Browse Skills

PCT Application prepares and checks Patent Cooperation Treaty international filings under PCT Rules 5-12. Use it to draft the request, description, claims, abstract, and drawings, assess unity of invention, and track national phase deadlines.

Prompt creates or refines prompts for Claude, GPT, Gemini, and image models. Use it when you want to turn an idea into a model-specific prompt or improve an existing one.

Prompt Engineering Guide routes to base templates for research, fact-check, image, video, and slide prompts. Use it when you need the right prompt structure or to find the relevant template section.

Prompt Variation Guide helps generate different prompt structures by model, task type, and difficulty. Use it when you need a reference for prompt variation strategies and model-specific formatting.

Research Prompt Guide provides routing and reference templates for fact-checking and general research prompts. Use it when composing verification workflows or research outputs based on IFCN principles and structured formats.

Running An Iteration executes the next pending roadmap iteration by reviewing scope, baselining sentinel scenarios, dispatching implementation and evidence tasks, and updating iteration artifacts. Use it in an iterative-development loop when advancing one iteration at a time.

Scoping The Simplest Core turns extracted requirements into a roadmap with a walking-skeleton iteration and follow-on iterations. It is used to choose the first runnable journey scenario, split stories by dependency profile, and validate scope via review.

At Vision inspects screenshots, photos, diagrams, and image paths or URLs when a task depends on visible content. Use it when direct inspection fails or when you need the inspect_image provider or CLI fallback.

Claude Historian searches past conversations, errors, sessions, files, and plans before starting fresh. Use it to recall prior fixes, decisions, and recent work in a familiar project.

Example demonstrates the skill file format used for loadable skills. Use it as a reference for frontmatter, structure, and how skill content is presented to the agent.

High Token Mode forces heavy internal computation before responding. Use it to stress test or A/B test LLM backend performance and token usage.

Keel discovers, judges, and governs load-bearing architecture for systems and modules. Use it to evaluate responsibility, interfaces, dependency direction, migration, retirement, or rewrite risk when architecture choices matter.