Grasshopper workflows often require many repeated component, connection, and parameter steps. This skill provides scripts and guidance to turn MMD plans into executable Grasshopper MCP workflows.

Location work often requires separate searches, route calls, and map links. This skill combines AMap POI search, route planning, travel planning, and visualization workflows.

Building AMap web maps requires many small API choices across loaders, controls, overlays, and services. This skill gives Claude, Codex, and Claude Code structured references for producing JSAPI v2.0 map implementations.

Production ML work needs deployment, monitoring, and architecture decisions that are hard to standardize. This skill gives Claude, Codex, and Claude Code structured guidance for MLOps, LLM integration, and RAG planning.

Teams need repeatable deployment guidance without rebuilding DevOps checklists from scratch. This skill provides CI/CD, Terraform, deployment, and operations references for Claude, Codex, and Claude Code workflows.

Startup teams need secure AWS designs without overspending. This skill recommends serverless architectures, IaC options, cost controls, and deployment guidance.

Current research often needs fresh sources beyond the model context window. This skill sends a research prompt to Gemini CLI and asks for sourced Markdown answers.

Branch setup can waste time when each task needs a clean workspace. This skill creates a Git worktree and prepares local environment files.

GitHub login and repository authorization often need separate OAuth flows. This skill shows a two-connection Nango pattern for user identity, GitHub App access, and webhook processing.

Manual UI checks can miss visual regressions and take repeated effort. This skill guides browser automation with screenshots, element selection, and page inspection for verifiable web testing.

Video region cleanup is difficult when objects move across frames. This skill helps Claude, Codex, and Claude Code choose RunComfy routes for prompt-driven video inpainting.

Short AI video clips often stop before the story beat is complete. This skill guides Claude, Codex, or Claude Code to extend a user-provided video through RunComfy.

Short video generation often needs consistent characters, media references, and clear model settings. This skill guides Claude, Codex, and Claude Code through Seedance 2.0 Pro prompts and RunComfy CLI invocation.

Media model workflows often require manual setup, schema lookup, and polling. This skill gives Claude, Codex, and Claude Code practical RunComfy CLI guidance for repeatable terminal automation.

Lighting changes often require a new shoot or careful editing. This skill routes still images to RunComfy relighting models for controlled results.

Teams need a reliable way to choose the right Kling 3.0 endpoint and prepare valid generation inputs. This skill guides RunComfy CLI calls for text-to-video, image-to-video, audio, tiers, and output settings.

Manual retouching is slow when a photo needs precise local edits. This skill routes masked inpainting jobs through RunComfy models with clear CLI inputs.

Choosing the right image edit model can waste time and credits. This skill routes each edit request to a suitable RunComfy model and gives model-specific prompt patterns.

Teams need clear guidance for short AI video generation without guessing model parameters. This skill guides Claude, Codex, and Claude Code through HappyHorse 1.0 prompts, schema choices, and RunComfy CLI execution.

Image edits often drift from the source asset, especially with text, layout, and identity preservation. This skill gives Claude, Codex, and Claude Code practical RunComfy prompts for controlled GPT Image 2 edits.