Agent skill
tasknotes
Manage tasks in Obsidian via TaskNotes plugin API. Use when user wants to create tasks, list tasks, query by status or project, update task status, delete tasks, or check what they need to do.
Install this agent skill to your Project
npx add-skill https://github.com/ArtemXTech/personal-os-skills/tree/main/skills/tasknotes
SKILL.md
TaskNotes Skill
Manage Obsidian tasks via the TaskNotes plugin HTTP API.
Requirements
- TaskNotes plugin installed in Obsidian
- Enable HTTP API in TaskNotes settings:
- Open Obsidian Settings → TaskNotes
- Enable "HTTP API" toggle
- Set API port (default: 8080)
- API token: leave empty for no auth, or set a token for security
- Environment variables in
.envfile at vault root (if using auth):If TaskNotes has no auth token set, you don't need aTASKNOTES_API_PORT=8080 TASKNOTES_API_KEY=your_token_here.envfile.
CLI Commands
# List all tasks
uv run scripts/tasks.py list
# List by status (use your configured status values)
uv run scripts/tasks.py list --status "in-progress"
# List by project
uv run scripts/tasks.py list --project "My Project"
# Create task
uv run scripts/tasks.py create "Task title" --project "My Project" --priority high
# Create task with scheduled time
uv run scripts/tasks.py create "Meeting prep" --scheduled "2025-01-15T14:00:00"
# Update task status
uv run scripts/tasks.py update "Tasks/task-file.md" --status done
# Add/update task description
uv run scripts/tasks.py update "Tasks/task-file.md" --details "Additional context here."
# Delete task
uv run scripts/tasks.py delete "Tasks/task-file.md"
# Get available options (statuses, priorities, projects)
uv run scripts/tasks.py options --table
# Human-readable output (add --table)
uv run scripts/tasks.py list --table
Task Properties
Status and Priority values: Configured in your TaskNotes plugin settings. Run options command to see available values:
uv run scripts/tasks.py options --table
Other fields:
projects- Array of project links, e.g.["[[Project Name]]"]contexts- Array like["office", "energy-high"]due- Due date (YYYY-MM-DD)scheduled- Scheduled date/time (YYYY-MM-DD or YYYY-MM-DDTHH:MM:SS)timeEstimate- Minutes (number)tags- Array of tagsdetails- Task description (writes to markdown body, not frontmatter)
API Reference
Base URL: http://localhost:8080/api
| Method | Endpoint | Description |
|---|---|---|
| GET | /tasks | List tasks (supports filters) |
| POST | /tasks | Create task |
| GET | /tasks/{id} | Get single task |
| PUT | /tasks/{id} | Update task |
| DELETE | /tasks/{id} | Delete task |
| GET | /filter-options | Available statuses, priorities, projects |
Query Parameters for GET /tasks
status- Filter by statusproject- Filter by project namepriority- Filter by prioritytag- Filter by tagoverdue- true/falsesort- Sort fieldlimit- Max resultsoffset- Pagination offset
When to Use
- "create a task for X" → create task
- "show my tasks" → list all tasks
- "show in-progress tasks" → list --status in-progress
- "mark X as done" → update task status to done
- "what should I work on" → list tasks by status
Example Workflow
# Morning: Check what to work on
uv run scripts/tasks.py list --status in-progress --table
uv run scripts/tasks.py list --limit 5 --table
# Create task linked to project
uv run scripts/tasks.py create "Finish landing page" \
--project "Website Redesign" \
--priority high
# Complete a task
uv run scripts/tasks.py update "Tasks/finish-landing-page.md" --status done
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
recall
Load context from vault memory. Temporal queries (yesterday, last week, session history) use native JSONL timeline. Topic queries use QMD BM25 search. "recall graph" generates interactive temporal graph of sessions and files. Every recall ends with "One Thing" - the single highest-leverage next action synthesized from results. Use when user says "recall", "what did we work on", "load context about", "remember when we", "prime context", "yesterday", "what was I doing", "last week", "session history", "recall graph", "session graph".
sync-claude-sessions
Sync Claude Code sessions to Obsidian markdown. Export, resume, add notes, close sessions. USE WHEN user says "sync sessions", "export sessions", "resume session", "add session note", "close session", "log session".
granola
Query and sync Granola meetings to Obsidian vault. Use when user mentions Granola, meeting transcripts, or wants to sync meeting notes. Reads from local cache - no API needed.
notebooklm
Import NotebookLM notebooks into your Obsidian vault as linked knowledge graphs. Sources become wikilink-able files, Q&A answers get citations resolved to [[wikilinks]] with passage-level deep links. Use when user says "notebooklm import", "import notebook", "notebooklm ask", "notebooklm sources", or wants to turn NotebookLM research into vault knowledge.
wispr-flow
Analyze Wispr Flow voice dictation data. Stats, search, export, visualizations. Use when user says "dictation history", "word counts", "voice analytics", "how much did I dictate", "search my dictation".
granola
Query and sync Granola meetings to Obsidian vault. Use when user mentions Granola, meeting transcripts, or wants to sync meeting notes. Reads from local cache - no API needed.
Didn't find tool you were looking for?