Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

project-daily-summary项目每日总结

Agent Skill

project-daily-summary 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

259

周安装

11

GitHub Stars

14

下载量

91
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:project-daily-summary(项目每日总结)
来源仓库:https://github.com/bahayonghang/my-claude-code-settings
仓库路径:skills/project-daily-summary
安装命令:
npx skills add https://github.com/bahayonghang/my-claude-code-settings --skill project-daily-summary
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/bahayonghang/my-claude-code-settings --skill project-daily-summary

简介

用于查找、检索和筛选项目相关信息。

  • 适合每日复盘时快速回顾关键活动和阻塞点。
  • 支持按时间线聚合 Issue、会议纪要和代码提交。
  • 安装命令:npx skills add https://github.com/bahayonghang/my-claude-code-settings --skill project-daily-summary
  • 注意个人设置类技能可能不具备通用适用性。

SKILL.md

project-daily-summary

Summarize today's coding work by project. Combine session evidence with git commits and uncommitted changes. Prioritize plans and final outcomes over process chatter.

Language Detection

Detect the user's language from their request:

  • Chinese or mixed Chinese input → output in Chinese (default)
  • English input → output in English
  • Keep identifiers, paths, branch names, and commit hashes in their original form

Core Rules

  • Do not produce a chronological 流水账.
  • Do not summarize reasoning noise or intermediate tool chatter.
  • Always summarize by project first, then by major workstream within each project.
  • If evidence is missing, say so explicitly. Do not fabricate sessions, commits, or validation results.

Workflow

Step 1: Determine today's local date

Use the local machine date, not UTC.

Step 2: Detect environment and load platform reference

Check for available session sources in this order:

  1. Codex sessions (~/.codex/sessions/YYYY/MM/DD/) → read $SKILL_DIR/references/codex-sessions.md for parsing details
  2. Claude Code context (current conversation + OMC notepad) → read $SKILL_DIR/references/claude-code-sessions.md
  3. Git-only fallback → skip session parsing, rely entirely on git evidence

If multiple sources are available, combine them. If none are available, report that clearly and proceed with git-only mode.

Step 3: Collect evidence

For each project in scope:

Session evidence (platform-specific, see loaded reference):

Extract these signal types in priority order:

  1. Goal / intent — what the user set out to do (from session start, plan files, or first prompt)
  2. Completed items — tasks marked done, files written, tests passing
  3. Key decisions — architecture choices, library selections, approach changes
  4. Changed files — from session context or git diff
  5. Validation state — tests run and their results, build status
  6. Open risks / blockers — unresolved issues, known failures

If a session source is available but parsing fails or returns empty, fall back to git evidence for that project and note (session data unavailable) in the output. Do not silently drop a project because session parsing failed.

Git evidence (universal):

git -C <repo> log --since="YYYY-MM-DD 00:00" --until="YYYY-MM-DD+1 00:00" --pretty=format:"%h %s"
git -C <repo> status --short
git -C <repo> diff --stat

Pre-check: Verify the directory is a git repository before running git commands. If not a repo, skip git evidence and rely on session evidence alone.

Read $SKILL_DIR/references/session-parsing.md for the universal signal extraction template and noise filtering rules.

Step 4: Group by project

For each session or working directory:

  1. Try git -C <cwd> rev-parse --show-toplevel to find the project root
  2. If that fails, use the working directory as the project key

Output one section per project, not one per session.

Step 5: Merge into major workstreams

Within each project, merge multiple sessions or commit groups into a few major workstreams using these signals:

  • Same branch or worktree
  • Same or similar user goal
  • Overlapping changed files
  • Same feature, bug, review, or topic

Target 1 to 5 workstreams per project, not dozens of entries.

Step 6: Output the report

Use the template below. Adjust section labels to match the output language.

Step 7: Save (optional)

Save policy:

  1. If the project's AGENTS.md defines a daily-summary output directory, follow it.
  2. Otherwise ask the user for the output directory on first use.
  3. Default filename: YYYY-MM-DD-project-daily.md
  4. If the user says not to save, return the summary in chat only.

Output Template

# Project Daily Summary
日期:YYYY-MM-DD

## 总览
- 项目数:
- 会话数:
- 主要推进:
- 今日仍未收尾:

## 项目:<repo-or-folder>
- 分支 / 仓库:
- 今日目标:
- 今日计划提炼:
- 今日完成事项:
- 今日 commits:
- 当前未提交改动:
- 风险 / 未完成项:
- 建议下一步:

## 跨项目总结
- 今天最重要的推进
- 重复出现的问题
- 明天最值得先做的 1-3 件事

Scope Rules

  • Default: summarize all projects that appear in today's sessions or that the user has committed to today.
  • If the user provides specific folders: summarize only those.

When Not to Use

  • User wants a current-session wrap-up only → use session-wrap
  • User wants a pure commit-based report → use commit-daily-summary
  • User says just "日报" without multi-project or session context → prefer commit-daily-summary

Quality Checklist

Before responding, verify:

  • Date scope is explicit
  • Projects are grouped correctly
  • Session evidence is distinguished from git evidence
  • Completed vs uncommitted vs unfinished items are clearly separated
  • No fabricated sessions, commits, or verification claims
  • Output language matches the user's language

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.74%
按下载量换算33

Claude

26.37%
按下载量换算24

Cursor

19.55%
按下载量换算18

Gemini CLI

8.95%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills