rad-explain

{
  "name": "rad-explain",
  "version": "0.1.0",
  "description": "Explain a project to humans, honestly — without overpromising or inventing features that aren't in the repo. Five skills generate audience-targeted communications from your project's actual artifacts (code, docs, planning files):\n\n- `narrate-project` — plain-English description, audience-adaptive (non-dev / investor / future-self / new-collaborator)\n- `elevator-pitch` — ~150 words, ~30 seconds spoken\n- `draft-pitch` — one-pager / executive summary for funding, grants, partnerships\n- `explain-document` — interpret a specific repo file (\"what does this commit me to?\", \"where could this go wrong?\")\n- `ground-readme` — generate or audit a README so it stays grounded in source (two modes: audit existing, or generate new)\n\nTwo pure-stdlib Python validators run on every output: `check-grounding.py` traces each substantive claim back to repo source, and `check-overpromise.py` flags superlatives, vague-quantity claims, marketing fluff, and production-readiness assertions without evidence.\n\nWorks on any repo with no rad-planner dependency. Reads canonical `docs/` if present (vision.md, decisions/, planning/current.md, status.md, roadmap.md), falls back to README + project manifest + source structure when absent. The plugin's own README passes its own `check-overpromise.py`.",
  "author": {
    "name": "RAD",
    "url": "https://github.com/RadOrigin-LLC"
  },
  "license": "Apache-2.0",
  "homepage": "https://github.com/RadOrigin-LLC/RAD-Claude-Skills/tree/main/plugins/rad-explain",
  "repository": "https://github.com/RadOrigin-LLC/RAD-Claude-Skills",
  "keywords": ["explain", "narrate", "pitch", "elevator-pitch", "readme", "documentation", "honest-marketing", "grounded", "project-story", "synthesis", "source-traceable", "anti-overpromise"]
}