데이터·AI 스킬

Change the language model used by a Worker Agent through the agt command-line tool. The controller resolves model settings, regenerates configuration, and recreates the container to apply the change without a manual restart.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Change a Worker's language model
• Apply registered model settings automatically
• Check whether a model change was accepted

Switch the Manager Agent's primary language model with a script that checks connectivity before saving configuration. You can also set how much context the model accepts and whether extended thinking is enabled.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Change the Manager's saved primary model
• Correct a model's context window setting
• Disable extended thinking for a model

Add AI chat, text generation, and agents to applications using AI SDK. The skill checks documentation and source code to guide streaming replies, external tool calls, structured results, React integration, and fixes for outdated API usage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add AI chat to an application
• Build an agent that calls external tools
• Build answers using retrieved documents

Select technologies for AI and machine learning features in .NET 8+ applications. Get task-specific plans or implementation guidance for structured predictions, text generation, document retrieval, tool-using agents, and running pretrained models locally or in production.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing libraries for classification or prediction in .NET
• Adding text generation or summarization to an application
• Designing document retrieval with source-backed AI answers

Pin the current parent thread to a chosen AI model through Weave Router while subagents keep automatic model selection. An optional effort setting controls the model's reasoning effort.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Keep the parent thread on a chosen model
• Let subagents keep automatic model selection
• Specify a model with an optional reasoning effort

View which models Weave Router can choose, grouped by provider. Enable or disable individual models or entire providers, set a preference order, and review the updated selection without restarting the router.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review available models by provider
• Enable or disable specific models
• Enable or disable an entire provider

Reconnect Codex through Weave Router using the managed configuration already saved on disk. It restores routing without running the installer again, and the change takes effect when Codex next starts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resume using Weave Router with Codex
• Restore routing with the saved configuration
• Check when routing becomes active again

Switch Codex from Weave Router back to its default provider without logging out or deleting the router configuration. The change applies the next time Codex starts and can be reversed with `$router-on`.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Return Codex to its default provider
• Turn routing off while keeping its configuration
• Check when the provider switch takes effect

Send feedback about a Weave Router model choice or model performance. A bundled script passes the feedback to the router for recording, and the agent then reports the router’s response.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comment on a router model choice
• Report feedback on model performance
• Send feedback using the short `$rf` command

Clear the model pin, a setting that holds a session to one model, in the current Codex session through Weave Router. The session continues within the same turn, and the router's response is reported.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Removing a model pin from the current Codex session
• Continuing the same turn after clearing a pin
• Using a short command to remove a model pin

Pin the current Codex session to a chosen model through Weave Router. This short alias accepts a model ID, runs the included script, and reports the router’s response while allowing the current turn to continue.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Pinning a Codex session to a chosen model
• Using a short alias for force-model
• Checking the router’s response after pinning a model

Pin the current Codex session to a specific model through Weave Router by providing its model ID. The skill applies the pin, continues the same turn, and reports the router's response.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Pinning the current Codex session to a model
• Specifying a model by its ID
• Applying a model pin while continuing the same turn

Check whether Codex is using Weave Router or its default provider. This skill runs a status command and summarizes the result in one line without changing any configuration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether Codex uses Weave Router
• Checking whether the default provider is active
• Reviewing routing status without changing settings

Submit feedback about Weave Router’s model selection or a model’s performance from the current session. This short alias passes your feedback through the included script, records it through the router, and reports the router’s response.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reporting feedback on a routing decision
• Recording observations about model performance
• Using a short alias for router-feedback

Build a data dashboard with key metrics, charts, filters, and tables. Display a compact version in chat, or publish a page for sharing, with scheduled data refreshes when ongoing updates are needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review sales metrics and trends on one page
• Share a dashboard through a public link
• Schedule updates to a shared data page

Turns collected repository statistics into an eight-panel PNG infographic. It shows pull request outcomes, timing, code changes, and human versus agent activity, with scripts to recalculate figures and check them against available source records.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Combining repository statistics into one image
• Updating an infographic with newer collected data
• Comparing human and agent contributions to pull requests

Convert SKILL.md files into SSL JSON, a structured format describing invocation conditions, workflow stages, and individual actions. Receive a validation report covering format errors, invalid references, and rejected outputs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Converting skill documents into structured JSON
• Reviewing skill stages and individual actions
• Checking workflow references and transitions

Switch automatic model selection to lower-cost options for agent tasks, either for one session or through a saved setting. Explicit model choices remain in effect, while architecture and security review tasks use a separate economy selection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing costs across a session with multiple agents
• Saving economy mode as the default setting
• Keeping explicit model choices while changing automatic selection

Plan how Squad agents separate current tasks, summarized history, and lasting reference knowledge so each launch receives relevant context. The skill provides loading rules and prompt templates; the supporting runtime is still a design proposal.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan which context agents load at launch
• Separate session history from lasting knowledge
• Design context templates for interrupted work

Choose the AI model for each agent launch using saved preferences, session instructions, agent settings, and task type. Save global or per-agent choices for future sessions and include the selected model in launch acknowledgments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose models automatically by task type
• Save a default model for all agents
• Assign a persistent model preference to one agent

Rewrite long prompts into shorter, clearer instructions for language models. Preserve essential requirements while removing repetition, defining scope, and making output formats and success criteria explicit to reduce ambiguity and unnecessary tokens.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Shortening a long prompt while preserving requirements
• Clarifying vague instructions and success criteria
• Making output formats and length limits explicit

Design ClickHouse tables, write analytical queries, and plan data loading using practical SQL and code patterns. Use it to review slow queries, build recurring summaries, and analyze user activity across large datasets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing tables for large analytical datasets
• Investigating slow queries
• Building real-time summaries

Predict patterns of gene expression and other genomic measurements from DNA sequences with Borzoi. Compare reference and altered sequences to estimate regulatory effects, generate predicted coverage tracks, and prioritize variants in regions that do not encode proteins.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing predicted effects before and after a DNA variant
• Generating predicted coverage tracks for a genomic region
• Prioritizing variants in non-coding regions

Use scGPT to convert single-cell gene expression data into numerical representations of cells and genes. These representations support clustering, data integration, cell-type annotation, and analyses of gene perturbations or regulatory relationships.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating cell representations from AnnData
• Preparing single-cell data for clustering and integration
• Annotating cell types with or without fine-tuning