A skill that cannot be invoked by the model.

[unclosed bracket

This skill has no YAML frontmatter at all.

'Intelligent Git Flow branch creator that analyzes git status/diff and creates appropriate branches following the nvie Git Flow branching model.'

Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact', 'which embedding model', or 'quality dropped after quantization'. Also use when search quality degrades without obvious changes.

Wire channels to agent groups, manage isolation levels, add new channel groups. Use after adding a channel, during setup, or standalone to reconfigure.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent lim

Campaign attribution analysis involves systematically evaluating evidence to determine which threat actor or

Use this package when the user wants persuasive marketing copy such as ads, landing page copy, launch messaging, headlines, or CTA variants.

AI 导师 skill。用于提供简历优化策略、面试准备、职业规划、薪资谈判和多版本简历建议。当用户说“面试怎么准备”“职业规划”“薪资怎么谈”时使用。

Explore Solana's architecture and protocol internals. Covers the SVM execution engine, account model, consensus, transactions, validator economics, data layer, development tooling, and token extensions using the Helius blog, SIMDs, and Agave/Firedancer source code.

ghostshield

> 🔍 一键提取长文本核心要点，告别信息过载

系统思维技能，让 AI 具备分析复杂系统的能力

Smart LLM router — save 67% on inference costs. Routes every request to the cheapest capable model across 41 models from OpenAI, Anthropic, Google, DeepSeek, and xAI.

Evaluate franchise opportunities and manage multi-unit operations with data-driven frameworks.

OpenClaw首个生活场景Skill - 你的AI穿搭闺蜜。拍照录入衣橱、智能推荐搭配、逛街种草咨询，还有衣橱分析帮你科学购物。支持多模态识别，无需关键词，像跟闺蜜聊天一样自然。

上海话是中国最具特色的方言之一，使用吴语语法和大量独有词汇。本技能使 AI 能够流利地使用上海话与用户交流。

> 信息收集与空间测绘工具

Route tasks to the cheapest capable model. Never crash on rate limits.

Compress natural language prompts into I-Lang — AI-native structured instructions. 40-65% token savings.

>

Simulate standardized patient encounters for medical training, supporting OSCE-style history-taking practice, communication skills rehearsal, and educational debriefing.

>

帮助地球人做人生选择的 AI 判断技能 - 你只管 do it，判断交给滚滚

狗狗如厕训练 - 记录排尿日志、遛狗提醒、意外追踪、进步分析。适合成年犬行为矫正。

A clean, modular, and user-friendly image generation tool powered by [Pollinations.ai](https://pollinations.ai).

🧊 IceCube 国内变现路径 — 无需海外账户，直接人民币收款。整合小红书、微信公众号、知识星球、服务型收入等多种变现渠道。当用户提到'国内变现'、'小红书变现'、'知识付费'、'人民币收款'、'没有海外账户'时使用。

Assess whether to escalate models

**Save 30-50% on model costs through intelligent, automatic model selection.**

Estimate the cost of any AI prompt across 19+ models before you run it. Works with OpenAI, Anthropic, Google, DeepSeek, xAI, MiniMax, and local models.

Estimate the cost savings from caching frequently-used prompts across AI models.

Use when executing implementation plans with independent tasks - coordinates task execution by dispatching subagents per task with verification checkpoints, adapted for OpenClaw's isolated session model

>-

glm-v-model

Run an autonomous Open Ralph Wiggum coding loop using OpenCode Zen with free models and automatic fallback.

自动模型故障切换守护。当主模型连续失败时自动切换到可用兜底模型，稳定后自动尝试切回主模型。适用于保证 OpenClaw 服务连续性。

>

Training Machine Learning Models

Explaining Machine Learning Models

explaining-machine-learning-models

klingai-camera-control

langchain-model-inference

salesloft-rate-limits

together-common-errors

threat-model-creator

confusion-matrix-generator

cross-validation-setup

distributed-training-setup