OpenParable
Skip to content
← Back to skills

Tasks

Productivity
tasks

Tasks is an Agent Skill for productivity published in the TinyAGI/tinyagi repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Manage your assigned tasks on the TinyAGI kanban board — list tasks, update task status, create new tasks, and add or view comments. Use when: you receive a message with a [task:ID] tag and need to mark it done, you want to check your task queue, you want to propose new work, or you need to add a comment/update to a task. Triggers: 'update task', 'mark task done', 'list my tasks', 'create task', 'check tasks', 'comment on task', 'task comments', or any message containing [task:ID].

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/TinyAGI/tinyagi/blob/HEAD/.agents/skills/tasks/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/tasks, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Tasks

Manage tasks on the TinyAGI kanban board via the REST API.

Automatic task completion

When you receive a message containing a [task:TASK_ID] tag, it means this work was dispatched from the task board. After you finish the work:

<skill_dir>/scripts/tasks.sh update TASK_ID --status done

Replace TASK_ID with the ID from the [task:...] tag in the message.

You should also leave a comment on the task to summarize what you did:

<skill_dir>/scripts/tasks.sh comment TASK_ID --content "Completed: brief summary of what was done"

Commands

List tasks

# List all tasks
<skill_dir>/scripts/tasks.sh list

# List only your own tasks (uses TINYAGI_AGENT_ID env var)
<skill_dir>/scripts/tasks.sh list --mine

# List tasks with a specific status
<skill_dir>/scripts/tasks.sh list --status in_progress

# Combine filters
<skill_dir>/scripts/tasks.sh list --mine --status in_progress

Update a task

# Move task to done
<skill_dir>/scripts/tasks.sh update TASK_ID --status done

# Move task to review
<skill_dir>/scripts/tasks.sh update TASK_ID --status review

Valid statuses: backlog, in_progress, review, done

Create a task

New tasks are always created in backlog status.

# Create a task assigned to yourself
<skill_dir>/scripts/tasks.sh create --title "Refactor auth module"

# Create with description
<skill_dir>/scripts/tasks.sh create --title "Fix login bug" --description "Login fails on mobile Safari"

# Create and assign to another agent
<skill_dir>/scripts/tasks.sh create --title "Review PR #42" --assignee reviewer --assignee-type agent

Add a comment to a task

# Add a comment to a task (author defaults to your agent ID)
<skill_dir>/scripts/tasks.sh comment TASK_ID --content "Started working on this, found the root cause in auth.ts"

# Use comments to provide progress updates, share findings, or summarize completed work
<skill_dir>/scripts/tasks.sh comment TASK_ID --content "Completed: refactored auth module, PR #55 is up for review"

List comments on a task

# View all comments on a task
<skill_dir>/scripts/tasks.sh comments TASK_ID

Environment

  • TINYAGI_AGENT_ID — your agent ID (set automatically, used by --mine and as default comment author)
  • TINYAGI_API_PORT — API port (default: 3777)