模式
- 绩效指标
### 2. 异常检测
- 识别异常
- 根本原因分析
### 3. 相关性分析
- 关键关系
- 影响因素
### 4. 预测分析
- 预测结果
- 场景建模
## 建议
1. [战略建议]
2. [战术建议]
## 限制
- [分析约束]
- [数据限制]# 直接导入
from joyagent_skill import JoyAgent
# 带自定义配置
from joyagent_skill import JoyAgent, JoyAgentConfig
# 单独组件使用
from joyagent_skill import SOPPlanningSkill, DataAnalysisSkill# REST API使用(通过FastAPI部署时)
import requests
response = requests.post('http://localhost:8000/api/chat', json={
'message': '分析销售数据',
'user_id': 'user_001'
})技能可以直接在Claude Agent环境中导入和使用:
# 在Claude Agent上下文中
skill = load_skill('joyagent_skill')
result = skill.execute("分析客户数据")问题:分析失败,显示"数据不足" 解决方案:确保最少50个数据点并包含足够列
问题:未生成执行计划 解决方案:检查查询清晰度和具体性
问题:响应缓慢 解决方案:减少数据集大小或简化分析范围
问题:结果不一致 解决方案:使用一致的数据格式和查询措辞
import logging
logging.basicConfig(level=logging.DEBUG)
agent = JoyAgent()
result = agent.process_request("测试查询", debug=True)# 获取系统统计
stats = agent.get_stats()
print(f"成功率: {stats['successful_requests']/stats['total_requests']:.2%}")
print(f"平均响应时间: {stats['avg_response_time']:.2f}s")虽然这是自包含技能,但欢迎通过以下方式进行改进:
本技能基于MIT许可证提供。详情请参见LICENSE文件。
如遇问题、问题或功能请求:
版本:2.0.0 最后更新:2024-12-14 兼容性:Claude Agent, Python 3.8+ 升级说明:从JoyAgent 1.0.0升级到XAgent 2.0.0,增强跨域能力和MCP集成
© xiaoyuge886, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 24 other files (references) in .claude/skills/x_agent_skill of xiaoyuge886/aigc.
Open the folder on GitHubat commit e970014
Xagent 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 |
|---|---|---|---|---|---|---|
| Xagent this skillxiaoyuge886/aigc | 198 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Cc Sdd New Agentgotalab/cc-sdd | 3.7k | — | ~1.1k | Automated safety check: Pass | MIT | |
| DBS Business Toolkit Entrydontbesilent2025/dbskill | 11k | — | ~2k | Automated safety check: Pass | Custom licence | |
| Agent Sop Authorstrands-agents/agent-sop | 1.2k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| Diffusion Narrative Denouncingcanwhite/Krebs | 1k | — | ~831 | Automated safety check: Pass | MIT | |
| Company Researchsimonlin1212/Vibe-Research | 2.7k | — | ~3.2k | Automated safety check: Pass | MIT |
gotalab/cc-sdd
Add or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end.
dontbesilent2025/dbskill
Chinese-language entry skill for the dontbesilent business toolkit: onboards new users, orchestrates tasks across sub-skills, runs numbered prompts and lists hidden ones.
strands-agents/agent-sop
Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints.
canwhite/Krebs
基于"扩散模型叙事去噪流"的小说写作 SOP。将 AI 视为去杂质机器,通过锁定全局信号、预测叙事噪声、精准去噪、随机修正四个步骤,解决 AI 翻译腔、逻辑断层和故事平淡的问题。
simonlin1212/Vibe-Research
A 股 / 港股 / 美股个股研究六阶段 SOP(profile → financials → estimates → valuation → risk → report),Phase 0 范围 = 财务估值闭环。当任务是研究 / 分析 / 评估一只或多只已指定代码的个股时使用(港股 / 美股的口径差异见 §7);规定每阶段取哪些数据、调哪些 calc 函数、必须落盘什么产物、过什么…
0xenzyme/polanyi-skill
Michael Polanyi 的思维框架。用 Polanyi 视角分析隐性知识、技能习得、经验传承、师徒制、 知识管理、学习方法、AI/工具替代边界、科学共同体与后批判哲学问题。
xiaoyuge886/aigc
Single source of truth and librarian for ALL Claude official documentation.
xiaoyuge886/aigc
Perform data analysis tasks including data cleaning, statistical analysis, visualization, and insight generation.
xiaoyuge886/aigc
投资尽调报告专业生成工具。当用户需要撰写投资尽调报告、尽职调查报告、投资分析报告时使用此skill。支持处理Excel财务数据、PDF文档等多种格式数据源,自动生成包含执行摘要、业务分析、财务分析、风险提示、投资建议等核心章节的专业报告。无论用户明确要求"写报告"还是提到"分析投资标的"、"评估项目"、"做DD"等相关需求时,都应使用此skill。
xiaoyuge886/aigc
简化版MinIO文件上传工具,支持一键上传文件到MinIO对象存储并获取访问链接. An agent skill from xiaoyuge886/aigc.
xiaoyuge886/aigc
专业的待办事项管理技能,指导如何有效使用 TodoWrite 工具进行任务规划、进度跟踪和状态管理。当用户需要处理复杂任务、多步骤工作流或需要任务规划时使用。
xiaoyuge886/aigc
Best practices for building Stripe integrations. An agent skill from xiaoyuge886/aigc.
Categories
XAgent是一个智能跨域分析助手,基于SOP驱动的规划、多工具协调和多层次数据分析框架,提供专业的商业智能和数据分析能力。当用户需要进行数据分析、业务分析、生成报告或需要结构化的问题解决方案时使用。. Xagent is an agent skill from xiaoyuge886/aigc.
Xagent fits situations like: tasks that involve Operations and SOPs.
Run `npx skills add xiaoyuge886/aigc --skill xagent -a claude-code`. Or copy the skill folder (.claude/skills/x_agent_skill in xiaoyuge886/aigc) into .claude/skills/xagent in your project. Claude Code loads it when a task matches its description.
Run `npx skills add xiaoyuge886/aigc --skill xagent -a codex`. Or copy the skill folder (.claude/skills/x_agent_skill in xiaoyuge886/aigc) into .agents/skills/xagent in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xiaoyuge886/aigc --skill xagent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xagent, .gemini/skills/xagent, .github/skills/xagent and .opencode/skills/xagent in your project.
Going by SKILL.md and its folder, Xagent needs Python for the scripts in its folder. Our summary lists: Python 3.
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.
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. Review the folder before installing.
Xagent is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.5k 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 1.9k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Xagent: Cc Sdd New Agent (gotalab/cc-sdd, 3.7k stars), DBS Business Toolkit Entry (dontbesilent2025/dbskill, 11k stars), Agent Sop Author (strands-agents/agent-sop, 1.2k stars) and Diffusion Narrative Denouncing (canwhite/Krebs, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
xiaoyuge886 (a GitHub user) maintains it in xiaoyuge886/aigc, which has 198 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on July 14, 2026.
Source: xiaoyuge886/aigc on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.