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 agentmods add skills/cxcscmu/skilllearnbench/docx-pptx-extractionnpx skills add cxcscmu/SkillLearnBench --skill docx-pptx-extractiongit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote 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/cxcscmu/skilllearnbench/docx-pptx-extraction)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/docx-pptx-extraction"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/docx-pptx-extraction.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00020 | $0.00476 |
| Opus 5 | $0.00010 | $0.00238 |
| Sonnet 5 | $0.00004 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
docx-pptx-extraction 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 4d 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.
What it actually says
DOCX and PPTX Text Extraction
Overview
Extract text content from Microsoft Office files (.docx, .pptx) for subject classification.
Installation
pip install python-docx python-pptx
DOCX Extraction
from docx import Document
def extract_docx_text(docx_path, max_chars=5000):
"""Extract text from DOCX files"""
try:
doc = Document(docx_path)
text = ""
for para in doc.paragraphs:
text += para.text + "\n"
if len(text) > max_chars:
break
return text[:max_chars]
except Exception as e:
return f"Error reading DOCX: {str(e)}"
PPTX Extraction
from pptx import Presentation
def extract_pptx_text(pptx_path, max_chars=5000):
"""Extract text from PPTX files"""
try:
prs = Presentation(pptx_path)
text = ""
for slide_num, slide in enumerate(prs.slides):
if slide_num >= 5: # First 5 slides
break
for shape in slide.shapes:
if hasattr(shape, "text"):
text += shape.text + "\n"
if len(text) > max_chars:
return text[:max_chars]
return text[:max_chars]
except Exception as e:
return f"Error reading PPTX: {str(e)}"
Combined Handler
def extract_text_by_type(file_path):
"""Route to appropriate extraction method based on file extension"""
ext = file_path.lower().split('.')[-1]
if ext == 'pdf':
return extract_pdf_text(file_path)
elif ext == 'docx':
return extract_docx_text(file_path)
elif ext == 'pptx':
return extract_pptx_text(file_path)
else:
return ""
Best Practices
- Extract from first 3-5 pages/slides only
- Handle missing text shapes gracefully
- Use consistent character limits across all file types
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.
- 4d ago First seen · 79 lines · 20 tokens per session scan A 798f1120d93e
docx-pptx-extraction is a skill published in the GitHub repository cxcscmu/SkillLearnBench (82 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 476 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
filler-word-processing
Process filler word annotations to generate video edit lists. Use when working with timestamp annotations for removing speech disfluencies (um, uh, like, you know) from audio/video content.
whisper-transcription
Transcribe audio/video to text with word-level timestamps using OpenAI Whisper. Use when you need speech-to-text with accurate timing information for each word.
ffmpeg-video-editing
Video editing with ffmpeg including cutting, trimming, concatenating segments, and re-encoding. Use when working with video files (.mp4, .mkv, .avi) for: removing segments, joining clips, extracting portions, or any video manipulation task.
agentsop-llamaindex
Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query engines, routers…
csv-processing
Use this skill when reading sensor data from CSV files, writing simulation results to CSV, processing time-series data with pandas, or handling missing values in datasets.