todo-tracker
The todo-tracker skill maintains a persistent TODO.md file in the workspace root for tracking tasks across sessions with high, medium, and low priority levels. Use it when the user requests to add, view, mark complete, or remove tasks, or when the system heartbeat triggers to alert about stale items older than seven days. Items are organized by priority and completed tasks are timestamped in a Done section.
git clone --depth 1 https://github.com/jdrhyne/agent-skills /tmp/todo-tracker && cp -r /tmp/todo-tracker/clawdbot/todo-tracker ~/.claude/skills/todo-trackerSKILL.md
# TODO Tracker Maintain a persistent TODO.md scratch pad in the workspace. ## File Location `TODO.md` in workspace root (e.g., `/Users/nuthome/nuri-bot/TODO.md`) ## Commands ### View TODO When user asks: "what's on the TODO?", "show TODO", "pending tasks?" ```bash cat TODO.md ``` Then summarize the items by priority. ### Add Item When user says: "add X to TODO", "TODO: X", "remember to X" ```bash bash skills/todo-tracker/scripts/todo.sh add "<priority>" "<item>" ``` Priorities: `high`, `medium`, `low` (default: medium) Examples: ```bash bash skills/todo-tracker/scripts/todo.sh add high "Ingest low-code docs" bash skills/todo-tracker/scripts/todo.sh add medium "Set up Zendesk escalation" bash skills/todo-tracker/scripts/todo.sh add low "Add user memory feature" ``` ### Mark Done When user says: "mark X done", "completed X", "finished X" ```bash bash skills/todo-tracker/scripts/todo.sh done "<item-pattern>" ``` Matches partial text. Moves item to ✅ Done section with date. ### Remove Item When user says: "remove X from TODO", "delete X from TODO" ```bash bash skills/todo-tracker/scripts/todo.sh remove "<item-pattern>" ``` ### List by Priority ```bash bash skills/todo-tracker/scripts/todo.sh list high bash skills/todo-tracker/scripts/todo.sh list medium bash skills/todo-tracker/scripts/todo.sh list low ``` ## Heartbeat Integration On heartbeat, check TODO.md: 1. Count high-priority items 2. Check for stale items (added >7 days ago) 3. If items exist, include brief summary in heartbeat response Example heartbeat check: ```bash bash skills/todo-tracker/scripts/todo.sh summary ``` ## TODO.md Format ```markdown # TODO - Nuri Scratch Pad *Last updated: 2026-01-17* ## 🔴 High Priority - [ ] Item one (added: 2026-01-17) - [ ] Item two (added: 2026-01-15) ⚠️ STALE ## 🟡 Medium Priority - [ ] Item three (added: 2026-01-17) ## 🟢 Nice to Have - [ ] Item four (added: 2026-01-17) ## ✅ Done - [x] Completed item (done: 2026-01-17) ``` ## Response Format When showing TODO: ``` 📋 **TODO List** (3 items) 🔴 **High Priority** (1) • Ingest low-code docs 🟡 **Medium Priority** (1) • Zendesk escalation from Discord 🟢 **Nice to Have** (1) • User conversation memory ⚠️ 1 item is stale (>7 days old) ```
Automatically update OpenClaw and selected skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
Check for new OpenClaw releases and notify once per new version.
OpenClaw documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all OpenClaw features
Bulk download images from login-protected gallery websites using an attached browser session. Use when asked to scrape, download, or save images from authenticated gallery pages, extract full-size images from thumbnails, or batch download from multi-page galleries.
Three-Layer Memory System — automatic fact extraction, entity-based knowledge graph, and weekly synthesis. Manages life/areas/ entities with atomic facts and living summaries.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
Sync skills between local installation and the GitHub source-of-truth repository. Use when asked to install, update, list, or push skills.
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.