Menu
Smart router for 102 Chinese AI prompt templates from yao-open-prompts.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | yao-prompt-router |
| description | Smart router for 102 Chinese AI prompt templates from yao-open-prompts. |
| version | 1.0.0 |
| author | Vivi |
| tags | ["prompts","ai-agents","content-creation","marketing","geo"] |
| platforms | ["all"] |
| dependencies | [] |
102 Chinese AI prompt templates, one natural-language entry point. Say what you need, get the right template.
# Install prompt files
./install.sh
# Then in Claude Code, just say:
# "Help me write a Xiaohongshu post" -> matches Xiaohongshu Expert
# "Optimize this title" -> matches Title Optimizer
# "Make a GEO strategy" -> matches GEO series
When triggered, follow these steps exactly:
Extract from user's natural language:
Before matching prompt templates, check if a more capable installed skill exists:
| Intent | Check Skill | When to use |
|---|---|---|
| PPT / slides | any2deck | Full slide generation |
| WeChat long article | khazix-writer | Complete writing system |
| Style cloning | style-clone | Professional style extraction |
| Anti-AI detection | anti-wechat-ai-check | WeChat compliance |
| Contract review | contract-review-pro | Professional review |
| Deep research | hv-analysis | 10k-word analysis |
| Frontend / landing page | frontend-design | Production-grade UI |
| Form filling | fill-form | Auto form detection |
| Expense report | expense-report | Invoice to Excel |
| Image generation | image-creator | Multi-engine output |
| Book writing | write-professional-book | Multi-chapter books |
| Thesis polish | thesis-polish | National-level quality |
| Translation review | translation-review | 6-dimension review |
| Business proposal | proposal | Proposal + quote |
| Event planning | event-curator | Complete event plan |
If matched, inform user: "Detected {skill} is installed, it handles this better. Use it?"
From prompt-index.json or the catalog in docs/prompt-catalog.md, match 1-3 best templates.
Priority rules:
Category quick match:
.md file from ~/.claude/skills/yao-*/## Prompt section{{variables}} or [placeholders] -> ask user to fillMatched: "{title}"
Category: {category}/{subcategory}
Source: {file_path}
[If installed skill available, note here]
Loading template...
---
[Execute as the prompt's role]
| # | Category | Count | Key scenarios |
|---|---|---|---|
| 1 | AI Methods | 8 | Meta prompts, reverse engineering |
| 2 | AI Work | 10 | Research, contracts, PPT, landing pages |
| 3 | AI Learning | 3 | Keywords, memory, habits |
| 4 | AI Life | 2 | Health report, parent-child songs |
| 5 | AI Education | 1 | Children's interactive learning |
| 6 | AI Content | 46 | Copywriting, platforms, industries |
| 7 | AI Coding | 1 | System architecture |
| 8 | AI Marketing | 28 | GEO full pipeline |
| 9 | AI Thinking | 3 | Memory palace, self-critique |
Full catalog: docs/prompt-catalog.md
See install.sh or README.md.
Template not found? Ensure yao-open-prompts is installed: ls ~/.claude/skills/yao-*/
Wrong match? Tell the router what you need more specifically. It re-matches on clarification.
Skill conflict? Router always asks before redirecting to an installed skill. You can choose the prompt template instead.
Open local review artifacts in Xiaoer Omia when users ask to open, preview, inspect, or review a file.
Run a measured improvement loop for a skill by defining a yes/no checklist, capturing a baseline, scoring candidate outputs, and logging each iteration's keep/revert decision. Use when a skill works inconsistently and you want evidence-driven iteration instead of random prompt edits.
Build a static HTML report site from CSV, JSON, Markdown, or HTML inputs. Use when the user wants to turn existing data into a human-readable site, generate a data showcase page, create a static report website, or optionally publish the built site.
Add offline multilingual support to static HTML, small web projects, or reports by extracting text into tokens, maintaining language dictionaries, applying translated outputs, and optionally embedding a local language switcher. Use when the user asks for bilingual support, tokenizing Chinese copy, offline language switching, or i18n for reports and lightweight sites.
Unified entrypoint for Obsidian note operations such as cleanup, merge, lint/fix, meeting archive, daily rollover, and docs sync. Use when the user wants one command surface over an existing notes-tools repo instead of calling many atomic scripts by hand.
Test, tune, and regression-check LLM system prompts with a golden dataset. Use when the user wants to optimize a prompt, run prompt regression tests, manage `cases.yaml`, compare expected vs actual outputs, or follow a TDD workflow for prompts.