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 TIKAZI/TIKAZ-AI-Skills --skill presentationgit clone --depth 1 https://github.com/TIKAZI/TIKAZ-AI-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/tikazi/tikaz-ai-skills/presentation)<a href="https://agentmods.dev/skills/tikazi/tikaz-ai-skills/presentation"><img src="https://agentmods.dev/badge/skills/tikazi/tikaz-ai-skills/presentation/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/tikazi/tikaz-ai-skills/presentation"><img src="https://agentmods.dev/badge/skills/tikazi/tikaz-ai-skills/presentation.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 | $0.00047 | $0.00446 |
| Opus 5.5 | $0.00019 | $0.00178 |
| Sonnet 5.5 | $0.00009 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
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 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.
What it actually says
Presentation
Designed, integrated, refactored, and continuously maintained by TIKAZ.
Inputs and routing
Accept the topic, audience, outcome, duration, source material, delivery environment, editability, template, and required formats. Use one child builder directly when HTML, PPTX, or editorial web output is already decided; otherwise use the orchestrator to choose exactly one primary format.
TIKAZ method
- Define audience, decision or learning outcome, duration, source material, delivery environment, and required editability.
- Create one narrative brief before slide production: opening tension, section logic, evidence, takeaway, and ending action.
- Route to exactly one builder:
html-deck-builder,powerpoint-deck-builder, ormagazine-web-deck. - Use a shared page contract: role, title, claim, evidence, visual job, content limits, speaker intent, and source/license status.
- Render representative pages early; test full deck after authoring.
- Check overflow, contrast, repetition, media licenses, chart truth, speaker flow, export integrity, and final file existence.
License boundary
Builders keep their own upstream licenses. In particular, AGPL-derived builders remain separately licensed and must not be presented as solely covered by the collection license.
Output, fallback, and limits
Return the narrative brief, page contracts, chosen builder, rendered QA evidence, source and license notes, final artifact path, and unresolved compatibility risks. If rendering or export is unavailable, do not treat file creation as visual approval. Do not claim native editability for flattened or HTML-only output.
Example
Use presentation to choose HTML or PPTX for this talk, write page contracts, render representative slides early, and verify the final artifact.
Read references/routing.md and references/output-contract.md.
What ships with it
12 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 281 B
- assets/workflow.svg 3.8 KB
- html-deck-builder/agents/openai.yaml 236 B
- html-deck-builder/SKILL.md 2.4 KB
- magazine-web-deck/agents/openai.yaml 245 B
- magazine-web-deck/SKILL.md 2.2 KB
- powerpoint-deck-builder/agents/openai.yaml 241 B
- powerpoint-deck-builder/SKILL.md 2.4 KB
- README.md 4.6 KB
- README.zh-CN.md 2.3 KB
- references/output-contract.md 298 B
- references/routing.md 633 B
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 · 38 lines · 47 tokens per session scan A 11f22dea6d18
presentation is a skill published in the GitHub repository TIKAZI/TIKAZ-AI-Skills (6 stars, last pushed 11d ago), licensed MIT. It adds 47 tokens to every session and 446 once invoked, about $0.0002 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
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
draft-emails-with-placeholders
Draft reusable email templates with clearly marked placeholders for names, dates, amounts, and other missing facts.
fetch-llm-apps
Regenerate the ranked GitHub LLM applications pool (section/xllmapps.md) with fetchllmapps.py. USE FOR: refreshing the pool linked from applications.md. DO NOT USE FOR: hand-curating entries in applications.md or adding star badges to the generated file.
add-new-entry-from-temp-md
Format new entries from temp.md into tempentries.md, ready to insert into the section files. USE FOR: adding new resources to the knowledge base. DO NOT USE FOR: editing existing entries or restructuring sections.