Long-running workflows need a reliable way to stop without leaving stale state. This skill outlines a Redis-backed stop design, API flow, frontend option, and tests.

Interactive workflow nodes require coordinated backend, frontend, history, and localization changes. This skill gives Claude, Codex, and Claude Code a focused implementation guide for FastGPT interactive responses.

Complex responses are difficult to review in plain text. Lavish creates interactive HTML artifacts that collect visual annotations and structured feedback.

Creating polished images and consistent visual sets requires detailed prompts and repeated API work. This skill prepares requests, calls Seedream, and downloads the results.

Home Assistant changes can be risky when deployments, reloads, and dashboards are handled manually. This skill gives Claude, Codex, and Claude Code structured workflows for validation, deployment, testing, and troubleshooting.

Sharing small pages and files can require hosting setup. This skill publishes text, Markdown, JSON, files, or static sites to Brewpage and returns a URL.

Coding-agent projects can drift when tasks, scope, and checks are vague. This skill gives PM templates and review rules that keep Claude, Codex, and Claude Code work bounded and verifiable.

Obsidian users need fast note operations without manual navigation. This skill uses the Obsidian CLI to read, update, search, and debug vaults.

Web pages often include navigation, ads, and layout text that waste tokens. This skill uses Defuddle CLI to extract cleaner Markdown for Claude, Codex, and Claude Code.

Academic submissions often fail because formatting rules vary by venue. This skill provides templates, requirements, and examples for faster preparation.

Large tabular datasets often exceed local memory and make pandas workflows slow. This skill guides Claude, Codex, and Claude Code through Vaex workflows for lazy analysis, conversion, visualization, and ML.

Patent and trademark research often requires several USPTO data sources. This skill gives Claude, Codex, and Claude Code focused workflows for USPTO API research.

Symbolic math tasks can become error-prone when formulas need exact algebraic results. This skill guides Claude, Codex, and Claude Code through SymPy workflows for solving, simplifying, differentiating, integrating, and generating mathematical output.

Scientific teams need clear diagrams without slow manual drawing. This skill turns detailed prompts into reviewed schematics, pathways, flowcharts, and architecture figures.

Early research planning often stalls when teams rely on familiar assumptions. This skill guides structured scientific brainstorming to surface new angles, methods, and research gaps.

Current literature searches can be slow and hard to verify. This skill uses OpenRouter access to Perplexity Sonar models to find scholarly sources, summarize findings, and return citations.

Cheminformatics work often needs precise molecule parsing, descriptor calculation, and structure search. This skill guides Claude, Codex, and Claude Code through RDKit workflows with focused references and scripts.

DICOM files contain complex image data and medical metadata that are hard to inspect safely. This skill guides Claude, Codex, and Claude Code through pydicom workflows for reading, converting, anonymizing, and extracting DICOM data.

Bulk RNA-seq differential expression requires careful count preparation, design selection, and result interpretation. This skill guides PyDESeq2 workflows from input checks to tested genes, plots, and saved results.

Reinforcement learning experiments slow down when environments and training loops cannot scale. PufferLib helps Claude, Codex, and Claude Code design faster vectorized training workflows.