用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/vamseeachanta/workspace-hub --skill docx-templates-1-template-design命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
Write outbound email and external messages in Vamsee Achanta's voice — a subtle offer to help, never bold or rash claims. Load before drafting ANY email, LinkedIn/Collide reply, proposal note, or outreach sent under his name.
Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis results", "hf dataset", "make results queryable", or "render via datasets-server API". Reshapes nested results into flat parquet tables, writes a dataset card with a viewer `configs:` block and provenance, applies license/public-vs-private routing, enforces a domain data-quality gate (faithful-to-source != correct), publishes to `aceengineer/<repo>-<projection>`, and verifies via the datasets-server API.
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
正在显示 SKILL.md
| name | docx-templates-1-template-design |
| description | Sub-skill of docx-templates: 1. Template Design (+2). |
| version | 1.0.0 |
| category | data |
| type | reference |
| scripts_exempt | true |
"""Best practices for template design."""
# DO: Use meaningful variable names
good_context = {
"customer_name": "John Smith",
"invoice_date": "2026-01-17",
"total_amount": "$1,500.00"
}
# DON'T: Use cryptic names
bad_context = {
"cn": "John Smith",
"d": "2026-01-17",
"t": "$1,500.00"
}
# DO: Organize context with nested objects
organized_context = {
"customer": {
"name": "John Smith",
"email": "john@example.com",
"address": {
"street": "123 Main St",
"city": "New York"
}
},
"invoice": {
"number": "INV-001",
"date": "2026-01-17",
"items": [...]
}
}
# DO: Include computed values
def prepare_context(data: dict) -> dict:
"""Prepare context with computed values."""
context = data.copy()
# Add computed fields
if "items" in context:
context["item_count"] = len(context["items"])
context["subtotal"] = sum(i["total"] for i in context["items"])
# Add display flags
context["has_discount"] = context.get("discount", 0) > 0
return context
"""Robust error handling for template rendering."""
from typing import Tuple, Optional
def safe_render(
template_path: str,
output_path: str,
context: dict
) -> Tuple[bool, Optional[str]]:
"""
Safely render template with error handling.
Returns:
Tuple of (success, error_message)
"""
try:
# Validate template exists
if not Path(template_path).exists():
return False, f"Template not found: {template_path}"
# Load and render
template = DocxTemplate(template_path)
# Check for missing variables
required_vars = template.get_undeclared_template_variables()
missing = [v for v in required_vars if v not in context]
if missing:
return False, f"Missing variables: {missing}"
template.render(context)
# Ensure output directory exists
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
template.save(output_path)
return True, None
except Exception as e:
return , (e)
"""Optimize batch document generation."""
# DO: Use parallel processing for large batches
def optimized_batch_generation(
template_path: str,
records: List[Dict],
output_dir: str,
batch_size: int = 100
) -> List[str]:
"""Generate documents in optimized batches."""
from concurrent.futures import ThreadPoolExecutor
def process_batch(batch_records):
results = []
for record in batch_records:
template = DocxTemplate(template_path)
template.render(record)
output_path = Path(output_dir) / f"{record['id']}.docx"
template.save(str(output_path))
results.append(str(output_path))
return results
# Process in batches
all_results = []
batches = [records[i:i+batch_size] for i in range(0, len(records), batch_size)]
with ThreadPoolExecutor(max_workers=4) as executor:
futures = [executor.submit(process_batch, b) for b in batches]
for future in futures:
all_results.extend(future.result())
return all_results