Skip to main content
ClaudeWave
ES, Spanish
Skill1.4k estrellas del repoactualizado 6d ago

tasks

This Claude Code skill implements a two-layer task management system for the Vellum Assistant. Task templates capture reusable conversation patterns with input placeholders via the `assistant task` CLI, while work items represent actual queued tasks with priority levels (0-2) and status tracking (queued to done). Use this skill when users need to save recurring task workflows, manage a prioritized work queue, or execute templated tasks with different inputs. The system requires explicit tool declarations when adding queue items to ensure proper authorization and execution.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/vellum-ai/vellum-assistant /tmp/tasks && cp -r /tmp/tasks/skills/tasks ~/.claude/skills/tasks
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

Two-layer task system: **task templates** (reusable definitions with input placeholders) and **work items** (instances in the Task Queue with priority tiers and status tracking).

## Task Templates

Templates are reusable definitions saved from conversations. They capture the conversation pattern with placeholders that can be run later with different inputs. Manage templates with the `assistant task` CLI:

```bash
# Save the current conversation as a reusable task template
assistant task save --conversation-id <id> --title "Weekly report"

# List all saved task templates
assistant task list

# Run a saved template with specific inputs
assistant task run --name "Weekly report" --inputs '{"team": "engineering"}'

# Delete a task template by ID
assistant task delete <id>
```

## Work Items (Task Queue)

Work items are the user-facing "Tasks" managed through conversation. They track status and priority:

- **Priority tiers**: 0 = high, 1 = medium (default), 2 = low
- **Status flow**: queued -> running -> awaiting_review -> done
- **Resolution precedence**: work_item_id > task_id > task_name > title

Manage the queue with `assistant task queue`:

```bash
# View the current task queue
assistant task queue show

# Add an item to the queue (ad-hoc or from a template)
assistant task queue add --title "Review Q2 metrics" --required-tools host_bash,web_search

# Update a work item's status
assistant task queue update --work-item-id <id> --status done

# Remove a work item from the queue
assistant task queue remove --work-item-id <id>

# Run a specific work item from the queue
assistant task queue run --work-item-id <id>
```

## Tips

- When the user says "add to my tasks" or "add to my queue", use `assistant task queue add` (NOT schedule).
- Use `assistant task save` only when the user wants to capture a conversation pattern as a reusable template.
- `assistant task list` shows saved templates; `assistant task queue show` shows the active work queue.
- **Always specify `--required-tools`** when running `assistant task queue add`. Think about what tools the task will need at execution time and list them explicitly (e.g. `host_bash` for shell commands, `host_file_read,host_file_write` for file operations, `web_search,web_fetch` for web lookups). The user must approve these tools before the task can run -- omitting them forces a fallback to all tools, which is noisy and may miss non-standard tools the task actually needs.
acpSkill

Set up, authenticate, and run external coding agents (Claude Code, Codex) via the Agent Client Protocol

amazonSkill

Shop on Amazon and Amazon Fresh through your browser

api-mappingSkill

Record and analyze API surfaces of web services

app-builderSkill

Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use, or to edit an app they already built here. Do NOT reach for a ui_show dynamic_page to fake an artifact — build a real persistent app here. A one-off diagram, chart, or explainer that just accompanies an answer belongs to the visualize skill (ui_show visual), not an app. NOT for complex, multi-user, or shippable products — those go to a real project folder with a coding agent (see Scope below).

app-controlSkill

Drive a specific named macOS app via raw input bypassing the Accessibility tree

assistant-migrationSkill

Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum primitives. Handles single-source and multi-source migrations with a unified, deduplicated inventory.

chat-complex-documentsSkill

Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready text for search, Q&A, and summarization without building a custom parsing pipeline.

chatgpt-importSkill

Import conversation history from ChatGPT into Vellum