skills/claude-skills-open/skills/pm/create-project/SKILL.md
Create new project with breakdown
npx skillsauth add aaaaqwq/claude-code-skills create-projectInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Creating a new project with task breakdown
| What | Path |
|------|------|
| Projects | $PM_PATH/pm_projects_master.csv |
| Tasks | $PM_PATH/pm_tasks_master.csv |
project_id,project_name,description,goal,status,priority,priority_score,owner,created_date,last_updated,deadline,estimated_hours,actual_hours,actual_tokens,crm_link_type,crm_link_id,tags,notes
import pandas as pd
from datetime import date
import uuid
projects = pd.read_csv('$PM_PATH/pm_projects_master.csv')
new_project = {
'project_id': f'proj-{uuid.uuid4().hex[:4]}',
'project_name': 'Project name',
'description': 'Detailed description',
'goal': 'What does success look like?',
'status': 'planning', # idea/planning/in_progress/on_hold/completed/cancelled
'priority': 'hot', # hot/medium/low
'priority_score': 0.9,
'owner': 'Ivan',
'created_date': str(date.today()),
'last_updated': str(date.today()),
'deadline': '2025-02-10', # if applicable
'estimated_hours': 10,
'actual_hours': 0,
'actual_tokens': 0,
'crm_link_type': '', # company/person/activity
'crm_link_id': '',
'tags': 'tag1;tag2',
'notes': ''
}
projects = pd.concat([projects, pd.DataFrame([new_project])], ignore_index=True)
projects.to_csv('$PM_PATH/pm_projects_master.csv', index=False)
tasks = pd.read_csv('$PM_PATH/pm_tasks_master.csv')
project_id = 'proj-xxxx' # ID of the created project
task_list = [
('Research', 'Gather information', 2),
('Planning', 'Define approach', 1),
('Implementation', 'Do the work', 5),
('Testing', 'Verify results', 1),
]
for i, (name, desc, hours) in enumerate(task_list):
new_task = {
'task_id': f'task-{uuid.uuid4().hex[:4]}',
'project_id': project_id,
'parent_task_id': '',
'task_name': name,
'description': desc,
'status': 'todo',
'priority': 'medium',
'priority_score': 0.5,
'assignee': 'Ivan',
'created_date': str(date.today()),
'last_updated': str(date.today()),
'deadline': '',
'estimated_hours': hours,
'actual_hours': 0,
'actual_tokens': 0,
'blocked_by': '',
'blocking': '',
'order_index': i + 1
}
tasks = pd.concat([tasks, pd.DataFrame([new_task])], ignore_index=True)
tasks.to_csv('$PM_PATH/pm_tasks_master.csv', index=False)
idea → planning → in_progress → on_hold → completed/cancelled
If the project is linked to CRM:
'crm_link_type': 'person', # or 'company', 'activity'
'crm_link_id': 'https://linkedin.com/in/example', # or website, activity_id
query-leads -- if linked to CRMtesting
通用自媒体文章自动发布工具。支持百家号、搜狐号、知乎、微信公众号、小红书、抖音号六个平台的自动化发布流程。使用Playwright自动化实现平台导航和发布,支持通过storageState管理Cookie实现账号切换。
development
# SKILL.md - Model Configuration Status (mcstatus) ## 触发条件 - `/mcstatus` 命令 - 用户询问模型配备、模型配置、model status、模型列表等 ## 功能 实时生成 Agent + Cron 的模型配置报告,展示当前所有 agent 的主模型/fallback链和所有 cron 任务的模型分配。 ## 执行步骤 ### Step 1: 收集 Agent 模型配置 读取各 agent 的 models.json 获取主模型和 fallback 链: ```bash for agent in main ops code quant data research content market finance pm law product sales batch; do config=$(cat ~/.openclaw/agents/$agent/agent/models.json 2>/dev/null) if [ -n "$config" ]; then echo "=== $agent
tools
MCP 服务器智能管理助手。自动检测 MCP 可用性、智能开关、功能问答,提供人性化的 MCP 管理体验。
tools
从GitHub搜索并自动安装配置MCP(Model Context Protocol)服务器工具到Claude配置文件。当用户需要安装MCP工具时触发此技能。工作流程:搜索GitHub上的MCP项目 -> 提取npx配置 -> 添加到~/.claude.json -> 处理API密钥(如有)。