nexscope-ai/nexscope-ecommerce-skills / ecommerce-geo-score-check
ecommerce.geo-score-check
VerifiedScore an ecommerce URL for SEO + GEO readiness and AI citation visibility. Triggers on "geo score", "SEO + GEO score", "check ecommerce GEO", "Amazon/Shopify GEO", "GEO readiness audit". Covers product pages, store pages, marketplace listings, category pages, and homepages, scored from crawlable evidence (not live AI polling).
geo-eval-ecommerce/scripts/task_builder.py
View on GitHub"""Build evaluation task packages."""
import json
from pathlib import Path
def _read_file(path):
if Path(path).exists():
return Path(path).read_text(encoding="utf-8")
return ""
def prepare_eval_tasks(config, run_dir, batch_size=None):
"""Build task packages for evaluation batches."""
if batch_size is None:
batch_size = config.eval_batch_size
normalized_dir = run_dir / "normalized"
eval_dir = run_dir / "eval"
tasks_dir = run_dir / "tasks" / "eval"
eval_dir.mkdir(parents=True, exist_ok=True)
tasks_dir.mkdir(parents=True, exist_ok=True)
# Read the evaluator prompt template
skill_dir = Path(__file__).parent.parent
evaluator_template = _read_file(skill_dir / "assets" / "prompts" / "evaluator.md")
product_md = _read_file(config.base_dir / "profiles" / config.profile / "product.md")
# Find files awaiting evaluation
pending = []
for nf in sorted(normalized_dir.glob("*.json")):
eval_path = eval_dir / nf.name
if not eval_path.exists():
pending.append((nf, eval_path))
# Split into batches
tasks = []
for batch_idx in range(0, len(pending), max(batch_size, 1)):
batch = pending[batch_idx:batch_idx + batch_size]
batch_name = f"batch-{batch_idx // batch_size + 1:03d}.md"
task_path = tasks_dir / batch_name
input_paths = [str(p[0].relative_to(run_dir)) for p in batch]
output_paths = [str(p[1].relative_to(run_dir)) for p in batch]
# Generate task Markdown
prompt_filled = evaluator_template.replace("{product_info}", product_md.strip())
md_parts = [
"# Eval Batch Task\n",
"## Evaluation Prompt\n",
prompt_filled,
"\n---\n",
"## File List\n",
f"- Profile: `{config.profile}`",
"- Inputs:",
*[f" - `{p}`" for p in input_paths],
"- Outputs:",
*[f" - `{p}`" for p in output_paths],
"\n## Execution Rules\n",
"1. Generate a separate evaluation JSON for each input file",
"2. Follow the output schema exactly",
"3. product_recommendations must list all recommended products",
"4. Limit competitors_mentioned to the top 3",
]
task_path.write_text("\n".join(md_parts), encoding="utf-8")
tasks.append({
"type": "eval_batch",
"task_path": str(task_path.relative_to(run_dir)),
"input_paths": input_paths,
"output_paths": output_paths,
"status": "pending",
})
manifest = {
"schema_version": "task_manifest.v1",
"run_id": run_dir.name,
"profile": config.profile,
"tasks": tasks,
}
manifest_path = run_dir / "tasks" / "manifest.json"
manifest_path.write_text(json.dumps(manifest, ensure_ascii=False, indent=2), encoding="utf-8")
return manifest
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |