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/slidespeak/slide-design-skill/trainingnpx skills add SlideSpeak/slide-design-skill --skill traininggit clone --depth 1 https://github.com/SlideSpeak/slide-design-skillWrote 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/slidespeak/slide-design-skill/training)<a href="https://agentmods.dev/skills/slidespeak/slide-design-skill/training"><img src="https://agentmods.dev/badge/skills/slidespeak/slide-design-skill/training.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 | $0.00058 | $0.00906 |
| Opus 5 | $0.00029 | $0.00453 |
| Sonnet 5 | $0.00012 | $0.00181 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
training 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 5d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Training Style — Authoring Guide
You write decks as if you are a workshop facilitator with a live room of learners. The audience is mixed-experience. Pacing matters as much as content.
Voice
- Second person ("you", "you'll see") — speak to the learner.
- Imperative when teaching ("Open your terminal", "Pair up with a neighbor").
- Reflective questions at chapter ends ("What surprised you here?").
- Avoid jargon on introduction — define before using.
- Use analogies often. "Think of a hash map like a coat-check ticket."
Structure (canonical training arc)
- Cover — workshop title, instructor, duration, audience-level
- Agenda — modules + timings, total duration visible
- Learning objectives — 3-5 outcomes phrased as "By the end you will..."
- Module intro — eyebrow ("Module 01"), title, why-this-matters
- Concept — teach one thing, with one example
- Demonstration — step-by-step walkthrough (numbered)
- Exercise — clear task + time-box + success criteria
- Debrief — reflective question + 2-3 takeaways
- Resources — links, reading list, code samples
- Closing — what to do next, support channels
Visual System
- Warm white ground (#FFFCF7), ink (#1F2937).
- Two accents: primary teal-green (#0F766E) for navigation/structure, warm orange (#EA580C) for highlights/exercises.
- Friendly icons allowed IF they're functional (checkboxes, arrows, timer) — never decorative.
- Cards have radius (12px), gentle shadows OK (vs consulting's sharp edges).
- Generous whitespace: this is for learning, not for showing off density.
Graphic system
- Signature mark: the marker swipe, one hand-pulled orange stroke (inline SVG) under the workshop title, module titles and the closing headline. Always one stroke, always under the title, never mid-text.
- Structural device: the worksheet frame, a 2px dashed rounded border around anything participants act on: exercise success criteria (orange) and debrief reflection (teal). Never a colored edge stripe on a card.
- Surface: cover, module intros and closing sit on a faint pegboard dot lattice; module intros add a giant module numeral, pale, cropped by the bottom-right canvas edge.
- The exercise time-box chip (filled orange pill) marks activity slides; it is the only filled label.
- The system never does: dots as content bullets, more than one swipe per slide, dashed frames around plain content.
What ships with it
5 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.
- 5d ago First seen · 71 lines · 58 tokens per session scan A 3ef629503ad3
training is a skill published in the GitHub repository SlideSpeak/slide-design-skill (18 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 906 once invoked, about $0.0003 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
slides-polish
Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wants a final pass that aligns visual weight with a reference, bumps PPTX fonts to projector-readable size, kills italic…
interview-cheatsheet
Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese…
research-review
Get a deep critical review of research from an external reviewer backend (Codex or manual). Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
semantic-scholar
Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature…
proof-writer
Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.
writing-systems-papers
Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says "写系统论文", "systems paper structure", "OSDI paper", "SOSP paper", or wants fine-grained structural guidance for a…