Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/HybridAIOne/hybridclawnpx agentmods add skills/hybridaione/hybridclaw/pptxWrote 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/hybridaione/hybridclaw/pptx)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/pptx"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/pptx/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/hybridaione/hybridclaw/pptx"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/pptx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00961 |
| Opus 5 | $0.00016 | $0.00481 |
| Sonnet 5 | $0.00006 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
pptx 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 9d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPTX
Use this skill whenever the user asks to create, revise, template, or review a .pptx presentation.
Start Here
- For new decks, read pptxgenjs.md.
- For template edits or preserving an existing deck, read editing.md.
Working Rules
- For template-based editing, use unpack -> edit OOXML -> pack. Do not round-trip an existing deck through
pptxgenjs. - For new decks, use
pptxgenjsfrom a CommonJS.cjsscript withrequire("pptxgenjs"). - For new decks built from a folder of source files, treat the named source documents as the inputs of record. Do not inspect older generated decks, dashboards, summary files, or helper scripts in that folder unless the user explicitly asks to reuse or update them.
- Use
node skills/office/soffice.cjs convert ... --format pdfonly when the runtime sayssofficeis available. - Keep layouts intentional: one message per slide, strong hierarchy, real whitespace, and consistent alignment.
- Use speaker-ready phrasing and evidence-based charts instead of generic bullet walls.
- For
pptxgenjstables, never use OOXML values directly in script options. Do not usevalign: "mid",valign: "ctr", or rawanchor: "mid". If vertical alignment is needed, use only thepptxgenjsvaluestop,middle, orbottom. If it is not essential, leave table-cell vertical alignment unset. - After
pptx.writeFile(...)succeeds and the requested deck exists at the expected path, return it immediately. Do not inspect your own generated script or rerun file-existence checks unless generation failed or the user asked you to debug the deck.
Visual QA Loop
- If both
sofficeandpdftoppmare available in the runtime, visual QA is required before final delivery. - If either dependency is unavailable, do not attempt the render-and-review loop. Return the generated
.pptxwithout mentioning the missing QA tools unless the user explicitly asked for QA, export, thumbnails, validation, or render verification.
What ships with it
3 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.
- 9d ago First seen · 77 lines · 32 tokens per session scan A 41fd1b2b8cb2
pptx is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 961 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 2026-09-03.
Other skills, from other repositories
lilbee-mcp
Search and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.…
lilbee-mcp-wiki
Wiki layer for lilbee. Use only when the user explicitly asks about wiki / concept / entity / synthesis pages, or when lilbeestatus shows a built wiki. Requires the lilbee-mcp skill to be active for the underlying MCP connection.
m3-health
Health check — package version, installed payload, chatlog DB row count, per-agent hook state.
m3-help
List all m3-memory slash commands / skills and what they do.
continuum-recipes
Copy-pasteable Continuum patterns — RAG, plan-and-execute, ReAct, multi-tenant agents, FastAPI integration, structured output, prompt-injection scanning, custom containers. Invoke when the user asks "how do I do X with Continuum" and X is a common app pattern rather than a single API question.
m3-forget
Delete a memory permanently. Asks for confirmation first.