深度专注
deepfocus
by bytesagain1
Run Pomodoro sessions with break timers and productivity tracking. Use when starting focus sessions, tracking streaks, reviewing productivity.
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/bytesagain1/deepfocus文档
Deepfocus
Deepfocus v2.0.0 — a productivity toolkit for managing tasks, plans, reviews, streaks, reminders, and more from the command line.
Commands
Run via: bash scripts/script.sh <command> [args]
| Command | Description |
|---|---|
add <input> | Add a new entry (task, note, idea). Without args, shows recent entries. |
plan <input> | Create or view plan entries for organizing your day/week. |
track <input> | Track progress on goals, habits, or tasks. |
review <input> | Log review notes — reflect on what went well or needs improvement. |
streak <input> | Record streak data for habit tracking and consistency. |
remind <input> | Set reminders and notes for future reference. |
prioritize <input> | Mark and log priority levels for tasks. |
archive <input> | Archive completed or outdated entries. |
tag <input> | Tag entries with labels for easy categorization. |
timeline <input> | Add timeline entries for chronological tracking. |
report <input> | Generate or log report entries for summaries. |
weekly-review <input> | Log weekly review notes for end-of-week reflection. |
stats | Show summary statistics across all entry types. |
export <fmt> | Export all data in json, csv, or txt format. |
search <term> | Search across all log files for a keyword. |
recent | Show the 20 most recent activity entries from the history log. |
status | Health check — version, data directory, entry count, disk usage. |
help | Show the built-in help message with all available commands. |
version | Print the current version (deepfocus v2.0.0). |
Each data command (add, plan, track, etc.) works in two modes:
- With arguments: saves the input with a timestamp to its dedicated log file.
- Without arguments: displays the 20 most recent entries from that log.
Data Storage
All data is stored locally in ~/.local/share/deepfocus/:
- Each command has its own log file (e.g.,
add.log,plan.log,track.log) - Entries are saved in
timestamp|valueformat - A unified
history.logrecords all activity across commands - Export files are written to the same directory
Requirements
- Bash (standard system shell)
- No external dependencies — uses only coreutils (
date,wc,du,grep,tail,cat)
When to Use
- When you need to quickly add tasks, plans, or notes from the terminal
- To track daily habits and maintain productivity streaks
- For end-of-day or weekly reviews and reflections
- To set reminders and prioritize tasks without leaving the command line
- To search through past entries by keyword
- To export your productivity data for analysis or backup
- When you want a lightweight, file-based focus and task management system
Examples
# Add a task
deepfocus add "Write unit tests for the auth module"
# Create a plan for the day
deepfocus plan "Morning: deep work on API refactor. Afternoon: PR reviews."
# Track a habit
deepfocus track "Completed 45-minute focus session on documentation"
# Log a review
deepfocus review "Good progress on backend. Need to speed up frontend work."
# Record a streak
deepfocus streak "Day 15 of daily coding — still going strong"
# Set a reminder
deepfocus remind "Submit expense report by end of week"
# Prioritize a task
deepfocus prioritize "P0: Fix production memory leak"
# Archive an old entry
deepfocus archive "Q3 planning notes — no longer relevant"
# Tag an entry
deepfocus tag "meeting-notes: Sprint retrospective takeaways"
# Add to timeline
deepfocus timeline "Shipped v2.0 release to production"
# Generate a report
deepfocus report "Weekly output: 12 tasks completed, 3 carried over"
# Log a weekly review
deepfocus weekly-review "Best week this month — cleared the entire backlog"
# View all statistics
deepfocus stats
# Export everything as JSON
deepfocus export json
# Search for entries mentioning "focus"
deepfocus search focus
# Check recent activity
deepfocus recent
# Health check
deepfocus status
Powered by BytesAgain | bytesagain.com | hello@bytesagain.com
相关 Skills
技能工坊
by anthropics
覆盖 Skill 从创建到迭代优化全流程:起草能力、补测试提示、跑评测与基准方差分析,并持续改写内容和描述,提升效果与触发准确率。
✎ 技能工坊把技能从创建、迭代到评测串成闭环,方差分析加描述优化,特别适合把触发准确率打磨得更稳。
PPT处理
by anthropics
处理 .pptx 全流程:创建演示文稿、提取和解析幻灯片内容、批量修改现有文件,支持模板套用、合并拆分、备注评论与版式调整。
✎ 涉及PPTX的创建、解析、修改到合并拆分都能一站搞定,连备注、模板和评论也能处理,做演示文稿特别省心。
PDF处理
by anthropics
遇到 PDF 读写、文本表格提取、合并拆分、旋转加水印、表单填写或加解密时直接用它,也能提取图片、生成新 PDF,并把扫描件通过 OCR 变成可搜索文档。
✎ PDF杂活别再来回切工具了,文本表格提取、合并拆分到OCR识别一次搞定,连扫描件也能变可搜索。
相关 MCP 服务
文件系统
编辑精选by Anthropic
Filesystem 是 MCP 官方参考服务器,让 LLM 安全读写本地文件系统。
✎ 这个服务器解决了让 Claude 直接操作本地文件的痛点,比如自动整理文档或生成代码文件。适合需要自动化文件处理的开发者,但注意它只是参考实现,生产环境需自行加固安全。
by wonderwhy-er
Desktop Commander 是让 AI 直接执行终端命令、管理文件和进程的 MCP 服务器。
✎ 这工具解决了 AI 无法直接操作本地环境的痛点,适合需要自动化脚本调试或文件批量处理的开发者。它能让你用自然语言指挥终端,但权限控制需谨慎,毕竟让 AI 执行 rm -rf 可不是闹着玩的。
EdgarTools
编辑精选by dgunning
EdgarTools 是无需 API 密钥即可解析 SEC EDGAR 财报的开源 Python 库。
✎ 这个工具解决了金融数据获取的痛点——直接让 AI 读取结构化财报,比如让 Claude 分析苹果的 10-K 文件。适合量化分析师或金融开发者快速构建数据管道。但注意,它依赖 SEC 网站稳定性,高峰期可能延迟。