deepwork-tracker
Track deep work sessions locally (start/stop/status) and generate a GitHub-contribution-graph style minutes-per-day heatmap for sharing (e.g., via Telegram). Use when the user says things like “start deep work”, “stop deep work”, “am I in a session?”, “show my deep work graph”, or asks to review deep work history.
Best use case
deepwork-tracker is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Track deep work sessions locally (start/stop/status) and generate a GitHub-contribution-graph style minutes-per-day heatmap for sharing (e.g., via Telegram). Use when the user says things like “start deep work”, “stop deep work”, “am I in a session?”, “show my deep work graph”, or asks to review deep work history.
Teams using deepwork-tracker should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/deepwork-tracker/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How deepwork-tracker Compares
| Feature / Agent | deepwork-tracker | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Track deep work sessions locally (start/stop/status) and generate a GitHub-contribution-graph style minutes-per-day heatmap for sharing (e.g., via Telegram). Use when the user says things like “start deep work”, “stop deep work”, “am I in a session?”, “show my deep work graph”, or asks to review deep work history.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Deepwork Tracker Use the local deepwork app (SQLite-backed) at `~/clawd/deepwork/deepwork.js`. ## Bootstrap (if the script is missing) If `~/clawd/deepwork/deepwork.js` does not exist, bootstrap it from the public repo: ```bash mkdir -p ~/clawd cd ~/clawd # Clone if missing [ -d ~/clawd/deepwork-tracker/.git ] || git clone https://github.com/adunne09/deepwork-tracker.git ~/clawd/deepwork-tracker # Ensure expected runtime path exists mkdir -p ~/clawd/deepwork cp -f ~/clawd/deepwork-tracker/app/deepwork.js ~/clawd/deepwork/deepwork.js chmod +x ~/clawd/deepwork/deepwork.js ``` (Do not fail the user request if clone/copy fails—still attempt other steps and report what’s missing.) ## Commands Run via exec: - Start a session (also starts a macOS Clock timer; default target 60m): - `~/clawd/deepwork/deepwork.js start --target-min 60` - Stop a session: - `~/clawd/deepwork/deepwork.js stop` - Check status: - `~/clawd/deepwork/deepwork.js status` - Generate a report: - Last 7 days (default): `~/clawd/deepwork/deepwork.js report --days 7 --format text` - Telegram-ready last 7 days: `~/clawd/deepwork/deepwork.js report --days 7 --format telegram` - Heatmap (optional): `~/clawd/deepwork/deepwork.js report --mode heatmap --weeks 52 --format telegram` ## Chat workflows ### Start deep work 1) Run `~/clawd/deepwork/deepwork.js start --target-min 60` (or another target if the user specifies it). 2) This should also start a macOS Clock timer for the target duration (best-effort; may require Accessibility permissions). 3) Reply with the confirmation line. ### Stop deep work 1) Run `~/clawd/deepwork/deepwork.js stop`. 2) Reply with duration. ### Show deep work graph 1) Run `~/clawd/deepwork/deepwork.js report --days 7 --format telegram`. 2) **Always send** the output to Alex on Telegram (id `8551040296`) using the `message` tool with a Markdown monospace code block. 3) Optionally acknowledge in the current chat that it was sent. If the user wants different ranges, support `--days 7|14|30|60`. (Heatmap is still available via `--mode heatmap --weeks ...` when explicitly requested.)
Related Skills
polymarket-copy-tracker
Analyze top Polymarket traders for copy trading. Use when asked to find best traders to copy, analyze trader performance/history, evaluate wallet PnL, discover high-ROI wallets, or research trader win rates on Polymarket. Supports Dune analytics, Polymarket Data API, and automated scoring.
payment-tracker-run
Automatic payment tracking and follow-up
Financial Tracker
Track business income and expenses in structured CSV format. Categorize transactions, monitor cash flow, generate P&L summaries, and spot spending trends.
expense-tracker
Manage expense tracker bot — deploy, check expenses, export data, sync locally
competitor-price-tracker
Monitor competitor pricing pages and send alerts when prices change. Track discount patterns, promotional cycles, and pricing strategy shifts.
wemp-operator
> 微信公众号全功能运营——草稿/发布/评论/用户/素材/群发/统计/菜单/二维码 API 封装
zsxq-smart-publish
Publish and manage content on 知识星球 (zsxq.com). Supports talk posts, Q&A, long articles, file sharing, digest/bookmark, homework tasks, and tag management. Use when publishing content to 知识星球, creating/editing posts, uploading files/images/audio, managing digests, batch publishing, or formatting content for 知识星球.
zoom-automation
Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.
zoho-crm-automation
Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.
ziliu-publisher
字流(Ziliu) - AI驱动的多平台内容分发工具。用于一次创作、智能适配排版、一键分发到16+平台(公众号/知乎/小红书/B站/抖音/微博/X等)。当用户需要多平台发布、内容排版、格式适配时使用。触发词:字流、ziliu、多平台发布、一键分发、内容分发、排版发布。
zhihu-post-skill
> 知乎文章发布——知乎平台内容创作与发布自动化
zendesk-automation
Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.