Skip to main content
ClaudeWave
Skill235 estrellas del repoactualizado 3d ago

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.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/jdrhyne/agent-skills /tmp/todo-tracker && cp -r /tmp/todo-tracker/clawdbot/todo-tracker ~/.claude/skills/todo-tracker
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.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)
```
auto-updaterSkill

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.

clawdbot-release-checkSkill

Check for new OpenClaw releases and notify once per new version.

clawddocsSkill

OpenClaw documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all OpenClaw features

gallery-scraperSkill

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.

knowledge-graphSkill

Three-Layer Memory System — automatic fact extraction, entity-based knowledge graph, and weekly synthesis. Manages life/areas/ entities with atomic facts and living summaries.

self-improving-agentSkill

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.

skill-syncSkill

Sync skills between local installation and the GitHub source-of-truth repository. Use when asked to install, update, list, or push skills.

codexSkill

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.