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 skills add dAAAb/agent-skills --skill ia-presentergit clone --depth 1 https://github.com/dAAAb/agent-skillsWrote 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/daaab/agent-skills/ia-presenter)<a href="https://agentmods.dev/skills/daaab/agent-skills/ia-presenter"><img src="https://agentmods.dev/badge/skills/daaab/agent-skills/ia-presenter/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/daaab/agent-skills/ia-presenter"><img src="https://agentmods.dev/badge/skills/daaab/agent-skills/ia-presenter.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00116 | $0.03447 |
| Opus 5.5 | $0.00046 | $0.01379 |
| Sonnet 5.5 | $0.00023 | $0.00689 |
| Haiku 4.5 | $0.00012 | $0.00345 |
Grade A, and why
ia-presenter 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 1mo 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iA Presenter
iA Presenter is a text-first presentation app (macOS / iOS). You write one Markdown file; the app auto-lays out responsive slides and keeps your speech as speaker notes. This skill covers two jobs:
- Authoring decks – writing iA Presenter Markdown, packaging it as a
.iapresenterbundle with a theme pre-selected, linting it, previewing it. - Custom themes –
template.json+presets.json+ CSS in the app's Themes folder.
Everything below was checked against the app's own bundled Help, layouts.json, the
theme files shipped inside iA Presenter 2.0.2, the metadata parser in the app binary,
and live rendering tests. Where community docs disagree with the app, the app wins.
Decision tree
| User wants | Do |
|---|---|
| A new presentation / deck / talk | Author → write text.md, run scripts/new_deck.py, lint, open, review |
| Turn an article / notes / outline into slides | Same as above; speech goes flush-left, only the punchline gets a TAB |
| Fix a deck that "looks wrong" | Run scripts/lint_deck.py, then check references/layouts.md |
| Change look / fonts / colors beyond built-ins | Theme → copy assets/starter-theme, edit, scripts/install_theme.sh |
| Choose a built-in theme | Set "template" in info.json (see Packaging) |
| Export PDF / PPTX / images / HTML | The app does it: File → Export or Command Palette. See references/file-format.md |
Load references progressively: syntax.md and layouts.md for any deck; content-blocks.md
for images/video; charts.md for tables→charts; themes.md + engine-css.md for themes;
file-format.md for bundle/export/automation.
Core model (memorize this)
Kicker line (TAB paragraph right before a heading = small line above it)
# Title ← headings are ALWAYS visible
Visible body text ← a real TAB (\t) at line start puts a paragraph on the slide
This flush-left paragraph is speech. The audience never sees it. ← speaker notes
--- ← three dashes on their own line = next slide
What ships with it
18 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.
- assets/example-deck.md 2.7 KB
- assets/starter-theme/presets.json 1.2 KB
- assets/starter-theme/README.md 765 B
- assets/starter-theme/starter.css 3.8 KB
- assets/starter-theme/template.json 687 B
- references/charts.md 2.5 KB
- references/content-blocks.md 4.1 KB
- references/engine-css.md 6.9 KB
- references/file-format.md 6.1 KB
- references/layouts.md 4.8 KB
- references/syntax.md 5.4 KB
- references/themes.md 9.6 KB
- scripts/__pycache__/lint_deck.cpython-311.pyc 21 KB
- scripts/__pycache__/new_deck.cpython-311.pyc 11 KB
- scripts/install_theme.sh 3.7 KB runs code
- scripts/lint_deck.py 12 KB runs code
- scripts/new_deck.py 5.5 KB runs code
- scripts/preview_deck.sh 955 B 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.
- 1mo ago First seen · 257 lines · 116 tokens per session scan A c91d9e0a08d0
ia-presenter is a skill published in the GitHub repository dAAAb/agent-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 3,447 once invoked, about $0.0005 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…