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/skillmedev/document-studio/slide-deck-buildernpx skills add SkillMedev/document-studio --skill slide-deck-buildergit clone --depth 1 https://github.com/SkillMedev/document-studioWhat 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 | $0.00043 | $0.01051 |
| Opus 5 | $0.00022 | $0.00526 |
| Sonnet 5 | $0.00009 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
Slide Deck Builder 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 yesterday.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slide Deck Builder
A slide deck is an argument, not a filing cabinet. Every structural choice either advances or dilutes the central point. Build the narrative before touching any slide.
Build the spine first
Before writing a single slide, answer three questions in writing:
- What does the audience believe now?
- What should they believe or do after?
- What is the single most important thing standing between those two states?
That gap is the deck's job. Every slide serves the journey across it. A deck that does not answer all three is not ready to build.
Narrative arc
Default structure for a decision-driving deck:
- Situation - shared context the audience already holds as true
- Complication - what changed or what is broken; the tension
- Resolution - the proposed path forward
- Proof - evidence the resolution works
- Ask - the specific decision or action requested
Never start with the ask. Never bury the complication in slide 9.
Size the deck to the meeting: budget roughly 2 minutes of talk time per slide, so a 30-minute decision meeting supports 10-15 slides - anything past that is appendix material.
One idea per slide
If a slide requires a sub-bullet to be understood, it has two ideas. Split it. The test: cover the body and read only the headline. If the point still lands, the slide is right. If the body is doing the work, the headline is wrong.
Do not use slides as documents. If content requires more than 40 words to be understood, it belongs in an appendix or a leave-behind - not on a live slide.
Headlines as takeaways
Every headline should be a complete, opinionated sentence - not a topic label - and short enough to read in one glance (about 12 words is the ceiling).
- Wrong: 'Market Analysis'
- Right: 'The market is growing 3x faster than our current capacity'
A reader who only reads headlines should get the whole argument. If the headlines form a logical chain, the deck is structurally sound.
Worked example: the headline chain
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.
- yesterday First seen · 94 lines · 43 tokens per session scan A b9d702a9f70d
Slide Deck Builder is a skill published in the GitHub repository SkillMedev/document-studio (1 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,051 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
markdown-documents
Use when creating or editing Markdown documents, notes, reports, briefs, drafts, or other editable writing where Markdown should be the primary artifact format.
writer-documents
Use when creating, opening, or editing LibreOffice Writer ODT documents, or DOCX documents only when Microsoft Word compatibility is explicitly required.
pipefy-reports
Use this skill when the user wants to create, read, update, delete, or export pipe reports or organization reports. Covers the async export workflow (trigger, poll, download). 17 MCP tools.
html-artifact
Create self-contained HTML artifacts (single-file by default, split bundles when oversized) for complex, reviewable, or shareable work outputs. Use for an HTML artifact, browser-viewable report, implementation plan, PR/code-review report, dashboard, or mini deck, or for long Markdown-like outputs needing navigation or…
making-academic-presentations
Create academic presentation slide decks and optionally demo videos from research papers.
erpclaw
AI-native ERP system. Full accounting, invoicing, inventory, purchasing, tax, billing, HR, payroll, advanced accounting (ASC 606/842, intercompany, consolidation), and financial reporting (including P&L / trial balance / spend grouped by department, project, cost center, location, or fund). 496 actions across 14…