content/skills/development-workflows/project-daily-summary/SKILL.md
Use when the user wants a same-day work summary grouped by project folder or repository, combining today's coding sessions, extracted plans, completed items, commits, and uncommitted changes, or says 项目日报, 今日工作总结, 按项目总结今天, 总结今天所有会话, 总结今天会话+提交+未提交改动. Use this instead of commit-daily-summary when the user explicitly wants multi-project aggregation or session-level evidence beyond pure git commits.
npx skillsauth add bahayonghang/my-claude-code-settings project-daily-summaryInstall 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.
Summarize today's coding work by project. Combine session evidence with git commits and uncommitted changes. Prioritize plans and final outcomes over process chatter.
Detect the user's language from their request:
Use the local machine date, not UTC.
Check for available session sources in this order:
~/.codex/sessions/YYYY/MM/DD/) → read $SKILL_DIR/references/codex-sessions.md for parsing details$SKILL_DIR/references/claude-code-sessions.mdIf multiple sources are available, combine them. If none are available, report that clearly and proceed with git-only mode.
For each project in scope:
Session evidence (platform-specific, see loaded reference):
Extract these signal types in priority order:
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.
For each session or working directory:
git -C <cwd> rev-parse --show-toplevel to find the project rootOutput one section per project, not one per session.
Within each project, merge multiple sessions or commit groups into a few major workstreams using these signals:
Target 1 to 5 workstreams per project, not dozens of entries.
Use the template below. Adjust section labels to match the output language.
Save policy:
AGENTS.md defines a daily-summary output directory, follow it.YYYY-MM-DD-project-daily.md# 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
session-wrapcommit-daily-summarycommit-daily-summaryBefore responding, verify:
tools
文献深度解读助手,像研究生导师一样交互式解读 Zotero 库中的学术论文,面向计算机科学、深度学习、自动化等方向(个人向)。当用户提供文献题目、DOI、PDF 或要求解读某篇论文时触发,通过 Zotero MCP 优先获取全文,并根据用户意图自动选择快速筛选、导师深读或研究复盘模式。完整深读时先完成叙事类型判断、阅读前预检、novelty 校准和作者思考路径重建,再整体概览,并基于图例、正文和表格逐图详细解读(Zotero MCP 无法提取 PDF 图片,解读基于文字信息,必要时提醒上传图片)。适用于:(1)快速判断文献是否值得深读 (2)深入理解某篇论文 (3)学习文章中的方法和技术 (4)批判性分析研究设计 (5)寻找研究灵感。需要多篇论文综合、对比或找研究空白,或 arXiv/DOI 批量规范化时,改用 paper-workbench。
development
Review Codex, Claude, OpenAI, or other agent skill directories as reusable capability packages. Use when asked to audit, review, improve, score, rewrite, debrand, package, or document a SKILL.md, skill package, marketplace skill, or agent skill directory, especially when the user wants a comprehensive findings-first report with concrete patch recommendations and validation steps.
development
Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evidence, and pause/block conditions. Use when the user asks for Codex goal instructions, Goal 指令, 目标指令, `/goal` prompts, 中文 Goal 模板, plan-to-goal interviews, success criteria, verification commands, or bounded agent work definitions.
tools
Write, debug, and validate ast-grep structural code search rules. Use this skill when the user needs syntax-aware code search, AST pattern matching, structural refactor discovery, language-construct queries, or searches that plain text tools like rg can miss, such as finding functions with particular descendants, calls inside specific contexts, missing error handling, React hook shapes, decorators, or other Tree-sitter-backed code structures.