Loading...
Loading...
Found 667 Skills
Probes CLI agents (Codex, Gemini) and writes docs/environment_state.json — agent availability config for Phase 0
Use when generating images with Gemini models, choosing between Nano Banana 1/2/Pro, optimizing image generation costs, writing image prompts, or needing visual grounding with real-world reference images
Generate or edit images using Gemini's native `generateContent` via New-API. Suitable for scenarios requiring text-to-image generation, reference image editing, local PNG output, and those who want to reuse the `.sofunny-image.env` file or current shell environment variables.
Exports the project's Claude configuration (CLAUDE.md + ai-context/) to tool-specific instruction files for GitHub Copilot, Google Gemini, and Cursor. Trigger: /config-export, export config, copilot instructions, gemini config, cursor rules.
Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.
US Stock Investment Research Assistant. Supports Gemini Deep Research or Claude Native Deep Research (7-Phase + GoT). Use when analyzing 10-K/10-Q reports or generating investment research reports.
Generate and transcribe speech using Google's Gemini-TTS and Chirp 3 models. Supports Text-to-Speech (Single/Multi-speaker), Instant Custom Voice, and Speech-to-Text (Transcription/Diarization).
AI image generation using Google Gemini (Gemini) and OpenAI GPT-Image. Generate, edit, iterate, and create assets.
Load project context from .claude/ directory at the start of every task. This ensures Gemini CLI has the same coding rules, design decisions, and library constraints as Claude Code.
Cross fact-checking with 4 models: Claude + Gemini + Codex. Conduct independent checks with Opus itself, Gemini Flash, Gemini Pro, and Codex (gpt-5.3-codex) → extract issues → discuss → output a consensus report.
Read, watch, and listen to video/audio files. Use Gemini for native video understanding, or extract key frames + Whisper transcription as fallback. Use when a user sends a video/audio and asks about its content, what's in it, what someone said, etc.
Build sticker-pack prompts and GIF sticker outputs from a reference image. Use this skill whenever the user wants emoji, 表情包, sticker packs, 微信表情, reaction GIFs, image-to-sticker workflows, 4x6 expression sheets, Nano Banana / Gemini image editing, or asks to turn EmojiGen-style generation into a reusable workflow. Prefer Nano Banana models through Gemini or Vertex AI, but still use this skill when the image grid comes from another tool and only the prompt assembly or GIF production is needed.