agent-skills

Use when the user asks you to analyze a repository, draw an architecture diagram, analyze a workflow/process, or explain something through a visual diagram. Prefer this skill whenever structured relationships, flows, states, sequences, or decision paths need to be communicated clearly. Do not use for general image generation or non-Mermaid charting tools.

Reference for klaude-code configuration, skill installation, and memory file locations. Use when the user asks about configuring models, installing skills, setting up providers, or wants to know where config/skill/memory files live and how they take effect.

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.

Create beautiful, performant SVG animations and illustrations. Use this skill when the user asks to create SVG graphics, icons, illustrations, animated logos, path animations, morphing shapes, loading spinners, or any animated SVG content. Covers SMIL animations, CSS-driven SVG animation, path drawing effects, shape morphing, motion paths, gradients, masks, and filters.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use whenever the user mentions "create a skill", "make a skill", "turn this into a skill", "skill for X", or wants to capture a workflow as reusable instructions.

Best practices for Remotion - Video creation in React

Use when the user asks to generate or edit images with Nano Banana / Nano Banana Pro (users often call these models 'banana'). Nano Banana (aka Nano Banana 2) maps to `gemini-3.1-flash-image-preview`; Nano Banana Pro maps to `gemini-3-pro-image`.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Search and analyze session logs (older/parent conversations) using jq. Use this skill when the user asks about prior chats, parent conversations, historical context, or session cost/usage analysis. Triggers include "session logs", "previous conversation", "what did we discuss", "session cost", "session history".

Search the web for up-to-date information and research topics. Use this skill when the user asks to search, look up, find current info, research a topic, or needs information beyond the knowledge cutoff. Triggers include "search", "look up", "web search", "find out", "what is the latest", "current status of".