Orkas is a desktop application for commanding a team of AI agents through one chat, with a commander model assigning work to specialist agents in parallel or in sequence. People use it to coordinate research, writing, presentations, and software tasks while keeping files on their computer. The catalogue includes skills for extending the agents available to Orkas.
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 Orkas-AI/Orkas --skill ppt-reviewgit clone --depth 1 https://github.com/Orkas-AI/OrkasWrote 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/orkas-ai/orkas/ppt-review)<a href="https://agentmods.dev/skills/orkas-ai/orkas/ppt-review"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/ppt-review/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/orkas-ai/orkas/ppt-review"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/ppt-review.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 | $0.00002 | $0.03290 |
| Opus 5.5 | $0.00001 | $0.01316 |
| Sonnet 5.5 | $0.00000 | $0.00658 |
| Haiku 4.5 | $0.00000 | $0.00329 |
Grade A, and why
ppt-review 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPT Review
Read this skill before the first deck or output quality review, so its criteria are available when the rendered images arrive. Apply the criteria to current office_review structural output and relevant rendered images. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.
Evidence set
- Run
office_reviewwithaction:"check_and_render"after every create or edit. Invalid OpenXML is a blocker, not a warning. - For a new deck, render every slide. For an existing deck, render every changed slide plus the cover, a representative unchanged content slide, and any slide whose theme, master, or shared element could be affected. Every render intended as current visual-defect evidence must set
analysis_mode:"quality_review"; ordinary source understanding keeps the defaultunderstandmode. - After a repair affects multiple pages, request them together in one
office_reviewcall withaction:"check_and_render", apagesarray, andanalysis_mode:"quality_review". One collected image set lets managed visual preprocessing analyze the affected pages as a batch. If one render fails after a valid check, retry only that page withaction:"render"rather than rerendering the successful set. - In the first response that sees each collected
quality_reviewimage set, record concrete findings with page numbers, supporting observations, and repair or retain decisions before follow-up tool calls. These are working notes, not the final handoff table; preserve observations for all reviewed pages, including pages without defects. Update only the affected findings after a repair, using the current render; retain unchanged-page evidence. When exact edit paths are needed, request targetedoffice_readcalls together; do not rerender an unchangedartifact_revisionmerely to recover forgotten pixels. - Use the returned
artifact_revisionto distinguish current from stale check/render evidence andimage_revisionto compare rerenders. If an edit claimed to repair a visible defect but the affected page keeps the sameimage_revision, do not claim a visual repair: verify that the edited artifact revision was rendered, then make a supported layout/content change or retain the finding as unresolved. - If rendering is unavailable, mark visual checks
not_run; do not infer a pass from structural validity.
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 Changed · +3 lines 7b78a949fe8c
- 1mo ago First seen · 188 lines · 2 tokens per session scan A a53b0428b72b
ppt-review is a skill published in the GitHub repository Orkas-AI/Orkas (2,337 stars, last pushed today), licensed MIT. It adds 2 tokens to every session and 3,290 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
technical-communication
Technical writing, engineering specifications, reports, presentations, and documentation standards for engineering practice. Covers document types (requirements documents, test reports, design rationale, operations manuals), writing style, data visualization, engineering drawing standards, and oral presentation…
pptx
Create/edit/inspect/verify slide decks and PPTX presentations.
xlsx
Create/edit/analyze/verify spreadsheet workbooks including XLSX/CSV/TSV.
ppt-analysis
A parser for PowerPoint presentations in .pptx or older .ppt format that extracts their contents and flags slides needing image-based inspection.
multi-sheet-reading-and-analysis
A workflow for reading and analyzing Excel files with multiple worksheets, including data cleaning, grouping, fitting lines to data, and formatted charts.
excel-data-analysis-and-report-generation
A skill for extracting, categorising, counting, and comparing data from Excel spreadsheets. It can produce summary tables with totals, percentages, and cross-tabulations.