zhongwei/gh-rawe-claude-agent-orchestrator-plugins-document-sync
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit

Browse Source
This commit is contained in:
Zhongwei Li
2025-11-30 08:49:56 +08:00
commit a250e458a9
14 changed files with 1221 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

380
skills/document-sync/README.md Normal file
View File

@@ -0,0 +1,380 @@
# Document Sync CLI Commands
Command-line tools for interacting with the Document Sync Server. These UV-based scripts enable Claude Code sessions to store, retrieve, query, inspect, read, and delete documents with metadata and tags.
## Prerequisites
- **Python 3.11+** - Required for script dependencies
- **UV package manager** - For running scripts with automatic dependency management
- **Document Server** - Must be running (see `../../document-server/README.md`)
## Available Commands
All commands output JSON for easy parsing and integration with Claude Code (except `doc-read`, which outputs raw text).
### doc-push - Upload Documents
Upload a document to the server with optional tags and description.
```bash
uv run /path/to/doc-push <file> [OPTIONS]
```
**Arguments:**
- `file` - Path to the file to upload (required)
**Options:**
- `--name TEXT` - Custom name for the document (defaults to filename)
- `--tags TEXT` - Comma-separated tags (e.g., "python,api,docs")
- `--description TEXT` - Document description
**Example:**
```bash
uv run doc-push architecture.md --tags "design,architecture" --description "System architecture document"
```
**Output:**
```json
{
"id": "doc_abc123...",
"filename": "architecture.md",
"content_type": "text/markdown",
"size_bytes": 2048,
"created_at": "2025-11-23T00:00:00",
"updated_at": "2025-11-23T00:00:00",
"tags": ["design", "architecture"],
"metadata": {"description": "System architecture document"},
"url": "http://localhost:8766/documents/doc_abc123..."
}
```
### doc-query - Search Documents
Query documents by name pattern and/or tags.
```bash
uv run /path/to/doc-query [OPTIONS]
```
**Options:**
- `--name TEXT` - Filter by filename pattern (partial match)
- `--tags TEXT` - Comma-separated tags with AND logic (document must have ALL tags)
- `--limit INTEGER` - Maximum number of results
**Examples:**
```bash
# List all documents
uv run doc-query
# Find documents with specific tags (AND logic)
uv run doc-query --tags "python,tutorial"
# Filter by name pattern
uv run doc-query --name "architecture"
# Combine filters
uv run doc-query --name "guide" --tags "python" --limit 5
```
**Tag AND Logic:** When querying with multiple tags (e.g., `--tags "python,api"`), only documents that have **both** tags will be returned.
**Output:**
```json
[
{
"id": "doc_abc123...",
"filename": "python-guide.md",
"content_type": "text/markdown",
"size_bytes": 1024,
"created_at": "2025-11-23T00:00:00",
"updated_at": "2025-11-23T00:00:00",
"tags": ["python", "tutorial"],
"metadata": {},
"url": "http://localhost:8766/documents/doc_abc123..."
}
]
```
### doc-info - Get Document Metadata
Retrieve metadata for a specific document without downloading the file.
```bash
uv run /path/to/doc-info <document_id>
```
**Arguments:**
- `document_id` - The document's unique identifier (required)
**Example:**
```bash
uv run doc-info doc_abc123...
```
**Output:**
```json
{
"id": "doc_abc123...",
"filename": "architecture.md",
"content_type": "text/markdown",
"size_bytes": 2048,
"created_at": "2025-11-23T00:00:00",
"updated_at": "2025-11-23T00:00:00",
"tags": ["design", "architecture"],
"metadata": {"description": "System architecture document"},
"url": "http://localhost:8766/documents/doc_abc123..."
}
```
**Use Case:** Check document metadata (file size, MIME type, tags) before downloading. The `url` field provides a direct link to retrieve the document, mostly interesting for the user or system having no access to the skill itself.
### doc-read - Read Text Documents
Read text document content directly to stdout without downloading to file.
```bash
uv run /path/to/doc-read <document_id>
```
**Arguments:**
- `document_id` - The document's unique identifier (required)
**Supported File Types:**
- Text files (`text/*`)
- JSON files (`application/json`)
- XML files (`application/xml`)
**Examples:**
```bash
# Output content to terminal
uv run doc-read doc_abc123...
# Pipe to grep
uv run doc-read doc_abc123... | grep "search term"
# Pipe to jq (for JSON documents)
uv run doc-read doc_abc123... | jq '.field'
# Save to file
uv run doc-read doc_abc123... > output.txt
```
**Output:** Raw text content (no JSON wrapper)
**Error (for non-text files):**
```json
{"error": "Cannot read non-text file (MIME type: image/png). Use doc-pull to download binary files."}
```
**Use Case:** Quick inspection of text files, piping content to other tools, processing documents in scripts without creating temporary files.
### doc-pull - Download Documents
Download a document by its ID.
```bash
uv run /path/to/doc-pull <document_id> [OPTIONS]
```
**Arguments:**
- `document_id` - The document's unique identifier (required)
**Options:**
- `--output PATH` or `-o PATH` - Output file path (defaults to original filename)
**Examples:**
```bash
# Download with original filename
uv run doc-pull doc_abc123...
# Download to specific path
uv run doc-pull doc_abc123... --output ~/downloads/my-document.md
```
**Output:**
```json
{
"success": true,
"document_id": "doc_abc123...",
"filename": "/path/to/output.md",
"size_bytes": 2048
}
```
### doc-delete - Remove Documents
Delete a document from the server.
```bash
uv run /path/to/doc-delete <document_id>
```
**Arguments:**
- `document_id` - The document's unique identifier (required)
**Example:**
```bash
uv run doc-delete doc_abc123...
```
**Output:**
```json
{
"success": true,
"message": "Document doc_abc123... deleted successfully",
"document_id": "doc_abc123..."
}
```
## Configuration
Commands connect to the document server using environment variables:
### DOC_SYNC_HOST
- **Description:** Server hostname or IP address
- **Default:** `localhost`
- **Example:**
```bash
DOC_SYNC_HOST=192.168.1.100 uv run doc-push file.txt
```
### DOC_SYNC_PORT
- **Description:** Server port number
- **Default:** `8766`
- **Example:**
```bash
DOC_SYNC_PORT=9000 uv run doc-query
```
### DOC_SYNC_SCHEME
- **Description:** HTTP scheme (http or https)
- **Default:** `http`
- **Example:**
```bash
DOC_SYNC_SCHEME=https uv run doc-pull doc_abc123...
```
**Combined Example:**
```bash
DOC_SYNC_HOST=example.com DOC_SYNC_PORT=443 DOC_SYNC_SCHEME=https \
uv run doc-push document.pdf --tags "report"
```
## Common Workflows
### Store and Retrieve a Document
```bash
# 1. Upload a document
uv run doc-push specs.md --tags "api,specification"
# Output includes the document ID: "doc_abc123..."
# 2. Later, query for it
uv run doc-query --tags "api,specification"
# 3. Check metadata before downloading
uv run doc-info doc_abc123...
# 4. Read content (for text files)
uv run doc-read doc_abc123... | less
# 5. Download it
uv run doc-pull doc_abc123... --output specs-copy.md
```
### Share Documents Across Sessions
```bash
# Session 1: Store architecture document
uv run doc-push architecture.md --tags "design,mvp" \
--description "MVP architecture decisions"
# Session 2: Query and retrieve
uv run doc-query --tags "design,mvp"
uv run doc-info doc_abc123... # Check metadata
uv run doc-read doc_abc123... | head -20 # Preview first 20 lines
uv run doc-pull doc_abc123... --output architecture.md
```
### Manage Document Repository
```bash
# List all documents
uv run doc-query
# Find specific category
uv run doc-query --tags "deprecated"
# Remove old documents
uv run doc-delete doc_old123...
```
## Error Handling
All commands output errors to stderr in JSON format and exit with code 1 on failure.
**Common Errors:**
**File not found:**
```json
{"error": "File not found: /path/to/file.txt"}
```
**Document not found:**
```json
{"error": "Document not found: doc_invalid123"}
```
**Non-text file (doc-read only):**
```json
{"error": "Cannot read non-text file (MIME type: image/png). Use doc-pull to download binary files."}
```
**Network error:**
```json
{"error": "Network error: Connection refused"}
```
**Server not running:**
```json
{"error": "Network error: [Errno 61] Connection refused"}
```
## Technical Details
### Script Architecture
- **UV Scripts:** Use PEP 723 inline dependency metadata
- **Shebang:** `#!/usr/bin/env -S uv run --script`
- **Dependencies:** Automatically installed by UV (httpx, typer)
- **Shared Library:** `lib/config.py` and `lib/client.py` provide reusable components
### Why UV?
- **Zero installation:** Scripts run with dependencies automatically installed
- **Reproducible:** PEP 723 metadata ensures consistent dependency versions
- **Fast:** UV's Rust-based resolver is extremely fast
- **Portable:** Scripts work across different environments
## Troubleshooting
### "Connection refused" error
The document server isn't running. Start it first:
```bash
cd ../../document-server
uv run python -m src.main
```
### "No such file or directory" when running commands
Use full paths or navigate to the commands directory:
```bash
# Use full path
uv run /full/path/to/doc-push file.txt
# Or navigate to commands directory
cd /path/to/commands
uv run doc-push file.txt
```
### Commands run slowly the first time
UV is installing dependencies. Subsequent runs will be fast as dependencies are cached.
## Development
See `../../docs/implementation/03-IMPLEMENTATION-CHECKLIST.md` for implementation details and design decisions.

143
skills/document-sync/SKILL.md Normal file
View File

@@ -0,0 +1,143 @@
---
name: document-sync
description: Document management system for storing, querying, and retrieving documents across Claude Code sessions. Use this to maintain knowledge bases, share documents between agent. Whenever you encounter a <document id=*> in a session, use this skill to retrieve its content.
---
# Document Sync Skill
## What & When
**What**: Commands for uploading, downloading, querying, and deleting documents with metadata and tags through a centralized document server.
**When to use**:
- Store important documents for retrieval in future sessions
- Build a knowledge base of project documentation
- Share architecture, API specs, or design documents across different work sessions
- Query documents by tags to find relevant information
**Key Benefits**:
- Cross-session persistence
- Tag-based organization with AND logic
- Simple JSON output
---
## Quick Reference
**CRITICAL**: Always use absolute paths - NEVER use `cd`:
### `doc-push` - Upload Documents
```bash
uv run <skill-root>/commands/doc-push <file> [--tags TEXT] [--description TEXT]
# Example: uv run <skill-root>/commands/doc-push specs.md --tags "api,v2"
```
**Use when**: Store a document for future reference.
### `doc-query` - Search Documents
```bash
uv run <skill-root>/commands/doc-query [--tags TEXT] [--name TEXT]
# Example: uv run <skill-root>/commands/doc-query --tags "api,v2"
```
**Use when**: Find documents by tags (AND logic) or name patterns.
### `doc-info` - Get Document Metadata
```bash
uv run <skill-root>/commands/doc-info <document-id>
# Example: uv run <skill-root>/commands/doc-info doc_abc123
```
**Use when**: View metadata for a specific document without downloading it.
### `doc-read` - Read Text Documents
```bash
uv run <skill-root>/commands/doc-read <document-id>
# Example: uv run <skill-root>/commands/doc-read doc_abc123
```
**Use when**: Output text document content directly to stdout (text files only).
### `doc-pull` - Download Documents
```bash
uv run <skill-root>/commands/doc-pull <document-id> [-o PATH]
# Example: uv run <skill-root>/commands/doc-pull doc_abc123 -o specs.md
```
**Use when**: Retrieve a document by its ID.
### `doc-delete` - Remove Documents
```bash
uv run <skill-root>/commands/doc-delete <document-id>
# Example: uv run <skill-root>/commands/doc-delete doc_abc123
```
**Use when**: Permanently remove a document.
---
## Typical Workflows
### Store and Retrieve
```bash
# Upload with tags
uv run <skill-root>/commands/doc-push specs.md --tags "api,v2"
# Find it later
uv run <skill-root>/commands/doc-query --tags "api,v2"
# Download it
uv run <skill-root>/commands/doc-pull doc_abc123
```
### Build Knowledge Base
```bash
# Upload multiple documents with consistent tags
uv run <skill-root>/commands/doc-push architecture.md --tags "design,mvp"
uv run <skill-root>/commands/doc-push api-spec.md --tags "api,mvp"
# Query by project phase
uv run <skill-root>/commands/doc-query --tags "mvp"
```
---
## Key Concepts
### Tag AND Logic
**IMPORTANT**: Multiple tags means ALL must match:
- `--tags "python,api"` → Document must have BOTH tags
- `--tags "v2,design,spec"` → Document must have ALL THREE tags
### Output Format
All commands output JSON. Save document IDs from upload for later retrieval/deletion.
---
## Notes for AI Assistants
1. **Tag AND logic** - Multiple tags = ALL must match
2. **Save document IDs** - From upload output for future operations
3. **Check server running** - Handle connection errors gracefully
4. **Parse JSON output** - All commands return JSON
5. **Tags are lowercase** - Use consistent tag naming (`python` not `Python`)
---
## Quick Decision Tree
**Store document?** → `doc-push <file> --tags "tag1,tag2"`
**Find documents?** → `doc-query --tags "tag1,tag2"` (AND logic)
**Check metadata?** → `doc-info <doc-id>` (metadata only)
**Read text file?** → `doc-read <doc-id>` (text files to stdout)
**Download document?** → `doc-pull <doc-id>` (ID from query)
**Remove document?** → `doc-delete <doc-id>` (permanent)
**List all?** → `doc-query` (no args)
---
## Additional Resources
- **Detailed Command Reference**: See `references/COMMANDS.md`
- **Configuration Options**: See `references/CONFIGURATION.md`
- **Error Handling**: See `references/TROUBLESHOOTING.md`

48
skills/document-sync/commands/doc-delete Executable file
View File

@@ -0,0 +1,48 @@
#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.11"
# dependencies = [
# "httpx",
# "typer",
# ]
# ///
"""Delete a document from the document sync server."""
import typer
from pathlib import Path
import json
import sys
# Add lib directory to path for imports
sys.path.insert(0, str(Path(__file__).parent / "lib"))
from config import Config
from client import DocumentClient
app = typer.Typer(add_completion=False)
@app.command()
def main(
document_id: str = typer.Argument(..., help="ID of the document to delete"),
):
"""Delete a document from the document sync server."""
try:
# Create client and delete document
config = Config()
client = DocumentClient(config)
result = client.delete_document(document_id)
# Output success result as JSON
print(json.dumps(result, indent=2))
except Exception as e:
# Output error as JSON to stderr
error = {"error": str(e)}
print(json.dumps(error), file=sys.stderr)
raise typer.Exit(1)
if __name__ == "__main__":
app()

48
skills/document-sync/commands/doc-info Executable file
View File

@@ -0,0 +1,48 @@
#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.11"
# dependencies = [
# "httpx",
# "typer",
# ]
# ///
"""Retrieve metadata for a document from the document sync server."""
import typer
from pathlib import Path
import json
import sys
# Add lib directory to path for imports
sys.path.insert(0, str(Path(__file__).parent / "lib"))
from config import Config
from client import DocumentClient
app = typer.Typer(add_completion=False)
@app.command()
def main(
document_id: str = typer.Argument(..., help="Document ID to retrieve metadata for"),
):
"""Retrieve metadata for a document without downloading the file."""
try:
# Create client and get document info
config = Config()
client = DocumentClient(config)
result = client.get_document_info(document_id)
# Output metadata as JSON
print(json.dumps(result, indent=2))
except Exception as e:
# Output error as JSON to stderr
error = {"error": str(e)}
print(json.dumps(error), file=sys.stderr)
raise typer.Exit(1)
if __name__ == "__main__":
app()

61
skills/document-sync/commands/doc-pull Executable file
View File

@@ -0,0 +1,61 @@
#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.11"
# dependencies = [
# "httpx",
# "typer",
# ]
# ///
"""Download a document from the document sync server."""
import typer
from pathlib import Path
import json
import sys
# Add lib directory to path for imports
sys.path.insert(0, str(Path(__file__).parent / "lib"))
from config import Config
from client import DocumentClient
app = typer.Typer(add_completion=False)
@app.command()
def main(
document_id: str = typer.Argument(..., help="ID of the document to download"),
output: str = typer.Option(None, "--output", "-o", help="Output file path (defaults to original filename)"),
):
"""Download a document from the document sync server."""
try:
# Create client and pull document
config = Config()
client = DocumentClient(config)
content, filename = client.pull_document(document_id)
# Determine output path
output_path = Path(output) if output else Path(filename)
# Write content to file
output_path.write_bytes(content)
# Output success message as JSON
result = {
"success": True,
"document_id": document_id,
"filename": str(output_path),
"size_bytes": len(content)
}
print(json.dumps(result, indent=2))
except Exception as e:
# Output error as JSON to stderr
error = {"error": str(e)}
print(json.dumps(error), file=sys.stderr)
raise typer.Exit(1)
if __name__ == "__main__":
app()

68
skills/document-sync/commands/doc-push Executable file
View File

@@ -0,0 +1,68 @@
#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.11"
# dependencies = [
# "httpx",
# "typer",
# ]
# ///
"""Upload a document to the document sync server."""
import typer
from pathlib import Path
import json
import sys
# Add lib directory to path for imports
sys.path.insert(0, str(Path(__file__).parent / "lib"))
from config import Config
from client import DocumentClient
app = typer.Typer(add_completion=False)
@app.command()
def main(
file_path: str = typer.Argument(..., help="Path to the file to upload"),
name: str = typer.Option(None, "--name", help="Custom name for the document (defaults to filename)"),
tags: str = typer.Option(None, "--tags", help="Comma-separated list of tags"),
description: str = typer.Option(None, "--description", help="Description of the document"),
):
"""Upload a document to the document sync server."""
try:
# Validate file exists
path = Path(file_path)
if not path.exists():
error = {"error": f"File not found: {file_path}"}
print(json.dumps(error), file=sys.stderr)
raise typer.Exit(1)
# Parse tags from comma-separated string
parsed_tags = None
if tags:
parsed_tags = [tag.strip() for tag in tags.split(",") if tag.strip()]
# Create client and push document
config = Config()
client = DocumentClient(config)
result = client.push_document(
file_path=path,
name=name,
tags=parsed_tags,
description=description
)
# Output success result as JSON
print(json.dumps(result, indent=2))
except Exception as e:
# Output error as JSON to stderr
error = {"error": str(e)}
print(json.dumps(error), file=sys.stderr)
raise typer.Exit(1)
if __name__ == "__main__":
app()

59
skills/document-sync/commands/doc-query Executable file
View File

@@ -0,0 +1,59 @@
#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.11"
# dependencies = [
# "httpx",
# "typer",
# ]
# ///
"""Query documents from the document sync server."""
import typer
from pathlib import Path
import json
import sys
# Add lib directory to path for imports
sys.path.insert(0, str(Path(__file__).parent / "lib"))
from config import Config
from client import DocumentClient
app = typer.Typer(add_completion=False)
@app.command()
def main(
name: str = typer.Option(None, "--name", help="Filter by filename pattern"),
tags: str = typer.Option(None, "--tags", help="Comma-separated list of tags (AND logic)"),
limit: int = typer.Option(None, "--limit", help="Maximum number of results"),
):
"""Query documents from the document sync server."""
try:
# Parse tags from comma-separated string
parsed_tags = None
if tags:
parsed_tags = [tag.strip() for tag in tags.split(",") if tag.strip()]
# Create client and query documents
config = Config()
client = DocumentClient(config)
results = client.query_documents(
name=name,
tags=parsed_tags,
limit=limit
)
# Output results as JSON array
print(json.dumps(results, indent=2))
except Exception as e:
# Output error as JSON to stderr
error = {"error": str(e)}
print(json.dumps(error), file=sys.stderr)
raise typer.Exit(1)
if __name__ == "__main__":
app()

48
skills/document-sync/commands/doc-read Executable file
View File

@@ -0,0 +1,48 @@
#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.11"
# dependencies = [
# "httpx",
# "typer",
# ]
# ///
"""Read text document content from the document sync server."""
import typer
from pathlib import Path
import json
import sys
# Add lib directory to path for imports
sys.path.insert(0, str(Path(__file__).parent / "lib"))
from config import Config
from client import DocumentClient
app = typer.Typer(add_completion=False)
@app.command()
def main(
document_id: str = typer.Argument(..., help="Document ID to read content from"),
):
"""Read text document content directly to stdout (text files only)."""
try:
# Create client and read document
config = Config()
client = DocumentClient(config)
content = client.read_document(document_id)
# Output raw content to stdout (no JSON wrapper)
print(content, end="")
except Exception as e:
# Output error as JSON to stderr
error = {"error": str(e)}
print(json.dumps(error), file=sys.stderr)
raise typer.Exit(1)
if __name__ == "__main__":
app()

223
skills/document-sync/references/COMMANDS.md Normal file
View File

@@ -0,0 +1,223 @@
# Command Reference
## doc-push
```bash
uv run commands/doc-push <file> [--name TEXT] [--tags TEXT] [--description TEXT]
```
**Arguments**: `<file>` - File path to upload
**Options**:
- `--name TEXT` - Custom name (default: filename)
- `--tags TEXT` - Comma-separated tags
- `--description TEXT` - Description
**Examples**:
```bash
uv run commands/doc-push specs.md --tags "api,v2"
uv run commands/doc-push arch.md --tags "design,mvp" --description "MVP architecture"
```
**Output**:
```json
{
"id": "doc_abc123def456...",
"filename": "specs.md",
"content_type": "text/markdown",
"size_bytes": 2048,
"created_at": "2025-11-23T00:00:00",
"updated_at": "2025-11-23T00:00:00",
"tags": ["api", "v2"],
"metadata": {"description": "Specification document for API v2"},
"url": "http://localhost:8766/documents/doc_abc123def456..."
}
```
**Note**: Save the `id` field for pull/delete operations.
---
## doc-query
```bash
uv run commands/doc-query [--name TEXT] [--tags TEXT] [--limit INTEGER]
```
**Options**:
- `--name TEXT` - Filter by filename pattern
- `--tags TEXT` - Filter by tags (AND logic - ALL tags must match)
- `--limit INTEGER` - Max results
**Examples**:
```bash
uv run commands/doc-query # List all
uv run commands/doc-query --tags "api,v2" # Both tags required (AND)
uv run commands/doc-query --name "spec" # Name contains "spec"
```
**Output**:
```json
[
{
"id": "doc_abc123...",
"filename": "api-spec.md",
"content_type": "text/markdown",
"size_bytes": 1024,
"created_at": "2025-11-23T00:00:00",
"updated_at": "2025-11-23T00:00:00",
"tags": ["api", "v2"],
"metadata": {},
"url": "http://localhost:8766/documents/doc_abc123..."
}
]
```
**Important**: Multiple tags = ALL must match (AND logic, not OR)
---
## doc-info
```bash
uv run commands/doc-info <document-id>
```
**Arguments**: `<document-id>` - Document ID to retrieve metadata for
**Examples**:
```bash
uv run commands/doc-info doc_abc123...
```
**Output**:
```json
{
"id": "doc_abc123...",
"filename": "api-spec.md",
"content_type": "text/markdown",
"size_bytes": 1024,
"created_at": "2025-11-23T00:00:00",
"updated_at": "2025-11-23T00:00:00",
"tags": ["api", "v2"],
"metadata": {"description": "API specification"},
"url": "http://localhost:8766/documents/doc_abc123..."
}
```
**Use Case**: View document metadata without downloading the file. The `url` field provides a direct link to retrieve the document. Useful to provide this url to a user if you don't want to download the file yourself.
**Error Output** (stderr):
```json
{"error": "Document not found: doc_abc123..."}
```
---
## doc-read
```bash
uv run commands/doc-read <document-id>
```
**Arguments**: `<document-id>` - Document ID to read content from
**Examples**:
```bash
# Direct output
uv run commands/doc-read doc_abc123...
# Pipe to grep
uv run commands/doc-read doc_abc123... | grep "pattern"
# Pipe to wc
uv run commands/doc-read doc_abc123... | wc -l
# Save to file
uv run commands/doc-read doc_abc123... > output.txt
```
**Output**: Raw text content to stdout (no JSON wrapper)
**Supported MIME Types**:
- `text/*` (text/plain, text/markdown, text/html, etc.)
- `application/json`
- `application/xml`
**Error Output** (stderr):
```json
{"error": "Cannot read non-text file (MIME type: image/png). Use doc-pull to download binary files."}
{"error": "File is not valid UTF-8 text. Use doc-pull to download."}
{"error": "Document not found: doc_abc123..."}
```
**Use Case**: Read text document content directly without downloading to file system. Ideal for:
- Piping content to other tools (grep, awk, jq, etc.)
- Quick inspection of text files
- Processing document content in scripts
**Limitations**:
- Text files only (binary files will error)
- UTF-8 encoding only
- For binary files or non-UTF-8 content, use `doc-pull` instead
---
## doc-pull
```bash
uv run commands/doc-pull <document-id> [--output PATH | -o PATH]
```
**Arguments**: `<document-id>` - Document ID from query results
**Options**: `--output PATH` or `-o PATH` - Output path (default: original filename)
**Examples**:
```bash
uv run commands/doc-pull doc_abc123...
uv run commands/doc-pull doc_abc123... -o custom-name.md
```
**Output**:
```json
{
"success": true,
"document_id": "doc_abc123...",
"filename": "/absolute/path/to/output.md",
"size_bytes": 2048
}
```
---
## doc-delete
```bash
uv run commands/doc-delete <document-id>
```
**Arguments**: `<document-id>` - Document ID from query results
**Example**:
```bash
uv run commands/doc-delete doc_abc123...
```
**Output**:
```json
{
"success": true,
"message": "Document doc_abc123... deleted successfully",
"document_id": "doc_abc123..."
}
```
**Warning**: Permanent deletion - cannot be undone.
---
## Exit Codes
- `0` - Success
- `1` - Error (JSON error in stderr)

14
skills/document-sync/references/CONFIGURATION.md Normal file
View File

@@ -0,0 +1,14 @@
# Configuration
## Environment Variables
- `DOC_SYNC_HOST` - Server hostname (default: `localhost`)
- `DOC_SYNC_PORT` - Server port (default: `8766`)
- `DOC_SYNC_SCHEME` - http or https (default: `http`)
## Example (only when overriding defaults is needed!!!)
```bash
DOC_SYNC_HOST=example.com DOC_SYNC_PORT=443 DOC_SYNC_SCHEME=https \
uv run commands/doc-push file.txt
```

21
skills/document-sync/references/TROUBLESHOOTING.md Normal file
View File

@@ -0,0 +1,21 @@
# Troubleshooting
## Common Errors
### Connection Refused
```json
{"error": "Network error: Connection refused"}
```
**Fix**: Start document server in the correct folder document-server with: (`docker-compose up -d`)
### File Not Found
```json
{"error": "File not found: /path/to/file"}
```
**Fix**: Check file path is correct
### Document Not Found
```json
{"error": "Document not found: doc_xxx"}
```
**Fix**: Run `doc-query` to find correct document ID