스킬 찾기

Inspect images and videos you generated or edited for AI watermarks and embedded origin information, then remove selected signals. The skill guides a command-line tool and reports completed operations without treating missing signals as proof of human authorship.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspecting files for AI origin signals
• Removing visible AI labels from your own media
• Removing embedded AI metadata

Check AI watermarks through Google, OpenAI, Microsoft, or Meta verification services. The skill links results to file hashes, identifiers used to verify file integrity, and records separate evidence for each configured account and verification route.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking watermarks through provider verification services
• Comparing Gemini results across configured accounts
• Recording API and browser checks separately

Build Java applications with cooperating AI agents using AgentScope Java. Guides asynchronous processing, where waiting tasks do not block execution, plus language model connections, external tools, workflow coordination, error handling, and tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a Java agent connected to a language model
• Coordinating agents in sequential or parallel workflows
• Connecting external tools through MCP

Coordinate multiple AI agents through code exploration, parallel implementation, review, and fixes. Defines roles, file ownership, task dependencies, shared progress records, and recovery procedures so separate contributions can be checked and combined into a final delivery.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Split changes across independent files
• Coordinate frontend, backend, and documentation work
• Review and fix contributions from multiple agents

Audit Kiln’s model list against provider APIs and catalogs to identify removed models and upcoming retirements. Get findings organized by provider, then mark affected entries as deprecated after reviewing and approving the proposed changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Audit Kiln’s model list for retired entries
• Identify models approaching their retirement dates
• Check model availability for a single provider

Validate a Kiln release candidate with standard code checks and selected tests against live APIs. Diagnose failures, inspect outdated model selections and coverage gaps, and produce a report with recommended actions without changing code or tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Validate a release candidate before publication
• Diagnose failures in live API tests
• Check test model selections for outdated versions

Add AI models to Kiln or find available models missing from its list. The skill checks provider model identifiers and capabilities, updates model settings, runs tests against real APIs, and drafts a Discord announcement.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a newly released model to Kiln
• Finding available models missing from Kiln
• Checking provider support for recently added models

Build a question set to check whether AI assistants mention your brand. Analyze the answers you collect, compare visibility against competitors, trace cited sources, and receive a prioritized list of opportunities to address gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Establishing a baseline for brand visibility in AI answers
• Comparing brand mentions and citations with competitors
• Tracking visibility changes each quarter

Save decisions, research findings, and work updates to Obsidian, then update related notes, daily entries, and task boards. Maintain existing pages, preserve changing facts with their history, and check for duplicates and broken links.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Save decisions and tasks from a conversation
• Connect development logs to project notes
• Check a vault for duplicates and broken links

Diagnose a Diverga installation by checking plugin registration, skill and cache synchronization, hooks, configuration, API key setup, and research project state. Receive pass, warning, or error results with suggested repair commands, without modifying files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Diagnose Diverga setup problems
• Check skill synchronization and stale plugin caches
• Verify hook execution and configuration

View a dashboard for a social science research environment with 24 specialized agents. Check configuration, project stage, human review settings, and connection readiness for paper retrieval services and other research tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check research environment configuration
• Review project stage and human checkpoints
• Find missing API settings

Create figures for machine learning papers from text or experiment data. Uses Gemini for architecture diagrams and matplotlib/seaborn for numerical charts, choosing suitable layouts and chart types while preparing consistent styling, export files, and reusable generation scripts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a methods section into an architecture diagram
• Charting model comparisons and ablation results
• Plotting training curves and confusion matrices

Turn academic papers or written content into slide images, then combine them into PowerPoint and PDF files. The workflow extracts figures from PDFs and offers outline choices, visual styles, audience settings, and output languages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create slides from an academic paper
• Reuse paper figures and tables in slides
• Prepare research slides for reading and sharing

Review English and Chinese empirical papers for formulaic language and claims that overstate the evidence. Supports revisions that preserve numbers and citations, checks bilingual consistency, and includes tools for inspecting invisible characters and file metadata.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Revising formulaic language in English or Chinese empirical papers
• Checking whether claims match tables and citations
• Aligning claims in Chinese text and an English abstract

Examine strategy, design, and difficult decisions through AI personas modeled on thinkers and engineers. The skill selects a panel, checks how members frame the problem, gathers independent analyses, and assigns a separate chair to synthesize a verdict.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare software architecture options
• Examine market entry and pricing strategies
• Review assumptions and blind spots in a decision

Create whiteboard diagrams, comparison images, logos, and social media visuals from text using Gemini 3 Pro Image. The skill helps turn requirements into detailed prompts, choose a resolution, and save generated images.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Summarize tutorial content as a whiteboard diagram
• Explore logo and icon design options
• Create a visual comparison of products or services

Build 2D game maps and backgrounds with generated artwork and explicit layout data. Check collision and route reachability, explore a playable HTML preview, and export scenes to Tiled, Godot 4 or LDtk.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a top-down map with collision and exits
• Design a side-scrolling stage
• Create battle backdrops or parallax backgrounds

Generate images, reference-based edits, and video clips from stills through configured APIs or local Codex and Grok tools. Check available generation options, configure keys, track estimated costs, and resume interrupted jobs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate an image or edit using reference images
• Animate a still image
• Check available tools and configure API keys

Generate 2D game characters, props, icons and effects, or prepare existing artwork for use in a game. The skill removes backgrounds, separates frames, adjusts size and palettes, checks results, and exports assets for game engines.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a character master still
• Split prop or effect sheets into frames
• Prepare existing frames for a game engine

Help text-only models work with images by converting visible text, layout, meaning, and visual clues into structured JSON. The skill also guides configuring image analysis providers and reporting unclear details from the returned evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reading text from an image with a text-only model
• Checking image layout and visual clues
• Locating pasted images for analysis

Generate videos from text or images, edit existing clips, and extend scenes with Gemini Omni 1.1 Flash. Includes scripts for preparing source footage, regenerating audio, refining previous results, and processing multiple video jobs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate a short video from text or a still image
• Create a transition between two images
• Change a video's style or regenerate its audio

Build applications that exchange live audio, video, and text with the Gemini Live API. Covers voice conversations, streaming transcription and translation, session recovery, authentication, and migration from older Live models in Python or JavaScript/TypeScript.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an AI app for live voice conversations
• Add real-time transcription or speech translation
• Send camera or screen frames alongside audio

Implement Gemini API applications in Python or TypeScript for text, image, video, and speech generation. Covers ongoing conversations, external tool calls, structured responses, background research, managed agents, and migration from the older generateContent API.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a chatbot that retains conversation context
• Add image, video, or speech generation to an app
• Connect external tools and return structured data

Turn written descriptions into scientific diagrams, including neural network architectures, biological pathways, and research flowcharts. Nano Banana 2 generates images, while Gemini 3.1 Pro Preview reviews them and guides regeneration when needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Illustrating neural network architectures
• Creating participant flowcharts for research
• Drawing biological signaling pathways