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 duc01226/EasyPlatform --skill presentation-buildergit clone --depth 1 https://github.com/duc01226/EasyPlatformWrote 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/duc01226/easyplatform/presentation-builder)<a href="https://agentmods.dev/skills/duc01226/easyplatform/presentation-builder"><img src="https://agentmods.dev/badge/skills/duc01226/easyplatform/presentation-builder/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/duc01226/easyplatform/presentation-builder"><img src="https://agentmods.dev/badge/skills/duc01226/easyplatform/presentation-builder.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 | $0.00032 | $0.06293 |
| Opus 5.5 | $0.00013 | $0.02517 |
| Sonnet 5.5 | $0.00006 | $0.01259 |
| Haiku 4.5 | $0.00003 | $0.00629 |
Grade A, and why
presentation-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 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex compatibility note:
- Invoke
$skill-name: load the registered.agents/skills/<name>/SKILL.mdand execute it with Codex tools; no separateSkilltool or Claude mode switch is needed. Author.claude/**; mirrors are generated.- Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
- Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
- Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required
spawn_agentsubagent(s) for that task.- Preserve protocol order unless the user approves a deviation. Workflows use
$start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence.
[BLOCKING] Execute the declared steps in order. Keep one task
in_progress; mark each task completed with evidence immediately after it returns. [BLOCKING] If task tools are unavailable, maintain an equivalent tracker in the working response or a disposable report undertmp/reports/. [BLOCKING] Do not claim browser behavior passed when only static inspection was possible.
Quick Summary
Goal: Turn any subject and source material into a clear, audience-specific presentation whose story, visuals, notes, and runtime behavior are all reviewable.
Summary:
- Frame audience/goal/environment and evidence boundaries; build a source ledger; select a subject-appropriate narrative archetype and slide map.
- Create and critique a subject-grounded design plan; generate semantic, self-contained HTML with stable slide/purpose/note markers.
- Guarantee the presenter runtime: complete notes, notes toggle, keyboard navigation, accessible state, explicit edit mode, local draft persistence, reset, export, overview, fullscreen, print, and reduced motion.
- Run static validation, browser/manual rehearsal when available, and a final evidence report that distinguishes PASS from
NOT VERIFIABLE.
Default output: One self-contained HTML deck. If another format is requested, keep a companion editable HTML deck unless the requested artifact itself satisfies the runtime contract.
Non-negotiables: Every slide has a job, title, source/rationale, and detailed speaker notes. The deck always includes a visible notes toggle and an explicit edit mode with editable prose and notes, local draft persistence, reset, and clean export.
Workflow: frame audience/goal/environment → research and source claims → choose narrative archetype → write slide map → make a subject-grounded design plan → generate → validate → manually rehearse/review → report evidence and limits.
Utilities: node .claude/skills/presentation-builder/scripts/create-presentation.cjs <deck.json> <output.html> generates a self-contained contract-compliant starter deck; node .claude/skills/presentation-builder/scripts/validate-presentation.cjs <deck.html> [--profile=presenter|review] performs deterministic static checks against one conformance profile (default presenter; review makes only the five editing checks advisory — references/web-runtime-contract.md §9). Run both utility test files after changing them.
Key Rules:
- MUST ATTENTION give every slide a single job, stable ID, meaningful title, rationale, and non-empty notes.
- MUST ATTENTION keep notes detailed enough for presenter handoff: talk track, why, evidence/caveat, timing, transition, and question.
- MUST ATTENTION provide visible Notes and Edit mode controls with stateful accessible semantics.
- MUST ATTENTION protect structure and persist edits as a namespaced local draft with reset and clean export.
- ALWAYS preserve keyboard navigation and a visible progress/status path.
- ALWAYS run static validation, then verify browser behavior separately when a browser is available.
- NEVER invent subject claims, precision, sources, audience, or design rationale.
- NEVER claim interactive, offline, fullscreen, persistence, or accessibility behavior from static markup alone.
What ships with it
8 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.
- agents/openai.yaml 162 B
- references/presentation-principles.md 12 KB
- references/web-runtime-contract.md 15 KB
- scripts/create-presentation.cjs 53 KB runs code
- scripts/validate-presentation.cjs 19 KB runs code
- tests/create-presentation.test.cjs 41 KB runs code
- tests/skill-genericity.test.cjs 948 B runs code
- tests/validate-presentation.test.cjs 26 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 · 244 lines · 32 tokens per session scan A b3218a9f88e3
presentation-builder is a skill published in the GitHub repository duc01226/EasyPlatform (12 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 6,293 once invoked, about $0.0001 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 2026-10-18.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…