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 agentmods add skills/xiaomimimo/mimo-code/pptx-officialnpx skills add XiaomiMiMo/MiMo-Code --skill pptx-officialgit clone --depth 1 https://github.com/XiaomiMiMo/MiMo-CodeWhat 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 | $0.00183 | $0.06976 |
| Opus 5 | $0.00092 | $0.03488 |
| Sonnet 5 | $0.00037 | $0.01395 |
| Haiku 4.5 | $0.00018 | $0.00698 |
Grade D, and why
pptx-official scanned grade D with 3 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get install -y libreoffice poppler-utils Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://astral.sh/uv/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPTX Skill
An Apache-2.0 toolkit for producing, editing, and reading Microsoft PowerPoint
(.pptx) files. Written from scratch against the public
ECMA-376 / ISO/IEC 29500 (PresentationML)
specification and built on permissively-licensed tooling (python-pptx MIT,
pptxgenjs MIT, lxml BSD-3-Clause, Pillow MIT-CMU, optional external
binaries soffice MPL 2.0 and pdftoppm GPL) so it can be reused in
commercial projects without restriction.
Decision matrix
| Situation | Path | Read first |
|---|---|---|
| Build a deck from a prompt or dataset — no source file to start from | Author with python-pptx (structured / repeatable) or PptxGenJS (design-heavy, JS) |
create.md |
You have a .pptx template to fill in — keep its master, layouts, look |
Placeholder replacement via python-pptx |
edit.md → Template fill |
| Deep structural edits — reorder slides, splice XML, add unusual objects | Explode → edit XML parts → assemble | edit.md → Raw XML workflow |
Only need the text / speaker notes / structure out of a .pptx |
Extraction pipeline | read.md |
| Turn a deck into PDF or PNG images (visual QA, publishing) | scripts/render_pdf.py / scripts/render_slides.py via LibreOffice |
see QA below |
| Grid of slide thumbnails for previewing a template | scripts/contact_sheet.py (Pillow) |
read.md → Thumbnails |
If the task mixes several of these, do them in this order: read → plan slide-by-slide → edit/create → validate → visual QA.
One-time environment setup
Bundled runtime: when the
MIMO_PYTHONenvironment variable is set, skipuv/pip installs — run every Python command below withuv runreplaced by"$MIMO_PYTHON"(python-pptx/Pillow/lxml preinstalled; pip console scripts unavailable, use"$MIMO_PYTHON" -m <module>). A bundled LibreOffice is exposed asMIMO_SOFFICE(picked up automatically bysoffice_bridge.py/render_pdf.py), and slide rasterisation automatically falls back to pypdfium2 in that interpreter when Poppler (pdftoppm) is absent. For the PptxGenJS authoring path, bundled Node.js is exposed asMIMO_NODE, with pptxgenjs/react/react-dom/sharp/react-icons/mathjax-full preinstalled inMIMO_NODE_MODULES— run scripts asNODE_PATH="$MIMO_NODE_MODULES" "$MIMO_NODE" <script.js>instead ofnpm install.
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.
- create.md 30 KB
- edit.md 16 KB
- LICENSE 1.4 KB
- read.md 9.3 KB
- scripts/assemble.py 2.9 KB runs code
- scripts/contact_sheet.py 5.5 KB runs code
- scripts/diagnose.py 4.4 KB runs code
- scripts/dump_text.py 13 KB runs code
- scripts/explode.py 3.4 KB runs code
- scripts/insert_slide.py 10.0 KB runs code
- scripts/preview_server.ts 6.3 KB runs code
- scripts/preview.ts 4.1 KB runs code
- scripts/prune.py 13 KB runs code
- scripts/render_pdf.py 1.2 KB runs code
- scripts/render_slides.py 2.2 KB runs code
- scripts/soffice_bridge.py 9.5 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.
- 2d ago First seen · 560 lines · 183 tokens per session scan D 78b4ff712e44
pptx-official is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,904 stars, last pushed 2d ago), licensed MIT. It adds 183 tokens to every session and 6,976 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
xiaomi-tts
Use this skill when the user wants to convert text to speech using Xiaomi MiMo's TTS models (mimo-v2.5-tts). Uses OpenAI-compatible chat/completions API with audio response. Supports multiple preset voices and custom voice design. Use when 用户提到 语音合成、文字转语音、TTS、朗读、读出来、生成语音、 生成音频、文本转音频、配音、念出来、小米语音、MiMo 语音、小米 TTS。.
byok-custom-model
Register a custom LLM endpoint with your own API key for chat in Starchild. Use when adding a personal Anthropic, OpenAI, Grok, Qwen, DeepSeek, Meta (Muse Spark), NEAR AI, or Venice key as a chat model (e.g. add my Claude key, register DeepSeek, use Muse Spark 1.1).
deepseek-vision
MUST use when the user sends or asks about images, photos, screenshots, pictures, audio, video, or mixed media documents, including requests to OCR/read text from an image. Route all media through Xiaomi MiMo V2.5 (mimo-v2.5) and mimo-v2.5-asr via scripts/mimo.py; never use local OCR, viewimage, native vision…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…