The shared input-resolution and output-naming rule for the bundled rad-prompt-studio skill's three master prompts (analysis-base-prompt.md, evaluation-base-prompt.md, edit-base-prompt.md). None of those three files restate this — they all point here. Without this file present, none of them can resolve where a report…
Every kit ships a settings.json at its own root (next to AGENTS.md, README.md) — committed to git, unlike analysis/ (gitignored, local-only). Think of it like a package.json's version field: it is this repo's own source of truth for its own operational state, not a shared cross-kit file like the workspace root's…
One root, %ProgramData%\rad (Windows) / /usr/local/share/rad. Outside every repo, never committed, never published. Holds a single settings.json, skills\ (the categorized link farm), and a handful of convenience links (rad.ps1, workspace, tools, rules, prompts, analysis, spec-kits\) — every one of them a live link…
Cursor rule "testing" from SecondLifes/code-intel, covering testing — rules, the two-tier split (non-negotiable), naming — the name states the locked-in behavior, good — the real convention (tests/testchunker.py) and weak — names the function, not the behavior.