'capability' 검색 결과

Combine capabilities from multiple fine-tuned LLMs without retraining using mergekit. Choose a merging method, configure how models are blended, and evaluate the resulting model on tasks such as math, code generation, and conversation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Combining math, coding, and conversation capabilities
• Blending two models at different ratios
• Comparing variants made with different merging methods

Check how much conversation capacity context-mode has saved during the current session. View token consumption, the context savings ratio, and a breakdown by tool in full tables, with one sentence highlighting the main savings figure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking context savings in the current session
• Reviewing token consumption
• Comparing usage statistics across tools

Turn a feature into an agent skill or improve an existing one. Define purpose-specific quality criteria, review outputs with models from three providers, then add tests and check that user requests reach the intended skill.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a reusable feature into an agent skill
• Audit an existing skill for missing parts
• Check quality after fixing or extending a skill

Manage shell commands and AI agent tasks through a shared gbrain job queue. Track progress, steer agents, pause or resume work, and coordinate parallel tasks, with guidance for long operations, completion reporting, and reusable stage checkpoints.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run scripts as monitored background jobs
• Coordinate parallel research by AI agents
• Redirect, pause, or resume an agent task

Enable NanoClaw agents to deploy web applications to Vercel. The skill installs the Vercel CLI, a command-line tool, and configures automatic credential injection through OneCLI, supporting production deployment and deployment status checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Enabling Vercel deployment for NanoClaw agents
• Configuring Vercel credentials through OneCLI
• Adding deployment tools to existing agent groups

Investigate failures in an existing Zoom integration by checking authentication, requests, SDK setup, media behavior, and MCP connections. The skill identifies the likely failing component and returns prioritized hypotheses, a short fix plan, and verification steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate Zoom authentication and app configuration errors
• Check failed webhooks and event verification
• Diagnose SDK meeting joins and media session issues

Update main specifications from delta specs, documents describing intended changes. Apply requirement additions, edits, removals, and renames while preserving unrelated content and keeping the change active for further implementation work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reflect requirement changes in main specifications
• Add scenarios while preserving existing ones
• Create main specifications for a new capability

Connects supported AI clients, including Claude Code and Codex, to OpenWork through MCP, a protocol for accessing external tools. It guides account sign-in and verifies that tools for finding and running organization capabilities are available.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connecting an AI client to OpenWork organization resources
• Signing in and verifying available MCP tools
• Switching organizations or troubleshooting authentication

Find and use skills, shared tools, and connected services available in an OpenWork organization. Match a requested outcome to an available capability, run it with the required parameters, and explain any connection or permission steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding skills available within an OpenWork organization
• Searching shared tools and connected services by intended outcome
• Running available OpenWork Cloud operations

Find and manage agent skills in the Gemini Enterprise Agent Platform Skill Registry, a catalog of available capabilities. The skill supports searching, uploading, updating, deleting, inspecting revision histories, checking operation status, and creating local starter files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Search for skills that provide a needed capability
• Upload or update skills in the registry
• Inspect skill details and revision histories

Find projects, skills, agents, and tools in the Kortix catalog, then adapt their files to an existing project. The skill guides source inspection, configuration merging, and preparation of a change request for user review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find skills and tools in the Kortix catalog
• Import selected parts of a ready-made project
• Adapt an external agent to an existing project

Evaluate AI agent outputs with code checks and model-based grading. Run repeated trials to measure reliability, compare prompts or models, and check whether changes reduce quality, with saved transcripts for reviewing the results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing two prompts on the same test cases
• Checking quality after agent configuration changes
• Turning real failures into repeatable evaluation cases

Helps extend an iii system by checking live functions, searching the public worker registry, and writing a worker when needed. Covers TypeScript SDK calls, event triggers, error handling, and worker operation through Compose.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding and calling functions already available in iii
• Searching for and adding a published worker
• Building a custom worker with the TypeScript SDK

Build a runnable prototype from a plain feature request, then add capabilities one step at a time. The skill records consequential assumptions before coding, checks each step, and reports remaining placeholders, deferred work, and review limits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a runnable prototype from a feature description
• Extending a prototype through checked feature steps
• Recording decisions where requirements are unclear

Turn a feature request into a working prototype, starting with a minimal path from input to output and adding features through individual checks. Record consequential assumptions before coding, then use a separate model to find decisions missing from that record.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a working prototype from a feature description
• Extending a prototype one checked feature at a time
• Recording assumptions made during implementation

Routes requests involving 飛書/Lark to the appropriate feature guides. It helps an agent select the relevant capabilities, load their instructions, and combine multiple capabilities in the order needed for a task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing the right capability for a Lark request
• Combining multiple Lark capabilities in sequence
• Working with Lark resources hosted on doubao.com

Combine specialized language models without retraining using mergekit. The skill explains how to choose merging methods, configure each model’s contribution, compare resulting variants, and prepare a merged model for evaluation and deployment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Combine math, coding, and conversation capabilities
• Compare model variants with different merge weights
• Choose a method for merging several models

Compress large language model weights to four bits with AWQ, a method that uses model activation patterns to limit quality loss. Follow workflows for quantization, loading compressed models, and serving them with vLLM using less GPU memory.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running large language models with limited GPU memory
• Quantizing a model with domain-specific text
• Serving an AWQ model with vLLM

Build custom WordPress themes, plugins, and editor blocks, extend WooCommerce stores, and add REST API endpoints. The skill also guides input protection, permission checks, caching, and database query tuning to improve security and performance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build custom WordPress themes and plugins
• Create Gutenberg blocks and block patterns
• Extend WooCommerce stores and REST API endpoints

Plan and review new Omnigent harness integrations, the adapters connecting agent runtimes to the platform. Compare SDK and subprocess approaches with native interface wrappers, using capability matrices and checklists for implementation and testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan a new agent runtime integration
• Compare SDK and native integration requirements
• Review approval, streaming, and session support

Diagnose paid advertising performance using account evidence, financial constraints, and experiments. Draft ranked changes to budgets, bids, or ad delivery, and apply supported operations only after approval and state checks, retaining a way to reverse them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing budget allocation and bids
• Planning ad pauses and creative rotation
• Assessing search terms before adding negative keywords

Prepare paid advertising launches by checking campaign settings, assets, tracking, and policy eligibility. Produce a detailed change plan, then apply supported, tested operations only with explicit approval, remote verification, and a rollback record.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Draft a campaign launch plan
• Check settings and assets before publishing
• Apply an explicitly approved launch plan

Help a spawned worker check which date-range helpers and external integrations are available and how to call them. The catalog explains environment settings, local broker access, and availability checks so the worker can choose tools for its task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking available tools when a worker starts
• Looking up calls for Slack replies or shared knowledge searches
• Checking date-range helpers before querying external services

Look up exact syntax, options, JSON output, defaults, and error meanings for a known OpenRig command. Use the reference to check command behavior and diagnose runtime differences against the installed help and running daemon.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking required flags for a known rig command
• Looking up queue commands and handoff syntax
• Investigating command errors and daemon compatibility