Build publication-style figures in Microsoft Visio through the DrawForge bridge after a planner has already analyzed the source figure and produced a plan. Use when the agent needs to translate a drawing plan into layout, typography, spacing, line-style semantics, and DrawDSL, especially for research figures.
Distill reusable lessons from Visio drawing iterations in DrawForge. Use when an agent encounters a drawing problem, layout failure, export surprise, bridge recovery issue, or any repeatable obstacle during Visio work and should convert that one-off fix into a generalized lesson stored under learningskills.
Operate Microsoft Visio through the DrawForge bridge with stable atomic actions. Use when an agent needs to create sessions, add/edit/connect/style shapes, save documents, export PNG previews, or execute a prepared drawing spec without taking over planning decisions.
Bootstrap skill for DrawForge. Use this skill to onboard an agent into the DrawForge GitHub repository, understand the project structure, run the canonical cold-start smoke test, and begin working with the Visio-based drawing loop safely.
Analyze a source figure, classify the diagram family, decompose regions and elements, and produce a drawing plan before any detailed Visio drawing begins. Use when a job starts from an input image and the agent must decide what to draw first, which drawskills to invoke, which visioskills capabilities are needed, and how round-by-round critique should be structured.