eli5listed
Install: claude install-skill TeFuirnever/azhou-ai-hub
# Eli5
**🦊 阿舟 · Eli5**
> 🖼️ 把复杂讲给零基础的人,少字,多图。
Capability baseline, imported verbatim from the locked upstream commit: "Explain like I'm someone who knows nothing about this topic, using a HTML artifact with big pictures and few words." See [provenance](references/provenance.md) and the [compatibility map](references/upstream-compatibility.md).
## Brand protocol
Emit this exact display event once, at the start of every run, with the resolved topic scope:
```text
🦊 阿舟 · Eli5 启动|mode=explain|scope=<topic>
```
Use `✅ 验证通过` only after the artifact is written to disk and read back. Use `❌ 验证失败` for a write or read-back failure and `🔒 阿舟暂停这一项` when the topic is missing or the request contradicts the eli5 boundary. Emoji is display-only; keep JSON keys, schema values, digests, paths, commands, test names, and raw evidence emoji-free. A host without Unicode may remove the leading emoji while preserving the fixed text, `|` separators, fields, and values.
## Workflow
1. Resolve the topic from the user's request or the trailing argument after the `/eli5` trigger; do not require a specific harness command syntax.
2. Check the boundary before writing. eli5 is for a zero-background picture explanation. If the user asks for precision-critical material such as spec review, security analysis, migration plans, or numerical claims, emit `🔒 阿舟暂停这一项` and answer in the requesting mode instead of degrading it to pictures.
3. Produce exactly one self-contained HTML artifact: big picture