Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill pptx-constructiongit clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_ConstructionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pptx-construction)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pptx-construction"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pptx-construction/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pptx-construction"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pptx-construction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.03881 |
| Opus 5.5 | $0.00012 | $0.01552 |
| Sonnet 5.5 | $0.00006 | $0.00776 |
| Haiku 4.5 | $0.00003 | $0.00388 |
Grade A, and why
pptx-construction scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- pptx-construction — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PowerPoint Generation for Construction
Overview
Create professional PowerPoint presentations for construction projects using python-pptx. Generate stakeholder updates, progress reports, and bid presentations with automated data visualization.
Construction Use Cases
1. Project Progress Presentation
Generate monthly progress update slides.
from pptx import Presentation
from pptx.util import Inches, Pt
from pptx.enum.chart import XL_CHART_TYPE
from pptx.chart.data import CategoryChartData
from pptx.dml.color import RGBColor
from pptx.enum.text import PP_ALIGN
def create_progress_presentation(project_data: dict, output_path: str) -> str:
"""Create project progress presentation."""
prs = Presentation()
prs.slide_width = Inches(13.333)
prs.slide_height = Inches(7.5)
# Title slide
title_slide = prs.slides.add_slide(prs.slide_layouts[0])
title_slide.shapes.title.text = project_data['project_name']
title_slide.placeholders[1].text = f"Progress Report - {project_data['report_date']}"
# Executive Summary slide
summary_slide = prs.slides.add_slide(prs.slide_layouts[1])
summary_slide.shapes.title.text = "Executive Summary"
summary_text = summary_slide.placeholders[1]
tf = summary_text.text_frame
tf.paragraphs[0].text = f"Overall Progress: {project_data['overall_progress']}%"
p = tf.add_paragraph()
p.text = f"Schedule Status: {project_data['schedule_status']}"
p = tf.add_paragraph()
p.text = f"Budget Status: {project_data['budget_status']}"
p = tf.add_paragraph()
p.text = f"Safety: {project_data['safety_status']}"
# Schedule Progress Chart
add_schedule_chart(prs, project_data['schedule_data'])
# Budget Chart
add_budget_chart(prs, project_data['budget_data'])
# Key Milestones
add_milestones_slide(prs, project_data['milestones'])
# Issues & Risks
add_issues_slide(prs, project_data.get('issues', []))
# Photos
if project_data.get('photos'):
add_photos_slide(prs, project_data['photos'])
prs.save(output_path)
return output_path
def add_schedule_chart(prs: Presentation, schedule_data: dict):
"""Add schedule progress chart."""
slide = prs.slides.add_slide(prs.slide_layouts[5])
slide.shapes.title.text = "Schedule Progress"
chart_data = CategoryChartData()
chart_data.categories = schedule_data['phases']
chart_data.add_series('Planned', schedule_data['planned'])
chart_data.add_series('Actual', schedule_data['actual'])
chart = slide.shapes.add_chart(
XL_CHART_TYPE.COLUMN_CLUSTERED,
Inches(1), Inches(1.5),
Inches(11), Inches(5),
chart_data
).chart
chart.has_legend = True
chart.legend.include_in_layout = False
def add_budget_chart(prs: Presentation, budget_data: dict):
"""Add budget status chart."""
slide = prs.slides.add_slide(prs.slide_layouts[5])
slide.shapes.title.text = "Budget Status"
chart_data = CategoryChartData()
chart_data.categories = ['Budget', 'Committed', 'Spent', 'Forecast']
chart_data.add_series('Amount ($M)', [
budget_data['budget'] / 1_000_000,
budget_data['committed'] / 1_000_000,
budget_data['spent'] / 1_000_000,
budget_data['forecast'] / 1_000_000
])
chart = slide.shapes.add_chart(
XL_CHART_TYPE.BAR_CLUSTERED,
Inches(1), Inches(1.5),
Inches(11), Inches(5),
chart_data
).chart
def add_milestones_slide(prs: Presentation, milestones: list):
"""Add key milestones slide."""
slide = prs.slides.add_slide(prs.slide_layouts[5])
slide.shapes.title.text = "Key Milestones"
# Create table
rows = len(milestones) + 1
cols = 4
table = slide.shapes.add_table(rows, cols, Inches(0.5), Inches(1.5), Inches(12), Inches(0.5 * rows)).table
# Headers
headers = ['Milestone', 'Planned', 'Actual/Forecast', 'Status']
for i, header in enumerate(headers):
table.cell(0, i).text = header
# Data
for i, ms in enumerate(milestones, 1):
table.cell(i, 0).text = ms['name']
table.cell(i, 1).text = ms['planned_date']
table.cell(i, 2).text = ms.get('actual_date', ms.get('forecast_date', 'TBD'))
table.cell(i, 3).text = ms['status']
def add_issues_slide(prs: Presentation, issues: list):
"""Add issues and risks slide."""
slide = prs.slides.add_slide(prs.slide_layouts[1])
slide.shapes.title.text = "Issues & Risks"
if not issues:
slide.placeholders[1].text = "No critical issues at this time."
return
tf = slide.placeholders[1].text_frame
for i, issue in enumerate(issues):
if i == 0:
tf.paragraphs[0].text = f"• {issue['description']} ({issue['status']})"
else:
p = tf.add_paragraph()
p.text = f"• {issue['description']} ({issue['status']})"
def add_photos_slide(prs: Presentation, photos: list):
"""Add site photos slide."""
slide = prs.slides.add_slide(prs.slide_layouts[5])
slide.shapes.title.text = "Site Progress Photos"
# Arrange up to 4 photos in grid
positions = [
(Inches(0.5), Inches(1.5)),
(Inches(6.5), Inches(1.5)),
(Inches(0.5), Inches(4)),
(Inches(6.5), Inches(4))
]
for i, photo in enumerate(photos[:4]):
left, top = positions[i]
slide.shapes.add_picture(photo['path'], left, top, width=Inches(5.5))
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 421 lines · 31 tokens per session scan A 3c600637af54
pptx-construction is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (374 stars, last pushed 8d ago), licensed MIT. It adds 31 tokens to every session and 3,881 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
treatment-plans
Formats and structurally validates local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
venue-templates
Prepares journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Supports selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF.
markdown-to-pdf
Convert a markdown file to PDF using mistune + reportlab. Use when the user wants to convert a .md file to PDF, or when another skill needs to produce a PDF from markdown output.
brand-consistency-checker
Scan documents and slides for off-brand colors, fonts, and logos. Validate against brand guidelines and suggest corrections.
012-agile-epic
Guides the creation of agile epics with comprehensive definition including business value, success criteria, and breakdown into user stories. Use when the user wants to create an agile epic, define large bodies of work, break down features into user stories, or document strategic initiatives. This should trigger for…
cowork-home-inventory
Build an insurance-grade home inventory from a folder of photos and receipts -- identifies items, pulls values from receipts, estimates replacement costs, organizes by room, and outputs the documentation an insurance claim actually requires. Update mode keeps it current after new purchases.