sanjay3290/outline
Search, read, and manage Outline wiki documents. Use when: (1) searching wiki for documentation, (2) reading wiki pages or articles, (3) listing wiki collections or documents, (4) creating or updating wiki content, (5) exporting documents as markdown. Works with any Outline wiki instance (self-hosted or cloud).
npx skills add https://github.com/sanjay3290/ai-skills --skill outline
Search, read, create, and manage documents in any Outline wiki instance. Works with all AI clients supporting the Agent Skills Standard.
pip install -r requirements.txt cp .env.example .env
# Edit .env with your API key
export OUTLINE_API_KEY=your-api-key-here
# Optional: for self-hosted instances
export OUTLINE_API_URL=https://your-wiki.example.com/api
python3 scripts/outline.py search "deployment guide"
python3 scripts/outline.py search "API documentation" --limit 10
python3 scripts/outline.py search "onboarding" --collection-id <id>
python3 scripts/outline.py read <document-id>
python3 scripts/outline.py read <document-id> --json
python3 scripts/outline.py list-collections
python3 scripts/outline.py list-collections --limit 50
python3 scripts/outline.py list-documents --collection-id <id>
python3 scripts/outline.py get-collection <collection-id>
python3 scripts/outline.py create --title "New Guide" --collection-id <id>
python3 scripts/outline.py create --title "Guide" --collection-id <id> --text "# Content here"
python3 scripts/outline.py create --title "Draft" --collection-id <id> --draft
python3 scripts/outline.py update <document-id> --title "Updated Title"
python3 scripts/outline.py update <document-id> --text "New content"
python3 scripts/outline.py update <document-id> --publish
python3 scripts/outline.py export <document-id>
python3 scripts/outline.py export <document-id> --output doc.md
python3 scripts/outline.py auth-info
Add --json flag to any command for machine-readable output:
python3 scripts/outline.py search "query" --json
python3 scripts/outline.py read <id> --json
| Command | Description | Required Args |
|---------|-------------|---------------|
| search | Full-text search | query |
| read | Get document content | document_id |
| list-collections | List all collections | - |
| list-documents | List docs (optionally in collection) | - |
| get-collection | Get collection details | collection_id |
| create | Create new document | --title, --collection-id |
| update | Update existing document | document_id |
| export | Export as markdown | document_id |
| auth-info | Test API connection | - |
| Variable | Required | Default | Description |
|----------|----------|---------|-------------|
| OUTLINE_API_KEY | Yes | - | Your Outline API token |
| OUTLINE_API_URL | No | https://app.getoutline.com/api | API URL |
| OUTLINE_TIMEOUT | No | 30 | Request timeout (seconds) |
| OUTLINE_VERIFY_SSL | No | true | Set to false to skip SSL verification (for self-hosted instances with self-signed certs) |
| Error | Solution |
|-------|----------|
| API key not configured | Set OUTLINE_API_KEY environment variable |
| Authentication failed | Verify API key is valid and not expired |
| Connection timeout | Check OUTLINE_API_URL and network connectivity |
| SSL certificate error | Set OUTLINE_VERIFY_SSL=false for self-signed certs |
| Document not found | Verify document ID is correct |
| Permission denied | Check API token has required permissions |
auth-info to verify connectionlist-collections to see available collectionssearch or list-documents to find contentread to get full document contentcreate/update to modify wiki contentTake sanjay3290/outline from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip.
Without those the skill loads but fails at the first command.