weekly-review
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@weekly-reviewRun my weekly review for last week"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
weekly-review-skill(AI 用量与提示词复盘助手)
一句话简介:面向任意 AI Agent 的自动复盘 Skill——用量看板、提示词改进、高低效归因、可视化图表、会话清理、定时周报。
目录
Related MCP server: YST KPI Daily Report Collector
解决什么问题
想提升自己的提示词表达能力
想查看本周 AI 用量(时长、投入分布、看板)
想总结复盘自己工作里低效和高效的地方
想看可视化图表报告(时间分布、归因、Token 趋势)
想清理/对齐自己和 AI 还开着的对话
想让 AI 自动/定时做周度复盘
功能特性
AI 用量与时间看板 + 一句话结论
提示词复盘与改写建议(分项目)
高效/低效归因(思路 / 记忆 / 流程)+ 正面范本
可视化图表:时间分布、低效归因、Token 趋势(SVG)
开放会话对齐清理 + 动作台账
定时自动周报:可被 Automation / CLI / MCP 调用(示例见
automations/)标准
review-inputJSON;宿主 Agent 采数,Skill 定结构与渲染
安装
推荐(skills.sh / 多 Agent)
npx skills add testman2025/weekly-review-skill
# 或指定 skill:
npx skills add testman2025/weekly-review-skill --skill weekly-reviewClawHub
openclaw skills install weekly-review本地试跑
git clone https://github.com/testman2025/weekly-review-skill.git
cd weekly-review-skill/skills/weekly-review
python -m cli --input schema/review-input.example.json -o weekly-report.md兼容:Cursor / Claude Code 等可经 npx skills 安装;OpenClaw 经 ClawHub;CLI / MCP 可选渲染。
使用说明
Agent 汇总本周会话事实 → 填入
review-input对话按六章输出,或 CLI:
python -m cli -i review-input.json -o 周度复盘.md对开放会话当场拍板
字段说明见 skills/weekly-review/schema/README.md。
Skill 定义见 skills/weekly-review/SKILL.md。
旧版「直接读 SQLite」代码已移至 skills/weekly-review/legacy/,非公开主路径。
示例输出
脱敏 Demo 见 demo/README.md:
cd skills/weekly-review
python -m cli --input ../../demo/review-input-cursor-demo.json -o ../../demo/2026-07-20周度复盘-Cursor-Demo.md安全与边界
采数由宿主 Agent 完成;本 skill 不上传密钥、Token、密码。
不做一键删除会话数据库;开放会话仅对齐拍板。
定时复盘依赖宿主 Automation / 调度,skill 本身不含独立 cron 守护进程。
发布到 ClawHub
clawhub login
clawhub skill publish ./skills/weekly-review \
--slug weekly-review \
--name "Weekly Review" \
--version 1.2.5 \
--changelog "Discoverability: concise Chinese description for prompts, usage, charts, session cleanup, auto review."许可证
本仓库:MIT
ClawHub 分发:MIT-0
This server cannot be deployed
Maintenance
Related MCP Connectors
- DoneThatOAuthai.donethat
Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.
Weekly 5-15 reports for executive teams: submit reports, fetch the Friday briefing.
List WaterrAI scenarios, fetch AI-run meetings, and pull rubric-scored analyses.
Portable AI memory shared across models and harnesses - plain markdown you own.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceConnects to Jira instances to generate weekly reports based on issue activity, supporting custom JQL queries and optional LLM summarization.1-
- FlicenseAqualityCmaintenanceAutomatically collects daily report data from KPI systems using browser automation and Google OAuth login. Generates structured Markdown reports for specified date ranges with persistent session management.6-
- FlicenseNot gradedqualityDmaintenanceSummarizes Slack activity and GitLab merge requests with OpenAI to help generate daily standups, weekly reports, or quarterly check-ins.-
- AlicenseAqualityDmaintenanceGenerates sprint retrospectives grounded in actual data from Jira, GitHub, and Slack, providing evidence-backed insights and action items.627 npmMIT