cli-jaw 0.1.0

package/skills_ref/postgres/scripts/query.py

@@ -0,0 +1,262 @@
+#!/usr/bin/env python3
+"""
+Read-only PostgreSQL query executor.
+Connects to configured databases and executes SELECT queries only.
+"""
+
+import json
+import os
+import re
+import stat
+import sys
+import argparse
+from pathlib import Path
+from typing import Optional
+
+try:
+    import psycopg2
+except ImportError:
+    print("Error: psycopg2 not installed. Run: pip install psycopg2-binary")
+    sys.exit(1)
+
+# Constants
+SCRIPT_DIR = Path(__file__).parent.parent
+CONFIG_LOCATIONS = [
+    SCRIPT_DIR / "connections.json",
+    Path.home() / ".config" / "claude" / "postgres-connections.json",
+]
+MAX_ROWS = 10000
+MAX_COLUMN_WIDTH = 100
+QUERY_TIMEOUT_MS = 30000
+CONNECTION_TIMEOUT_SEC = 10
+NULL_DISPLAY = "<NULL>"
+
+
+def is_read_only(query: str) -> bool:
+    """Basic client-side check. Primary protection is readonly=True session."""
+    query_upper = query.upper().strip()
+    safe_starts = ('SELECT', 'SHOW', 'DESCRIBE', 'EXPLAIN', 'WITH', '\\D')
+    return any(query_upper.startswith(cmd) for cmd in safe_starts)
+
+
+def validate_single_statement(query: str) -> bool:
+    """Check query contains only one statement."""
+    # Remove trailing semicolon and whitespace, then check for remaining semicolons
+    clean = query.rstrip().rstrip(';')
+    return ';' not in clean
+
+
+def validate_config_permissions(path: Path) -> None:
+    """Warn if config file has insecure permissions (Unix only)."""
+    if os.name != 'nt':  # Skip on Windows
+        mode = path.stat().st_mode
+        if bool(mode & stat.S_IRWXG) or bool(mode & stat.S_IRWXO):
+            print(f"WARNING: {path} has insecure permissions!")
+            print(f"Config contains credentials. Run: chmod 600 {path}")
+
+
+def validate_db_config(db: dict) -> None:
+    """Validate required fields exist in database config."""
+    required = ['name', 'host', 'database', 'user', 'password']
+    missing = [f for f in required if f not in db]
+    if missing:
+        print(f"Error: Database config missing fields: {', '.join(missing)}")
+        sys.exit(1)
+
+
+def find_config() -> Optional[Path]:
+    """Find config file in supported locations."""
+    for path in CONFIG_LOCATIONS:
+        if path.exists():
+            return path
+    return None
+
+
+def load_config(config_path: Optional[Path] = None) -> dict:
+    """Load database connections from JSON config."""
+    path = config_path or find_config()
+    if not path:
+        print("Config not found. Searched:")
+        for loc in CONFIG_LOCATIONS:
+            print(f"  - {loc}")
+        print("\nCreate connections.json with format:")
+        print(json.dumps({
+            "databases": [{
+                "name": "mydb",
+                "description": "Description of database contents",
+                "host": "localhost",
+                "port": 5432,
+                "database": "mydb",
+                "user": "user",
+                "password": "password",
+                "sslmode": "prefer"
+            }]
+        }, indent=2))
+        sys.exit(1)
+
+    validate_config_permissions(path)
+
+    with open(path) as f:
+        return json.load(f)
+
+
+def list_databases(config: dict) -> None:
+    """List all configured databases."""
+    print("Configured databases:\n")
+    for db in config.get("databases", []):
+        validate_db_config(db)
+        print(f"  [{db['name']}]")
+        print(f"    Host: {db['host']}:{db.get('port', 5432)}")
+        print(f"    Database: {db['database']}")
+        print(f"    Description: {db.get('description', 'No description')}")
+        print()
+
+
+def execute_query(db_config: dict, query: str, limit: Optional[int] = None) -> None:
+    """Execute a read-only query against the specified database."""
+    if not is_read_only(query):
+        print("Error: Only read-only queries (SELECT, SHOW, EXPLAIN) are allowed.")
+        sys.exit(1)
+
+    if not validate_single_statement(query):
+        print("Error: Multiple statements not allowed. Execute queries separately.")
+        sys.exit(1)
+
+    # Apply limit using regex to avoid false positives from string content
+    if limit and not re.search(r'\bLIMIT\s+\d+', query, re.IGNORECASE):
+        query = f"{query.rstrip(';')} LIMIT {limit}"
+
+    conn = None
+    try:
+        conn = psycopg2.connect(
+            host=db_config['host'],
+            port=db_config.get('port', 5432),
+            database=db_config['database'],
+            user=db_config['user'],
+            password=db_config['password'],
+            sslmode=db_config.get('sslmode', 'prefer'),
+            connect_timeout=CONNECTION_TIMEOUT_SEC,
+            options=f'-c statement_timeout={QUERY_TIMEOUT_MS}'
+        )
+        # Primary safety: readonly session prevents any write operations
+        conn.set_session(readonly=True, autocommit=True)
+
+        with conn.cursor() as cur:
+            cur.execute(query)
+            if cur.description:
+                columns = [desc[0] for desc in cur.description]
+                rows = cur.fetchmany(MAX_ROWS)
+                truncated = len(rows) == MAX_ROWS
+
+                # Calculate column widths with cap
+                widths = [min(len(col), MAX_COLUMN_WIDTH) for col in columns]
+                for row in rows:
+                    for i, val in enumerate(row):
+                        val_str = str(val) if val is not None else NULL_DISPLAY
+                        widths[i] = min(max(widths[i], len(val_str)), MAX_COLUMN_WIDTH)
+
+                # Print header
+                header = " | ".join(col[:MAX_COLUMN_WIDTH].ljust(widths[i]) for i, col in enumerate(columns))
+                print(header)
+                print("-" * len(header))
+
+                # Print rows
+                for row in rows:
+                    cells = []
+                    for i, val in enumerate(row):
+                        val_str = str(val) if val is not None else NULL_DISPLAY
+                        if len(val_str) > MAX_COLUMN_WIDTH:
+                            val_str = val_str[:MAX_COLUMN_WIDTH-3] + "..."
+                        cells.append(val_str.ljust(widths[i]))
+                    print(" | ".join(cells))
+
+                msg = f"\n({len(rows)} rows)"
+                if truncated:
+                    msg += f" [truncated at {MAX_ROWS}]"
+                print(msg)
+            else:
+                print("Query executed (no result set returned)")
+
+    except psycopg2.Error as e:
+        error_msg = str(e)
+        # Sanitize to avoid leaking credentials
+        if 'password' in error_msg.lower() or 'authentication' in error_msg.lower():
+            error_msg = "Authentication failed. Check credentials in connections.json"
+        print(f"Database error: {error_msg}")
+        sys.exit(1)
+    finally:
+        if conn:
+            conn.close()
+
+
+def find_database(config: dict, name: str) -> dict:
+    """Find database config by name (case-insensitive)."""
+    for db in config.get("databases", []):
+        if db.get('name', '').lower() == name.lower():
+            validate_db_config(db)
+            return db
+    available = [db.get('name', 'unnamed') for db in config.get("databases", [])]
+    print(f"Database '{name}' not found.")
+    print(f"Available: {', '.join(available)}")
+    sys.exit(1)
+
+
+def main() -> None:
+    """Main entry point."""
+    parser = argparse.ArgumentParser(
+        description="Execute read-only PostgreSQL queries",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  %(prog)s --list
+  %(prog)s --db mydb --tables
+  %(prog)s --db mydb --query "SELECT * FROM users" --limit 100
+        """
+    )
+    parser.add_argument("--config", "-c", type=Path, help="Path to config JSON")
+    parser.add_argument("--db", "-d", help="Database name to query")
+    parser.add_argument("--query", "-q", help="SQL query to execute")
+    parser.add_argument("--limit", "-l", type=int, help="Limit rows returned")
+    parser.add_argument("--list", action="store_true", help="List configured databases")
+    parser.add_argument("--schema", "-s", action="store_true", help="Show database schema")
+    parser.add_argument("--tables", "-t", action="store_true", help="List tables")
+
+    args = parser.parse_args()
+    config = load_config(args.config)
+
+    if args.list:
+        list_databases(config)
+        return
+
+    if not args.db:
+        print("Error: --db required. Use --list to see available databases.")
+        sys.exit(1)
+
+    db_config = find_database(config, args.db)
+
+    if args.tables:
+        query = """
+            SELECT table_schema, table_name, table_type
+            FROM information_schema.tables
+            WHERE table_schema NOT IN ('pg_catalog', 'information_schema')
+            ORDER BY table_schema, table_name
+        """
+        execute_query(db_config, query, args.limit)
+    elif args.schema:
+        query = """
+            SELECT c.table_schema, c.table_name, c.column_name, c.data_type, c.is_nullable
+            FROM information_schema.columns c
+            JOIN information_schema.tables t ON c.table_name = t.table_name AND c.table_schema = t.table_schema
+            WHERE c.table_schema NOT IN ('pg_catalog', 'information_schema')
+            ORDER BY c.table_schema, c.table_name, c.ordinal_position
+        """
+        execute_query(db_config, query, args.limit)
+    elif args.query:
+        execute_query(db_config, args.query, args.limit)
+    else:
+        print("Error: --query, --tables, or --schema required")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

package/skills_ref/pptx/LICENSE.txt

@@ -0,0 +1,30 @@
+© 2025 Anthropic, PBC. All rights reserved.
+
+LICENSE: Use of these materials (including all code, prompts, assets, files,
+and other components of this Skill) is governed by your agreement with
+Anthropic regarding use of Anthropic's services. If no separate agreement
+exists, use is governed by Anthropic's Consumer Terms of Service or
+Commercial Terms of Service, as applicable:
+https://www.anthropic.com/legal/consumer-terms
+https://www.anthropic.com/legal/commercial-terms
+Your applicable agreement is referred to as the "Agreement." "Services" are
+as defined in the Agreement.
+
+ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the
+contrary, users may not:
+
+- Extract these materials from the Services or retain copies of these
+  materials outside the Services
+- Reproduce or copy these materials, except for temporary copies created
+  automatically during authorized use of the Services
+- Create derivative works based on these materials
+- Distribute, sublicense, or transfer these materials to any third party
+- Make, offer to sell, sell, or import any inventions embodied in these
+  materials
+- Reverse engineer, decompile, or disassemble these materials
+
+The receipt, viewing, or possession of these materials does not convey or
+imply any license or right beyond those expressly granted above.
+
+Anthropic retains all right, title, and interest in these materials,
+including all copyrights, patents, and other intellectual property rights.

package/skills_ref/pptx/SKILL.md

@@ -0,0 +1,232 @@
+---
+name: pptx
+description: "Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill."
+license: Proprietary. LICENSE.txt has complete terms
+---
+
+# PPTX Skill
+
+## Quick Reference
+
+| Task | Guide |
+|------|-------|
+| Read/analyze content | `python -m markitdown presentation.pptx` |
+| Edit or create from template | Read [editing.md](editing.md) |
+| Create from scratch | Read [pptxgenjs.md](pptxgenjs.md) |
+
+---
+
+## Reading Content
+
+```bash
+# Text extraction
+python -m markitdown presentation.pptx
+
+# Visual overview
+python scripts/thumbnail.py presentation.pptx
+
+# Raw XML
+python scripts/office/unpack.py presentation.pptx unpacked/
+```
+
+---
+
+## Editing Workflow
+
+**Read [editing.md](editing.md) for full details.**
+
+1. Analyze template with `thumbnail.py`
+2. Unpack → manipulate slides → edit content → clean → pack
+
+---
+
+## Creating from Scratch
+
+**Read [pptxgenjs.md](pptxgenjs.md) for full details.**
+
+Use when no template or reference presentation is available.
+
+---
+
+## Design Ideas
+
+**Don't create boring slides.** Plain bullets on a white background won't impress anyone. Consider ideas from this list for each slide.
+
+### Before Starting
+
+- **Pick a bold, content-informed color palette**: The palette should feel designed for THIS topic. If swapping your colors into a completely different presentation would still "work," you haven't made specific enough choices.
+- **Dominance over equality**: One color should dominate (60-70% visual weight), with 1-2 supporting tones and one sharp accent. Never give all colors equal weight.
+- **Dark/light contrast**: Dark backgrounds for title + conclusion slides, light for content ("sandwich" structure). Or commit to dark throughout for a premium feel.
+- **Commit to a visual motif**: Pick ONE distinctive element and repeat it — rounded image frames, icons in colored circles, thick single-side borders. Carry it across every slide.
+
+### Color Palettes
+
+Choose colors that match your topic — don't default to generic blue. Use these palettes as inspiration:
+
+| Theme | Primary | Secondary | Accent |
+|-------|---------|-----------|--------|
+| **Midnight Executive** | `1E2761` (navy) | `CADCFC` (ice blue) | `FFFFFF` (white) |
+| **Forest & Moss** | `2C5F2D` (forest) | `97BC62` (moss) | `F5F5F5` (cream) |
+| **Coral Energy** | `F96167` (coral) | `F9E795` (gold) | `2F3C7E` (navy) |
+| **Warm Terracotta** | `B85042` (terracotta) | `E7E8D1` (sand) | `A7BEAE` (sage) |
+| **Ocean Gradient** | `065A82` (deep blue) | `1C7293` (teal) | `21295C` (midnight) |
+| **Charcoal Minimal** | `36454F` (charcoal) | `F2F2F2` (off-white) | `212121` (black) |
+| **Teal Trust** | `028090` (teal) | `00A896` (seafoam) | `02C39A` (mint) |
+| **Berry & Cream** | `6D2E46` (berry) | `A26769` (dusty rose) | `ECE2D0` (cream) |
+| **Sage Calm** | `84B59F` (sage) | `69A297` (eucalyptus) | `50808E` (slate) |
+| **Cherry Bold** | `990011` (cherry) | `FCF6F5` (off-white) | `2F3C7E` (navy) |
+
+### For Each Slide
+
+**Every slide needs a visual element** — image, chart, icon, or shape. Text-only slides are forgettable.
+
+**Layout options:**
+- Two-column (text left, illustration on right)
+- Icon + text rows (icon in colored circle, bold header, description below)
+- 2x2 or 2x3 grid (image on one side, grid of content blocks on other)
+- Half-bleed image (full left or right side) with content overlay
+
+**Data display:**
+- Large stat callouts (big numbers 60-72pt with small labels below)
+- Comparison columns (before/after, pros/cons, side-by-side options)
+- Timeline or process flow (numbered steps, arrows)
+
+**Visual polish:**
+- Icons in small colored circles next to section headers
+- Italic accent text for key stats or taglines
+
+### Typography
+
+**Choose an interesting font pairing** — don't default to Arial. Pick a header font with personality and pair it with a clean body font.
+
+| Header Font | Body Font |
+|-------------|-----------|
+| Georgia | Calibri |
+| Arial Black | Arial |
+| Calibri | Calibri Light |
+| Cambria | Calibri |
+| Trebuchet MS | Calibri |
+| Impact | Arial |
+| Palatino | Garamond |
+| Consolas | Calibri |
+
+| Element | Size |
+|---------|------|
+| Slide title | 36-44pt bold |
+| Section header | 20-24pt bold |
+| Body text | 14-16pt |
+| Captions | 10-12pt muted |
+
+### Spacing
+
+- 0.5" minimum margins
+- 0.3-0.5" between content blocks
+- Leave breathing room—don't fill every inch
+
+### Avoid (Common Mistakes)
+
+- **Don't repeat the same layout** — vary columns, cards, and callouts across slides
+- **Don't center body text** — left-align paragraphs and lists; center only titles
+- **Don't skimp on size contrast** — titles need 36pt+ to stand out from 14-16pt body
+- **Don't default to blue** — pick colors that reflect the specific topic
+- **Don't mix spacing randomly** — choose 0.3" or 0.5" gaps and use consistently
+- **Don't style one slide and leave the rest plain** — commit fully or keep it simple throughout
+- **Don't create text-only slides** — add images, icons, charts, or visual elements; avoid plain title + bullets
+- **Don't forget text box padding** — when aligning lines or shapes with text edges, set `margin: 0` on the text box or offset the shape to account for padding
+- **Don't use low-contrast elements** — icons AND text need strong contrast against the background; avoid light text on light backgrounds or dark text on dark backgrounds
+- **NEVER use accent lines under titles** — these are a hallmark of AI-generated slides; use whitespace or background color instead
+
+---
+
+## QA (Required)
+
+**Assume there are problems. Your job is to find them.**
+
+Your first render is almost never correct. Approach QA as a bug hunt, not a confirmation step. If you found zero issues on first inspection, you weren't looking hard enough.
+
+### Content QA
+
+```bash
+python -m markitdown output.pptx
+```
+
+Check for missing content, typos, wrong order.
+
+**When using templates, check for leftover placeholder text:**
+
+```bash
+python -m markitdown output.pptx | grep -iE "xxxx|lorem|ipsum|this.*(page|slide).*layout"
+```
+
+If grep returns results, fix them before declaring success.
+
+### Visual QA
+
+**⚠️ USE SUBAGENTS** — even for 2-3 slides. You've been staring at the code and will see what you expect, not what's there. Subagents have fresh eyes.
+
+Convert slides to images (see [Converting to Images](#converting-to-images)), then use this prompt:
+
+```
+Visually inspect these slides. Assume there are issues — find them.
+
+Look for:
+- Overlapping elements (text through shapes, lines through words, stacked elements)
+- Text overflow or cut off at edges/box boundaries
+- Decorative lines positioned for single-line text but title wrapped to two lines
+- Source citations or footers colliding with content above
+- Elements too close (< 0.3" gaps) or cards/sections nearly touching
+- Uneven gaps (large empty area in one place, cramped in another)
+- Insufficient margin from slide edges (< 0.5")
+- Columns or similar elements not aligned consistently
+- Low-contrast text (e.g., light gray text on cream-colored background)
+- Low-contrast icons (e.g., dark icons on dark backgrounds without a contrasting circle)
+- Text boxes too narrow causing excessive wrapping
+- Leftover placeholder content
+
+For each slide, list issues or areas of concern, even if minor.
+
+Read and analyze these images:
+1. /path/to/slide-01.jpg (Expected: [brief description])
+2. /path/to/slide-02.jpg (Expected: [brief description])
+
+Report ALL issues found, including minor ones.
+```
+
+### Verification Loop
+
+1. Generate slides → Convert to images → Inspect
+2. **List issues found** (if none found, look again more critically)
+3. Fix issues
+4. **Re-verify affected slides** — one fix often creates another problem
+5. Repeat until a full pass reveals no new issues
+
+**Do not declare success until you've completed at least one fix-and-verify cycle.**
+
+---
+
+## Converting to Images
+
+Convert presentations to individual slide images for visual inspection:
+
+```bash
+python scripts/office/soffice.py --headless --convert-to pdf output.pptx
+pdftoppm -jpeg -r 150 output.pdf slide
+```
+
+This creates `slide-01.jpg`, `slide-02.jpg`, etc.
+
+To re-render specific slides after fixes:
+
+```bash
+pdftoppm -jpeg -r 150 -f N -l N output.pdf slide-fixed
+```
+
+---
+
+## Dependencies
+
+- `pip install "markitdown[pptx]"` - text extraction
+- `pip install Pillow` - thumbnail grids
+- `npm install -g pptxgenjs` - creating from scratch
+- LibreOffice (`soffice`) - PDF conversion (auto-configured for sandboxed environments via `scripts/office/soffice.py`)
+- Poppler (`pdftoppm`) - PDF to images