skills/claude-skills-open/skills/pm/weekly-review/SKILL.md
Weekly project review report
npx skillsauth add aaaaqwq/claude-code-skills weekly-reviewInstall 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.
Weekly work review -- hours, tokens, progress
| What | Path |
|------|------|
| Tasks | $PM_PATH/pm_tasks_master.csv |
| Execution Log | $PM_PATH/pm_execution_log.csv |
| Learnings | $PM_PATH/pm_learnings.csv |
| Script | $PROJECT_ROOT/projects/scripts/weekly_report.py |
cd $PROJECT_ROOT
python3 projects/scripts/weekly_report.py
import pandas as pd
from datetime import date, timedelta
# Last 7 days
week_ago = str(date.today() - timedelta(days=7))
today = str(date.today())
tasks = pd.read_csv('$PM_PATH/pm_tasks_master.csv')
log = pd.read_csv('$PM_PATH/pm_execution_log.csv')
learnings = pd.read_csv('$PM_PATH/pm_learnings.csv')
# Filter by date
log_week = log[(log['date'] >= week_ago) & (log['date'] <= today)]
# Total hours
total_hours = log_week['duration_minutes'].sum() / 60
print(f"Total hours: {total_hours:.1f}")
# Total tokens
total_tokens = log_week['tokens_total'].sum()
print(f"Total tokens: {total_tokens:,}")
# Completed tasks
completed = tasks[(tasks['status'] == 'done') & (tasks['last_updated'] >= week_ago)]
print(f"Tasks completed: {len(completed)}")
# By activity type
by_type = log_week.groupby('activity_type')['duration_minutes'].sum() / 60
print("\nBy type:")
print(by_type)
# By project
by_project = log_week.groupby('project_id')['duration_minutes'].sum() / 60
print("\nBy project:")
print(by_project)
=== WEEKLY REPORT ===
Period: 2025-01-27 — 2025-02-03
METRICS
* Hours: 12.5
* Tokens: 45,230
* Tasks completed: 8
BY PROJECT
* proj-001 (Client D): 6.5 hrs
* proj-002 (CRM): 4.0 hrs
* proj-003 (Infra): 2.0 hrs
BY TYPE
* coding: 5.5 hrs
* research: 3.0 hrs
* planning: 2.0 hrs
* discussion: 2.0 hrs
COMPLETED TASKS
* [proj-001] Send outreach
* [proj-001] Check responses
* [proj-002] Update CRM schema
...
LEARNINGS
* Telegram has a 60 sec limit between messages
* WhatsApp does not sync history
...
BLOCKED
* [proj-003] task-004: Waiting for Tailscale account
NEXT WEEK
* Finish proj-001
* Start proj-004
report_path = f'$PROJECT_ROOT/reports/weekly_{today}.md'
with open(report_path, 'w') as f:
f.write(report_content)
show-today -- what's for todaytesting
通用自媒体文章自动发布工具。支持百家号、搜狐号、知乎、微信公众号、小红书、抖音号六个平台的自动化发布流程。使用Playwright自动化实现平台导航和发布,支持通过storageState管理Cookie实现账号切换。
development
# SKILL.md - Model Configuration Status (mcstatus) ## 触发条件 - `/mcstatus` 命令 - 用户询问模型配备、模型配置、model status、模型列表等 ## 功能 实时生成 Agent + Cron 的模型配置报告,展示当前所有 agent 的主模型/fallback链和所有 cron 任务的模型分配。 ## 执行步骤 ### Step 1: 收集 Agent 模型配置 读取各 agent 的 models.json 获取主模型和 fallback 链: ```bash for agent in main ops code quant data research content market finance pm law product sales batch; do config=$(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)。