flitzrrr/agent-skills / skills/product-description-seo
product-description-seo
VerifiedEnd-to-end skill for SEO-optimized product descriptions: inventory analysis, generation, quality assurance, catalog update, and deployment. Use whenever the user wants to analyze, write, check, update, or deploy product descriptions — whether for a single product, a category, or an entire catalog. Triggers on: 'product description', 'Produktbeschreibung', 'SEO text', 'catalog text', 'update descriptions', 'which descriptions are missing', 'thin content', 'QA check', 'description quality', or when the user names a product category and wants texts for it. Also triggers on 'deploy' or 'commit' in the context of product descriptions.
| File | Kind | Size |
|---|---|---|
| CROSS-SELL.md | markdown | 1.9 KB |
| KEYWORDS.md | markdown | 1.3 KB |
| SKILL.md | skill md | 12.5 KB |
| scripts/analyze_catalog.py | script | 4.8 KB |
| scripts/check_quality.py | script | 7.5 KB |
| scripts/extract_category.py | script | 2.9 KB |
| scripts/track_progress.py | script | 5.0 KB |
| scripts/update_catalog.py | script | 2.3 KB |
| scripts/validate_json.py | script | 2.5 KB |
scripts/extract_category.py
View on GitHub#!/usr/bin/env python3
"""Extract products of a category as JSON for batch prompting.
Usage:
python extract_category.py <catalog.json> <category-name> [--limit 8]
Supports fuzzy category matching and pagination.
"""
import json
import sys
import argparse
DESC_FIELD = "beschreibung"
CAT_FIELD = "kategorieName"
CAT_FIELD_ALT = "kategorie"
SKU_FIELD = "sku"
NAME_FIELD = "name"
STATUS_FIELD = "status"
STATUS_ACTIVE = "aktiv"
def main():
parser = argparse.ArgumentParser(description="Extract category products for batch prompting")
parser.add_argument("catalog_path", help="Path to catalog JSON file")
parser.add_argument("category", help="Category name (fuzzy match)")
parser.add_argument("--limit", "-l", type=int, default=8,
help="Max products per batch (default: 8)")
parser.add_argument("--offset", "-o", type=int, default=0,
help="Skip first N products for pagination")
parser.add_argument("--thin-first", "-t", action="store_true",
help="Sort thinnest descriptions first")
args = parser.parse_args()
with open(args.catalog_path, "r", encoding="utf-8") as f:
data = json.load(f)
search = args.category.lower()
products = [
p for p in data.get("products", [])
if p.get(STATUS_FIELD, STATUS_ACTIVE) == STATUS_ACTIVE
and (search in p.get(CAT_FIELD_ALT, "").lower()
or search in p.get(CAT_FIELD, "").lower()
or p.get(CAT_FIELD_ALT, "").lower() == search
or p.get(CAT_FIELD, "").lower() == search)
]
if not products:
all_cats = sorted(set(
p.get(CAT_FIELD, p.get(CAT_FIELD_ALT, "?"))
for p in data.get("products", [])
))
print(f"No active products found for '{args.category}'.", file=sys.stderr)
print("Available categories:", file=sys.stderr)
for c in all_cats:
print(f" - {c}", file=sys.stderr)
sys.exit(1)
if args.thin_first:
products.sort(key=lambda p: len(p.get(DESC_FIELD, "").split()))
batch = products[args.offset:args.offset + args.limit]
output = []
for p in batch:
entry = {
SKU_FIELD: p.get(SKU_FIELD, ""),
NAME_FIELD: p.get(NAME_FIELD, ""),
DESC_FIELD: p.get(DESC_FIELD, ""),
}
# Include optional fields if present
for field in ["variante", "preis", "preisAufAnfrage", "einheit"]:
if field in p:
entry[field] = p[field]
output.append(entry)
total = len(products)
shown = len(batch)
remaining = total - args.offset - shown
print(json.dumps(output, ensure_ascii=False, indent=2))
print(f"\n// Category: {args.category} | Shown: {shown}/{total}"
f" | Offset: {args.offset} | Remaining: {max(0, remaining)}",
file=sys.stderr)
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |