查找技能

为OpenClaw添加模型服务商，并通过实际回复验证连接。凭据以环境变量或文件引用的形式配置，同时验证设置并报告测试结果。

• 为OpenClaw添加模型服务商
• 通过引用配置认证凭据
• 确认模型能返回实际回复

通过Gemini CLI单次执行问答、文本生成和文件内容摘要，可指定模型及JSON输出格式，并使用管理扩展、技能、钩子和MCP连接的命令。

• 总结笔记文件
• 通过单次请求生成文本
• 以JSON格式获取回答

Create an SVG usage card from local Claude Code, Codex, Gemini CLI, and OpenCode logs. It summarizes token counts, equivalent API cost, consecutive activity days, and each agent's share for inclusion in a README or documentation.

中文简介正在准备中。当前显示英语简介。

• Displaying coding-agent usage in a README
• Sharing an activity summary across multiple agents
• Showing token counts and equivalent API cost

Restructure repeated LLM API requests so shared instructions and reference material can be cached, meaning reused across calls. Track cached input, write and storage costs, and response times to assess whether the changes actually save money.

中文简介正在准备中。当前显示英语简介。

• Reordering shared instructions in repeated API requests
• Estimating cache read, write, and storage costs
• Measuring cache hit rates and response times

Build Bengali search and AI features with guidance on consistent character encoding, word splitting, digit conversion, and safe text display. Includes patterns for cleaning training data, storing text, and handling Bengali alongside English.

中文简介正在准备中。当前显示英语简介。

• Implementing Bengali search and text input
• Cleaning Bengali text for model training
• Handling Bengali and English in chatbots

Extract reusable solutions and project conventions from completed Claude Code sessions and save them as learned skills. This deprecated version documents the older session-end workflow and explains how it differs from its successor.

中文简介正在准备中。当前显示英语简介。

• Reviewing an existing session-end learning workflow
• Organizing previously learned skills
• Adjusting pattern extraction criteria

Design text extraction for forms, invoices, and quizzes using regex, rules that match text patterns. Check extraction confidence and send uncertain items to an LLM for review, with guidance on testing and tracking processing costs.

中文简介正在准备中。当前显示英语简介。

• Extracting quiz questions, choices, and answers
• Designing extraction for forms and invoices
• Choosing between regex and an LLM

Repeat candidate searches and comparisons while keeping an append-only decision log. Record evidence, compare results with earlier winners, and check replay, freshness, and approval requirements before moving to live trading or production actions.

中文简介正在准备中。当前显示英语简介。

• Comparing candidates through repeated trials
• Keeping an evidence trail for decisions
• Reassessing earlier winners with fresh information

Turn a draft request into a ready-to-paste prompt by clarifying intent, missing context, and completion criteria. Recommend suitable ECC commands, skills, and agents, then provide full and compact versions with explanations for the changes.

中文简介正在准备中。当前显示英语简介。

• Make a vague development request more specific
• Add completion criteria and checks to a prompt
• Choose ECC commands and skills for a task

Helps write and review PyTorch models, training loops, and data loading code. Covers repeatable experiments, saving training progress, and techniques for reducing GPU memory use or improving training speed, with practical code examples.

中文简介正在准备中。当前显示英语简介。

• Writing or reviewing PyTorch training code
• Investigating inconsistent experiment results
• Improving data loading and GPU memory use

Design recommendation and ranking workflows that select the best items for a user or situation. Organize candidate retrieval, enrichment, filtering, scoring, selection, and background recording into six stages, then generate a runnable code scaffold.

中文简介正在准备中。当前显示英语简介。

• Designing personalized content feeds
• Reranking search or RAG results
• Building task prioritization workflows

Design or review repeating agent workflows with machine-checkable goals, protected boundaries, independent verification, and retry limits. It helps identify endless retries, manipulated checks, and incorrect completion while keeping final judgment with a human.

中文简介正在准备中。当前显示英语简介。

• Define completion criteria for repeating agent tasks
• Review loops for endless retries and manipulated checks
• Separate planning, building, and independent verification

Add machine learning to an existing application through a structured workflow. The skill guides problem definition, data checks, separation from business logic, and training and evaluation of a simple initial model.

中文简介正在准备中。当前显示英语简介。

• Adding recommendations to an existing application
• Checking whether training data is ready
• Integrating a prediction model with fallback rules

Design an OpenClaw agent persona from preferences or random draws. Build a consistent background, personality, behavioral boundaries, name, SOUL.md and IDENTITY.md files, plus an avatar prompt, with optional image generation through an approved skill.

中文简介正在准备中。当前显示英语简介。

• Creating an OpenClaw persona from scratch
• Exploring character ideas through random draws
• Completing a rough persona with a name and boundaries

Plan and review machine learning systems for production use, covering data requirements, repeatable training, quality checks, deployment, monitoring, and rollback. Produce concrete plans and review findings for moving model experiments into operational systems.

中文简介正在准备中。当前显示英语简介。

• Turning notebook experiments into reusable training pipelines
• Defining quality checks before releasing a model
• Investigating data leakage and training–serving mismatches

Add on-device language model features to iOS 26+ apps with Apple's FoundationModels framework. Covers text generation, summarization, extracting data into Swift types, calling custom app functions, and progressively updating screens as responses are generated.

中文简介正在准备中。当前显示英语简介。

• Adding offline text generation and summarization
• Extracting structured data from user input
• Connecting AI responses to custom app functions

Gather relevant code and background for subagents, agents assigned part of a larger task. Search broadly, assess each file, identify missing information, and refine the search for up to three cycles to assemble context for bug fixes or feature work.

中文简介正在准备中。当前显示英语简介。

• Finding relevant files for a subagent assigned a bug fix
• Gathering code patterns before implementing a feature
• Refining searches to match terminology used in a project

Clarify the availability and requirements of model serving on booked Itô GPUs. The supplied implementation does not support serving, so it reports that limitation and documents future booking verification, configuration review, and explicit confirmation requirements.

中文简介正在准备中。当前显示英语简介。

• Checking documented serving availability after an Itô GPU booking
• Clarifying limitations for an OpenAI-compatible endpoint
• Reviewing future model-serving configuration requirements

Check whether machine learning training is available for a completed Itô GPU booking. Training is currently unavailable; the skill explains this limitation and documents the requirements for a future confirmed handoff of a training plan.

中文简介正在准备中。当前显示英语简介。

• Checking training availability after a GPU booking
• Reviewing future fine-tuning handoff requirements
• Identifying booking, budget, and confirmation requirements

Find bottlenecks in large data transfers, imports, transformations, and historical data catch-up. Benchmark alternative processing methods, turn the fastest correct approach into a repeatable workflow, and verify file counts, row counts, and timestamps after execution.

中文简介正在准备中。当前显示英语简介。

• Speeding up large data imports and exports
• Reducing the time needed to load historical data
• Comparing batch sizes and worker counts

Design an LLM API workflow that controls spending through task-based model selection, budget tracking, selective retries, and caching repeated prompts. Use the examples to route simpler tasks to cheaper models and track cumulative costs.

中文简介正在准备中。当前显示英语简介。

• Reviewing costs in an LLM API application
• Choosing models by batch task complexity
• Tracking cumulative spending against a budget

Design continuous agent workflows with quality checks, evaluations, and recovery controls. Helps choose a loop pattern for the task and define how to pause, audit, narrow scope, and retry when work stalls or fails.

中文简介正在准备中。当前显示英语简介。

• Choosing a loop pattern for ongoing agent work
• Combining quality checks and evaluations
• Recovering from repeated failures or stalled progress

Design and refine an AI agent’s available actions, tool inputs, and result formats. Define recovery steps for errors, manage the information kept in context, and evaluate changes through completion rates, retries, and cost per successful task.

中文简介正在准备中。当前显示英语简介。

• Define an AI agent’s tool set and input formats
• Make tool results and next steps easier to interpret
• Specify safe retries and stopping conditions

Helps design ClickHouse tables, write analytical queries, and improve slow queries. Covers loading data in batches, preparing reusable summaries, and monitoring performance for large datasets, real-time dashboards, and time-series analysis.

中文简介正在准备中。当前显示英语简介。

• Designing tables for large-scale analytics
• Improving slow aggregation queries
• Loading large datasets in batches