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/learningmatter-mit/atomisticskills/general-presentationnpx skills add learningmatter-mit/AtomisticSkills --skill general-presentationgit clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkillsWhat 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 | $0.00021 | $0.00980 |
| Opus 5 | $0.00010 | $0.00490 |
| Sonnet 5 | $0.00004 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
general-presentation 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presentation Generation
Goal
Create professional PowerPoint presentations from simulation results (plots, tables, parameters) using python-pptx. The agent writes standalone Python scripts using a helper library, enabling direct iteration with the user on the script to refine slides.
Instructions
1. Import the Helper Library
All scripts should import slide_utils from this skill:
# Env: base-agent
import sys
sys.path.insert(0, ".agents/skills/general-presentation/scripts")
from slide_utils import *
2. Build Slides Using Helper Functions
Available functions:
| Function | Purpose |
|---|---|
create_presentation(title, subtitle, author) |
Create a new presentation with a styled title slide |
add_title_slide(prs, title, subtitle) |
Additional title/divider slides |
add_section_slide(prs, title) |
Section divider (colored background) |
add_image_slide(prs, title, image_path, caption, notes) |
Single image/plot slide |
add_two_image_slide(prs, title, left_img, right_img, ...) |
Side-by-side images |
add_image_and_text_slide(prs, title, image_path, text, ...) |
Image + text layout |
add_table_slide(prs, title, headers, rows) |
Data table slide |
add_bullets_slide(prs, title, bullets) |
Bullet point slide |
add_autofit_box(slide, left, top, height, text, bg_color) |
Add a colored box that auto-scales width to text |
save_presentation(prs, path) |
Save to .pptx file |
Every builder function returns the Slide (or Shape) object, allowing further customization with raw python-pptx calls if needed.
3. Customize the Theme (Optional)
Override the THEME dictionary before building slides:
from slide_utils import *
THEME["primary"] = RGBColor(0x00, 0x50, 0x80)
THEME["font_family"] = "Arial"
4. Save and Iterate Visually
save_presentation(prs, "output.pptx")
The agent edits the Python script and re-runs to reflect changes. CRITICAL ITERATION LOOP: The agent MUST visually inspect the generated slides using their VLM capabilities to ensure elements do not overlap, text fits perfectly within boxes, and the slide space is used efficiently with a universal, professional design style.
What ships with it
6 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.
- examples/amorphorization/amorphorization_skill_demo.pptx 708 KB
- examples/amorphorization/amorphorization_slides.py 5.8 KB runs code
- examples/amorphorization/LiCl_amorphous.png 400 KB
- examples/amorphorization/LiCl_crystalline.png 316 KB
- examples/amorphorization/README.md 1.3 KB
- scripts/slide_utils.py 23 KB runs code
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.
- 3d ago First seen · 102 lines · 21 tokens per session scan A a8702aa3891d
general-presentation is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (154 stars, last pushed 8d ago), licensed MIT. It adds 21 tokens to every session and 980 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
audience-aware-communication
Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.
graceful-error-recovery
Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.
aios-work-dispatch
Decide when a coding agent may use aios work for independent parallel work, preview the dispatch, and require explicit approval before live model execution. TRIGGER: aios work、parallel dispatch、并发派发、independent work items、独立工作项并行、多 agent 派发、multi-agent dispatch.
skill-constraints
Enforce browser automation safety constraints — tool usage order, anti-detection rules, screenshot discipline, and human-in-the-loop checks. Use when setting up or verifying browser/MCP tool operations, NOT for every skill execution.
clarify-ambiguous-requests
Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If proceeding with a wrong assumption would waste significant work, always ask exactly one focused clarifying question before doing anything.
structured-step-by-step-reasoning
Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before answering to improve accuracy and transparency. Apply whenever the answer is not immediately obvious.