Proma is a local-first AI desktop application that combines multi-model chat, general-purpose agents, workspaces, skills, MCP servers, remote bots, and shared memory. People use it as a workspace for personal workflows, letting agents handle files, browser tasks, long-running jobs, and collaborative subtasks while storing sessions and configuration locally.
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 proma-ai/Proma --skill guizang-ppt-skillgit clone --depth 1 https://github.com/proma-ai/PromaWrote 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/proma-ai/proma/guizang-ppt-skill)<a href="https://agentmods.dev/skills/proma-ai/proma/guizang-ppt-skill"><img src="https://agentmods.dev/badge/skills/proma-ai/proma/guizang-ppt-skill/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/proma-ai/proma/guizang-ppt-skill"><img src="https://agentmods.dev/badge/skills/proma-ai/proma/guizang-ppt-skill.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 | $0.00161 | $0.10228 |
| Opus 5 | $0.00081 | $0.05114 |
| Sonnet 5 | $0.00032 | $0.02046 |
| Haiku 4.5 | $0.00016 | $0.01023 |
Grade A, and why
guizang-ppt-skill 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 12d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
16 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/motion.min.js 63 KB runs code
- assets/template-swiss.html 99 KB
- assets/template.html 38 KB
- LICENSE 1.0 KB
- README.en.md 11 KB
- README.md 11 KB
- references/checklist.md 28 KB
- references/components.md 15 KB
- references/image-prompts.md 12 KB
- references/layouts-swiss.md 50 KB
- references/layouts.md 28 KB
- references/swiss-layout-lock.md 5.8 KB
- references/swiss-map-component.md 13 KB
- references/themes-swiss.md 5.5 KB
- references/themes.md 3.5 KB
- scripts/validate-swiss-deck.mjs 4.8 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.
- 12d ago First seen · 492 lines · 161 tokens per session scan A 9fc83b3a8b9e
guizang-ppt-skill is a skill published in the GitHub repository proma-ai/Proma (2,163 stars, last pushed yesterday), licensed AGPL-3.0. It adds 161 tokens to every session and 10,228 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
pptx
Create and validate Microsoft PowerPoint presentations (.pptx), including structured slide decks, tables, workflows, metadata, and reproducible generation scripts. Use for presentation, slides, PowerPoint, PPT, or PPTX creation and verification tasks.
lume-infographic
A Chinese-language workflow for presenting dense information as a safe Lume infographic. It chooses a supported visual layout for comparisons, stages, timelines, hierarchies, relationships, metrics, or categories.
画师工作流程（白洛）
A visual-creation workflow for turning image requests into briefs and generation prompts. It covers style, mood, composition, color, consistency, and reference-image changes.
配音师工作流程（宋澈）
A Chinese voice-over writing workflow for improving spoken scripts through shorter sentences, pauses, emphasis, pronunciation notes, and style selection. It supports formal announcements, friendly narration, energetic promotion, and documentary-style delivery.
小说家工作流程（温序）
A Chinese-language workflow for writing novels with stored story details, continuing chapters, tracking foreshadowing, and checking for continuity errors. Foreshadowing is an earlier clue that supports a later story event.
图片生成
A Chinese-language skill for generating or editing bitmap images with an image-generation tool and showing the result to the user.