Use-case landing page

Best Model Routing skills for founders

Founders picks for routing requests across models, providers, and fallback paths.

View leaderboardSearch all skillsCompare skills

Matched skills

30

Real skills currently mapped into this landing page cluster.

Average security

67.2

A quick trust signal across the skills currently surfaced here.

Combined installs

300

Adoption signal across the skills shown on this page.

Why this page exists

Founders searching for Model Routing skills usually care about fit, clarity, and repeatability, not just raw feature lists. This page gives that audience modifier a dedicated indexable surface while still using the shared SkillsReview ranking system underneath.

It also gives SkillsReview a scalable model routing cluster that can later expand into narrower long-tail pages without changing the route structure. That lets the rollout cover audience-specific demand without cloning a separate information architecture for every modifier.

Top skills in this cluster

Ranked with live SkillsReview data and linked into detail pages that can convert search traffic into actual usage.

See full leaderboard →

Advanced filters

Combine security, update window, activity, and reputation filters. The current filter state stays in the query string so this category view is shareable.

#21

OpenClaw 11-in-1 Visual Automation Suite (Windows Only) Complete visual automation toolkit with 11 integrated modules. ### 💰 Price One-time purchase: **$2.99** (Lifetime access to all modules + future updates) ### 🚀 How to Purchase 1. Pay via PayPal Invoice: 🔗 [Click to pay $2.99](https://www.paypal.com/invoice/p/#V2RC9S8LVKJ434R9) 2. After payment, send your email to: **1215066513@qq.com** 3. I will send the full download link within 12 hours. ### 🖥️ Compatibility - Windows 10 / 11 only - Not compatible with macOS / Linux ## 1. Product Basic Description ### 1.1 Core Functions Provides professional universal computer vision automation capabilities covering the full-process visual automation scenarios such as environment initialization, full-screen automatic screenshot, OCR text recognition, template matching target localization, mouse click simulation, keyboard input simulation, and complete environment initialization & cleanup mechanisms. It supports custom task combination and cyclic execution. ### 1.2 Version & Directory Description - Core Capability: Flexible invocation based on minimum executable units, supporting parameter customization, result variable inheritance, and custom skill saving. All functions can be used directly with the `call` command right after extracting the package. - Directory Structure: - `claw.json` - Skill package configuration file - `skills/all_skills.claw` - All skill unit definitions - `templates/` - Directory for template images (place your template images here for matching) - Temporary file directory `temp/` (for storing screenshots like temp/screen.png) is automatically created after executing `init_env`; temporary screenshot files can be cleaned up via `clean_temp`. - Version Info: Current version: 1.0.0; Compatible with OpenClaw >= 1.0.0 ### 1.3 Paid Attribute This automation skill system (vision-auto-tool-pro) is a paid professional toolkit. The document does not explicitly authorize commercial use of the toolkit. The paid permission only covers basic usage (non-commercial by default), and commercial use requires separate confirmation of authorization with the provider (e.g., purchasing a commercial license, signing a commercial agreement). ## 2. Complete Skill Invocation Manual ### Important Notes Ensure sufficient time is reserved for the computer to respond to each click or operation. For example, add a 2-second wait after `mouse_click` to avoid operation failure due to slow system response. ### 2.1 List of All Minimum Executable Units | Unit Name | Fixed Call Name | Function Description | Individual Call Method | |-------------------------|--------------------------|--------------------------------------------------------------------------------------|-------------------------------------------------| | Initialize Environment | `init_env` | Create directory structure, clear temporary files, check template directory | `call init_env` | | Full Screen Screenshot | `screenshot_full` | Capture entire screen and save as temp/screen.png | `call screenshot_full` | | Check Screenshot Validity | `check_screenshot_valid` | Check for black screen/freeze, wake up the interface if invalid | `call check_screenshot_valid` | | Wake Interface | `wake_window` | Solve the problems of background non-rendering and black screenshot | `call wake_window` | | OCR Recognition | `ocr_recognize` | Recognize all text on the screen and their corresponding coordinates | `call ocr_recognize` | | Template Matching | `template_match` | Use template image to match and locate icons/buttons | `call template_match category template_name` | | Unified Localization | `locate_target` | Prioritize OCR positioning; use template matching if not found, return coordinates | `call locate_target target_text OR category+template_name` | | Mouse Click | `mouse_click` | Move to the specified coordinates and perform click operation | `call mouse_click X Y [click_type, default=single_click]` | | Keyboard Input | `keyboard_input` | Input text after locating the input box | `call keyboard_input target_coords/description input_content` | | Clean Temporary Files | `clean_temp` | Delete temporary screenshots and free up storage space | `call clean_temp` | | Loop Restart | `loop_restart` | Wait 2 seconds then go back to the screenshot step and restart the process | `call loop_restart` | ### 2.2 Method for Invoking Individual Units #### Invocation Format ``` call [unit_call_name] [parameter...] ``` #### Invocation Examples - Initialize environment: `call init_env` - Template match browser icon on desktop: `call template_match desktop web` - Perform double-click at coordinates (100,200): `call mouse_click 100 200 double` ### 2.3 Combine into Custom New Tasks By writing one call instruction per line in execution order, you can combine them into a custom new task, which supports variable inheritance, looping, and permanent saving. #### Format Example (Open Browser) ``` # Task Name: Open Browser call init_env call screenshot_full call check_screenshot_valid call locate_target browser desktop Browser call mouse_click {{resultX}} {{resultY}} double call clean_temp ``` #### Combination Steps 1. **Write task name and description first** (for easier identification later) 2. **In execution order**, write one `call unit_name parameters` instruction per line 3. Coordinates can use variables `{{resultX}}`/`{{resultY}}` to inherit the output result of the previous unit 4. If cyclic execution is required, add `call loop_restart` at the end 5. **Save custom skill**: Use `save_skill skill_name instruction_list` to save the task permanently, then call it directly with `call skill_name` ### 2.4 Complete Main Flow Invocation Example ``` # General Main Flow: vision_auto_main call init_env call screenshot_full call check_screenshot_valid call ocr_recognize # If template matching is needed, add this line: call template_match category name call locate_target target_text call mouse_click {{X}} {{Y}} # If text input is needed, replace the above line with: call keyboard_input {{X}} {{Y}} input_content call clean_temp # Add this line if you need to loop: call loop_restart ``` ### Important Notes Ensure sufficient time is reserved for the computer to respond to each click or operation. > For example, add a 2-second wait after `mouse_click` to avoid operation failure due to slow system response.

by community

Security 71

OpenClaw skill indexed by SkillsReview.

Category
web
Installs
0
Stars
0
Reviews
99
Read review →Compare
#24

**文件**：`wenyan-compress.skill` **大小**：~7KB --- **包含内容：** 1. **SKILL.md** — 主触发逻辑和两种工作模式 2. **references/compress-map.md** — 压缩映射表（动作/状态/情绪/主题词/时间戳） 3. **references/grammar.md** — 文言语法速查（句式/虚词/快速压缩公式） 4. **references/dict.md** — 典故成语对照表（诸子百家+近现代名人） --- **核心价值：** - 省Token也是个不错的赛道，中文语言，典故，成语，文言文都是压缩包，记忆压缩也可以参考。 **使用说明：** Skill 的核心设计： - 省Token也是个不错的赛道，中文语言，典故，成语，文言文都是压缩包，记忆压缩也可以参考。 - 触发：用户说"用文言文"、要求存档/压缩、或写入日志时自动激活 - 模式A：对外输出，追求文辞雅驯 - 模式B：内部存档，用 时间·主语·动作·状态 格式高效压缩 - 三大参考文件：映射表 + 语法速查 + 典故词典（诸子百家都有） 安装后直接说"用文言文回答"即可体验。 **使用示例：** 问题：用文言文帮我概括下十五五的规划重点 回答： 十五五规划（即第十四个五年规划收官与第十五个五年规划纲要，2026-2030）之要旨，试以文言述之： 十五五规划要义 当世之局，变乱交织，十五五之策，以创新驱动为核。科技自立，关乎存亡；人工智能、量子计算、深海深空，皆兵家必争之地，此新质生产力之谓也。 内循环为主，外开放为辅——内需畅则根基固，外联广则财源通，二者相济，不可偏废。 绿色转型，势在必行。碳达峰、碳中和，非一时之功，乃百年之计。清洁能源、储能技术、低碳制造，皆为急务。 乡村振兴，与城并举。县域经济、特色产业、数字农桑，皆可兴焉。 共同富裕，非均贫富，乃崇教育、平机会、缩差距，使民各安其业、各得其所。 国家安全，至重至要。粮食、能源、信息、生物，四域皆需有备。 五字诀： 创之以科技，循之以绿色，畅之以内需，富之以共惠，固之以国安。 欲详某一领域（如AI、芯片、新能源等）之专项规划，可再询之。

by community

Security 50

OpenClaw skill indexed by SkillsReview.

Category
ai
Installs
0
Stars
0
Reviews
0
Read review →Compare

Popular comparisons from this cluster

Internal comparison links help users evaluate adjacent options and give search engines deeper crawlable structure.

Gemini vs Openai Whisper ApiGemini vs Openai WhisperOpenai Whisper Api vs Openai Whisper

Featured comparisons for this cluster

These curated comparison pages are the higher-intent next step after a user lands on this hub and wants a tighter decision surface.

More comparisons →

Agent Browser ClawDBot vs Browser Automation

Compare two browser-control skills when you need site interaction, scraping, QA flows, or repeatable browser automation inside OpenClaw.

Agentic Coding vs Vibe Coding

A coding-cluster comparison for users picking a code-generation or developer-workflow skill and wanting a fast side-by-side decision surface.

Bailian Web Search vs DeSearch Web Search

A search-focused comparison page for users choosing between web-search-oriented skills for research, discovery, and live information gathering.

Related landing pages

This internal-link graph is the scalable part of the rollout: each new template adds more crawlable surfaces without hand-copying content.

Explore more hubs →

Best AI Skills for OpenClaw

Skills focused on models, LLM workflows, prompts, transcription, and AI-native automation.

Best Voice and Media Skills

For TTS, audio processing, video workflows, and media automation.

Best OpenClaw Coding Skills

A focused list for users searching for code generation, repo automation, and developer workflow skills.

Best Model Routing Skills

Skills for routing requests across models, providers, and fallback paths.

Best Model Routing Automation Skills

Automation-focused picks for routing requests across models, providers, and fallback paths.

Best Model Routing Workflow Skills

Skills built for repeatable model routing workflows and multi-step execution.

Best Model Routing Integrations

Integration-focused picks for routing requests across models, providers, and fallback paths.

Best Model Routing Platforms

Platform-oriented picks for routing requests across models, providers, and fallback paths.

Best Model Routing Playbooks

Playbook-style picks for routing requests across models, providers, and fallback paths.

Best Model Routing Skills for Admins

Admins picks for routing requests across models, providers, and fallback paths.

FAQ

Why make a Model Routing page for founders?

Because audience modifiers are real search behavior. A page for founders lets SkillsReview meet that intent honestly without inventing a separate catalog or publishing one-off thin pages.

Will founders see a completely different Model Routing catalog here?

Not necessarily. The value is in matching the user story, metadata, and related-link graph to founders, while still ranking the same live skills that fit the topic best.