Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skillsnpx agentmods add skills/cosmicstack-labs/mercury-agent-skills/presentation-automationWrote 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/cosmicstack-labs/mercury-agent-skills/presentation-automation)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/presentation-automation"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/presentation-automation/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/cosmicstack-labs/mercury-agent-skills/presentation-automation"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/presentation-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 902 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00023 | $0.07608 |
| Opus 5 | $0.00012 | $0.03804 |
| Sonnet 5 | $0.00005 | $0.01522 |
| Haiku 4.5 | $0.00002 | $0.00761 |
Grade C, and why
presentation-automation scanned grade C with 2 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
@rm -rf $(OUTPUT_DIR)/*.pptx Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(cmd, capture_output=True, text=True) How it starts
The opening of the file, as written. The whole thing — 1,010 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presentation Automation
Automate slide generation from data sources, build programmatic presentations, and integrate slide creation into CI/CD pipelines.
Core Principles
1. Templates Are the Foundation
Never build slides from scratch in code. Create a well-designed template (.potx or Google Slides master), then populate it programmatically. Templates enforce consistency; code fills in the blanks.
2. Separate Data from Presentation
Keep data extraction, transformation, and presentation logic in distinct layers. CSV/JSON/API → Data transformation → Slide population. This makes both testing and maintenance easier.
3. Idempotency Matters
The same input data should always produce the same output slides. Use deterministic logic, avoid random placement, and version your templates alongside your code.
4. Validate Before Generating
Validate input data, template placeholders, and output formats before generating slides. A broken slide at 11:59 PM before the board meeting is a career-limiting bug.
Presentation Automation Maturity Model
| Level | Approach | Data Integration | Error Handling | Maintainability |
|---|---|---|---|---|
| 1: Manual | Copy-paste into PowerPoint | Manual data entry | Human review | Fragile, one-off |
| 2: Scripted | Basic python-pptx scripts | CSV/Excel import | Try-except blocks | Single-purpose scripts |
| 3: Templated | Template-based generation | API/DB connections | Validation, logging | Modular functions |
| 4: Automated | CI/CD pipeline, scheduled runs | Multiple data sources | Automated testing | Parameterized, configurable |
| 5: Intelligent | Auto-charting, NLP summaries | Streaming data | Self-healing | Framework with plugins |
Target: Level 3 for recurring reports. Level 4 for client-facing and board presentations.
python-pptx Fundamentals
Installation and Setup
# Install python-pptx
pip install python-pptx
# For working with images
pip install Pillow
# For data processing
pip install pandas numpy openpyxl
# Verify installation
python -c "import pptx; print(pptx.__version__)"
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.
- 8d ago First seen · 1,010 lines · 23 tokens per session scan C 22cdc648f92b
presentation-automation is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (471 stars, last pushed 17d ago), licensed MIT. It adds 23 tokens to every session and 7,608 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
manim-animation-maker
Create educational explainer videos with a Manim plus FFmpeg workflow. Use when the user asks for Manim animation, math/physics/geometry/algorithm visualization, formula derivation, concept explainer video, scene planning, MP4 rendering, preview frames, or video quality checks.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
slack-gif-creator
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
hyperframes-media
Asset preprocessing for HyperFrames compositions — text-to-speech narration (Kokoro), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing the background from a video or image to use as a…