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/design-qanpx skills add XiaomiMiMo/MiMo-Code --skill design-qagit 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 | $0.00068 | $0.02048 |
| Opus 5 | $0.00034 | $0.01024 |
| Sonnet 5 | $0.00014 | $0.00410 |
| Haiku 4.5 | $0.00007 | $0.00205 |
Grade A, and why
design-qa 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 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.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- product-design-design-qa — 91% identical, 25 lines differ
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design QA
Use this internal helper to compare a prototype's source design against the rendered implementation before handoff.
Do not use this skill for broad UX critique, design critique, product audits, or flow reviews. Use audit for those user-facing requests.
Use this skill before every Product Design build handoff.
A passing QA run requires both:
- a source visual target: Figma node, image, screenshot, mockup, or source capture
- a rendered implementation: local URL, deployed URL, app screen, component, or screenshot
If either artifact cannot be opened, captured, or compared, write design-qa.md with final result: blocked and name the blocker. Do not let the build skill hand off as done.
Critical Overrides
Follow critical-overrides.
Workflow
Compare the intended design to the implementation as a product-quality reviewer, not as a generic aesthetic critic. The output must be a prioritized fix list grounded in evidence from both artifacts.
Do not write the QA review from memory, code, or file paths alone. Open or capture both the source design and the implementation first, then compare what is actually visible.
Do not pretend separate image views are side-by-side comparison. Put the source image and the implementation screenshot together in the same comparison input, then judge the visible differences from that combined input.
Design QA is an iteration loop. The first comparison may pass only when it finds no actionable P0/P1/P2 differences and no visual fixes are made in response.
When a comparison finds any P0/P1/P2 issue:
- Record the finding and keep the current result blocked.
- Apply the fix.
- Capture the revised implementation at the same viewport and state.
- Compare the revised capture against the source again.
A later pass must identify the earlier findings, the fixes made, and the post-fix visual evidence. Build, dependency, lint, deployment, and preview troubleshooting do not count as design-QA iterations.
What ships with it
2 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.
- 2d ago First seen · 149 lines · 68 tokens per session scan A a761ed96e1e9
design-qa is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,904 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 2,048 once invoked, about $0.0003 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
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…