Personal agent toolkit: workflow agents, skills, stances, and prompts for VS Code Copilot
This repository also configures its own agents. See what vscode-ai-plugin tells them →
Skill Claude Code
Use when writing durable public design prose for RFCs, proposals, architecture notes, and canonization summaries where the document must serve users, implementers, maintainers, educators, and future readers.
Skill Claude Code
Background guidance for all plugin work: keep language inside the work, focus on what we're doing, and use precise and meaningful language that stays attached to the work underway.
Skill Claude Code
Use when helping the user articulate their own thinking — when they have insight they haven't fully formed, or when the task requires the user to see something the agent can point to but not resolve.
Skill Claude Code
Use when selecting among locally valid project moves by relating them to a durable project thesis, or when new evidence should revise the route while the user's situated judgment remains authoritative about what the project is for.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: