shared-patterns
Reference reusable patterns for validation, error handling, and test scaffolding
openclaw-reflect
Self-improvement layer with evaluation separation, rollback, and tiered operator gates. Observes outcomes across sessions, detects recurring patterns, proposes improvements, validates proposals through a separate evaluator invocation, and applies changes safely with snapshot/rollback capability.
qwen-image
调用阿里云百炼（DashScope/Model Studio）平台上的千问及万相2.6模型，完成图像生成与编辑任务。 当用户涉及以下任何场景时，必须使用此 skill： - 调用千问或万相2.6模型生成、编辑图片 - 百炼平台图像相关 API - 使用 dashscope SDK 访问 qwen-image / wan2.6 模型 - 文生图、图像编辑、图文混排输出 - 用户提及 qwen-image、wan2.6-image、wan2.6-t2i 等关键词
tool-call-retry
Auto retry & fix LLM tool calls with exponential backoff, format validation, error correction, boost tool call success rate by 90%
universal-expert
百变专家 · Universal Expert Engine v5.2 任意领域的专业分析、决策支持、信息验证。 触发：说"深度分析 XXX"、"完整分析 XXX"、"全面评估 XXX"时加载。 日常闲聊/简单问答不触发。累计修复28项逻辑缺陷。
model-fallback
Multi-model automatic fallback system. Monitors model availability and automatically falls back to backup models when the primary model fails. Supports MiniMax, Kimi, Zhipu and other OpenAI-compatible APIs. Use when: (1) Primary model API is unavailable, (2) Model response time is too slow, (3) Rate limit exceeded, (4) Need to optimize costs by using cheaper models for simple tasks.
advancedmlclassificationskill
自动化生成工业级机器学习分类算法代码、调用算法做预测、输出准确率对比和可视化结果，支持新手友好的结果解读。
glm-v-model
智谱 GLM-4V/4.6V 视觉模型调用技能。用于图像/视频理解、多模态对话、图表分析等任务。 当用户提到：图片理解、图像识别、视觉模型、GLM-4V、GLM-4.6V、多模态分析、看图说话、图表分析、视频理解时使用此技能。
astrai-code-review
AI-powered code review with intelligent model routing — saves 40%+ vs always using the most expensive model
smart-model-selector
智能模型路由系统，根据任务自动选择最优 Qwen 模型（qwen3.5-plus/qwen-max/qwen-coder-plus），越用越聪明，节省成本
skill-router-bzai
Cost-effective skill selector for maximizing ROI on AI operations (增收降本版 v1.0.0). Use when the user needs to accomplish a task and wants the optimal skill chosen automatically to minimize costs while maximizing quality. Evaluates skills based on quality (35%), token cost (30%), security/reliability (20%), and speed (15%). Searches both local skills and clawhub.com, presents top recommendations for user confirmation before execution.
lmms-eval-guide
Guides AI coding agents through the lmms-eval codebase - a unified evaluation framework for Large Multimodal Models (LMMs). Use when integrating new models, adding evaluation tasks/benchmarks, running YAML config-driven evaluations, orchestrating non-blocking training-time evaluation via the HTTP eval server, or navigating the evaluation pipeline architecture.
evaluate-environments
Run and analyze evaluations for verifiers environments using prime eval. Use when asked to smoke-test environments, run benchmark sweeps, resume interrupted evaluations, compare models, inspect sample-level outputs, or produce evaluation summaries suitable for deciding next steps.
optimize-with-environments
Optimize environment system prompts with GEPA through prime gepa run. Use when asked to improve prompt performance without gradient training, compare baseline versus optimized prompts, run GEPA from CLI or TOML configs, or interpret GEPA outputs before deployment.
train-with-environments
Train models with verifiers environments using hosted RL or prime-rl. Use when asked to configure RL runs, tune key hyperparameters, diagnose instability, set up difficulty filtering and oversampling, or create practical train and eval loops for new environments.
antv-l7
Comprehensive guide for AntV L7 geospatial visualization library. Use when users need to: (1) Create interactive maps with WebGL rendering (2) Visualize geographic data (points, lines, polygons, heatmaps) (3) Build location-based data dashboards (4) Add map layers, interactions, or animations (5) Process and display GeoJSON, CSV, or other spatial data (6) Integrate maps with AMap (GaodeMap), Mapbox, Maplibre, or standalone L7 Map (7) Optimize performance for large-scale geographic datasets
database-clickhouse-weaviate
ClickHouse queries, Goose migrations, chdb test schema, Weaviate collections/migrations, or telemetry storage paths.
database-postgres
Drizzle schema, repositories, RLS, SqlClient wiring, Postgres migrations, psql / reset, or platform mappers (toDomain* / toInsertRow).
red-team-tools-and-methodology
This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate subdomains", or needs security researcher techniques and tool configurations from top bug bounty hunters.
plot-skill
Plot and compare simulation summary metrics. Use when visualizing time-series results, comparing multiple cases, or analyzing production performance. Supports single and multi-metric plots, case comparisons, and automatic metric keyword resolution.
mpx-rn-style-guide
Mpx 跨端输出 RN （简称为 Mpx2RN or Mpx2DRN）的样式适配开发指南，当用户问题或上下文中同时包含 Mpx、RN、样式三个关键要素时强制调用，如：Mpx2RN 样式适配、Mpx2RN 样式报错等。当用户问题不涉及 Mpx 跨端输出 RN 或与样式无关时不应调用，如：Mpx 输出小程序相关问题、RN 相关问题等。
add-pattern
Use this skill when you learn one or more design pattern(s) in the Langroid (multi) agent framework, and want to make a note for future reference for yourself. Use this either autonomously, or when asked by the user to record a new pattern.
