数据与 AI技能

Clean messy tabular data through OpenRefine using command-line operations. Import files, inspect rows, apply reusable JSON transformation histories, and export cleaned CSV or TSV data, with session support for undoing and redoing changes.

中文简介正在准备中。当前显示英语简介。

• Remove extra spaces from names in a CSV file
• Reuse the same cleaning steps on another dataset
• Inspect sample rows before and after transformation

Create and edit QGIS map projects from the terminal. Add geographic features and attributes, arrange maps and labels in print layouts, export PDFs or images, and run QGIS algorithms for processing geographic data.

中文简介正在准备中。当前显示英语简介。

• Creating a map project and adding points
• Adding geographic features and attributes
• Exporting labeled maps as PDFs or images

Manage Ollama models and run text generation, chat, and embeddings, which represent text as numerical vectors, through command-line requests. Check server status, inspect model details, and receive structured JSON output for agent workflows.

中文简介正在准备中。当前显示英语简介。

• Download models and inspect their details
• Generate text or chat with a chosen model
• Convert text into numerical vectors

Create, inspect, edit, and validate Dify workflow definition files from the command line. This wrapper provides access to node and connection edits, model and prompt settings, file comparisons, and import or export through the upstream CLI.

中文简介正在准备中。当前显示英语简介。

• Create a Dify workflow from a template
• Inspect and validate workflow definition files
• Edit nodes and their connections

Manage ChromaDB collections and documents from the command line, and search by meaning rather than exact wording. JSON output supports automated agent workflows, while server checks and an interactive mode help with everyday database operations.

中文简介正在准备中。当前显示英语简介。

• Manage document collections in ChromaDB
• Search stored documents by meaning
• Feed JSON results into agent workflows

Process 3D scan data with CloudCompare through text commands. Clean point clouds, collections of measured 3D points, extract ground surfaces, align scans, calculate distances, and convert or export point clouds and surface meshes in supported formats.

中文简介正在准备中。当前显示英语简介。

• Remove noise and reduce point counts in LiDAR scans
• Extract ground points from buildings and vegetation
• Align two scans and calculate distances between them

Perform mathematical calculations and descriptive statistics, summaries of a dataset, using information already supplied with sources. Report expressions, units, and assumptions so results can be checked, and identify missing data rather than guessing.

中文简介正在准备中。当前显示英语简介。

• Calculating from data with known sources
• Summarizing a dataset with descriptive statistics
• Checking expressions, units, and assumptions

Investigate slow response starts and low cache reuse in agent applications. The skill explains how to keep instructions and tool definitions stable, append changing information, and preserve message formats so earlier processing can be reused across requests.

中文简介正在准备中。当前显示英语简介。

• Investigating slow response starts and low cache hit rates
• Deciding where to place timestamps and changing user data
• Reviewing tool order and session restoration

Design how an AI agent trims long conversations and large tool outputs while retaining decisions, constraints, failed approaches, and sources. Compare summarization strategies, choose compression triggers, and consider separate subagents to keep intermediate information out of the main conversation.

中文简介正在准备中。当前显示英语简介。

• Managing large search results and tool outputs
• Preserving decisions and constraints during summarization
• Choosing compression triggers and batch processing

Design how an AI agent finds and loads tools as needed. Compare discovery approaches, organize large tool collections, and assess tool selection accuracy, token costs, and cache reuse without placing every tool definition in the initial context.

中文简介正在准备中。当前显示英语简介。

• Designing on-demand loading for many MCP tools
• Comparing tool discovery approaches
• Investigating cache misses after loading tools

Design and evaluate how an AI agent remembers user preferences and history across conversations. Compare storage formats and memory frameworks, plan updates and compression, and distinguish personal memory from shared document retrieval while addressing sensitive information.

中文简介正在准备中。当前显示英语简介。

• Design user memory that persists across conversations
• Compare storage formats, Mem0, and Memobase
• Evaluate recall and cross-conversation reasoning

Organize the instructions, conversation history, and tool information an agent receives. Use the skill to clarify business rules, structure SKILL.md files for loading when needed, and distinguish external source material from instructions to reduce prompt injection risks.

中文简介正在准备中。当前显示英语简介。

• Reorganizing an agent's system instructions
• Reviewing SKILL.md structure and activation conditions
• Turning vague business rules into explicit decisions

Plan and review systems where several AI agents work together. Assess whether multiple agents are useful, choose roles and communication methods, and define shared files, verification, and resource limits to address conflicts, spreading errors, and uncontrolled execution.

中文简介正在准备中。当前显示英语简介。

• Deciding between one agent and several agents
• Designing agent roles and communication
• Reviewing shared files and context boundaries

Design a process for AI agents to learn from execution records. Evaluate outcomes, actions, and quality, choose whether to update knowledge, instructions, code, or model parameters, and define independent validation, release checks, and rollback procedures.

中文简介正在准备中。当前显示英语简介。

• Turning repeated agent failures into reusable guidance
• Designing evidence-based reviews of execution records
• Converting browser actions into validated workflows

Plan further training for AI agent models by diagnosing gaps in knowledge, output consistency, or decision making. Compare continued pretraining, supervised fine-tuning, reinforcement learning, and distillation, then design training data, feedback environments, and evaluation checks.

中文简介正在准备中。当前显示英语简介。

• Choosing a training approach for an agent model
• Designing training examples and source data
• Planning reward checks and reinforcement learning environments

Design knowledge systems that preserve document structure and connections across sources. Choose retrieval methods, organize conversation memory, and plan evidence-based updates, review workflows, and access controls for information that scattered text searches cannot adequately cover.

中文简介正在准备中。当前显示英语简介。

• Designing searches that combine information across documents
• Organizing and retrieving long conversation histories
• Establishing knowledge update and review workflows

Design a running status summary that keeps an agent aware of tasks, tool call counts, time, errors, and its environment. The skill covers updating that summary and balancing cache reuse against the buildup of outdated information.

中文简介正在准备中。当前显示英语简介。

• Addressing repeated tool calls and retry loops
• Keeping TODO progress and original goals visible
• Choosing how to update runtime status messages

Design and troubleshoot agent workflows that stop too early or keep repeating. The skill explains how to separate creation from review, verify real results, give actionable repair instructions, and set clear completion criteria and resource limits.

中文简介正在准备中。当前显示英语简介。

• Investigating completion claims made before tests run
• Designing separate creator and reviewer agents
• Resuming long tasks from verified progress

Turn agent failure records into training examples by locating the first incorrect decision and pairing preferred actions with rejected ones. Assess whether training is appropriate, then check both targeted improvements and preservation of correct behavior.

中文简介正在准备中。当前显示英语简介。

• Diagnosing the first incorrect decision in an agent failure
• Building preference pairs from failure records
• Choosing between system fixes and model training

Build an evaluation process for AI agents using success, reliability, cost, and latency measures. Define scoring criteria, repeatable environments, failure analysis, and regression tests that check for recurring problems to support model selection and system improvements.

中文简介正在准备中。当前显示英语简介。

• Building an initial agent evaluation process
• Comparing models on actual work tasks
• Investigating a drop in evaluation scores

Design and improve retrieval for RAG, which supplies external knowledge to AI answers. Cover document splitting, semantic and keyword search, combined result ranking, and quality measurements to identify where relevant information is being missed.

中文简介正在准备中。当前显示英语简介。

• Building search for a knowledge base
• Comparing semantic, keyword, and hybrid search
• Diagnosing missed search results

Design rewards for reinforcement learning, where feedback guides model behavior. Choose how to score outcomes and intermediate actions, check for scoring loopholes, and use independent tests to detect incomplete work presented as finished.

中文简介正在准备中。当前显示英语简介。

• Designing rewards for reinforcement learning
• Investigating scoring loopholes and early completion
• Choosing outcome rewards or intermediate feedback

Revisit a recent answer, plan, draft, or decision using selected critique methods. The skill offers relevant approaches, explains what they reveal, and proposes improvements that are applied only after the user accepts them.

中文简介正在准备中。当前显示英语简介。

• Examining assumptions in a plan
• Reviewing a draft from several perspectives
• Exploring failure risks before a launch

Build and troubleshoot TorchDrug 0.2.1 workflows for molecular property prediction, molecule generation, protein modeling, and knowledge graph reasoning. Connect datasets, models, training tasks, and evaluation while checking version compatibility and common implementation errors.

中文简介正在准备中。当前显示英语简介。

• Training and evaluating molecular property prediction models
• Building molecule generation workflows
• Learning representations of protein sequences and structures