discovery-project-storylisted

Cross-domain / Research communication — Turn a Microsoft Discovery project's own record (git history, task board, engine/agent/Clio runs, outcomes and grades, the human side of chat sessions, token usage) into an evidence-true, animated, self-contained HTML presentation of how the work happened. The number of scenes and beats comes from the evidence and needs the user's approval before any prose is written. Each scene renders as a tree, a flow graph or a metrics chart, and every human quote is exact and re-verified at build time. WHEN: "tell the story of this project", "what happened in this project", "present how Discovery did this work", "project retrospective deck", "replay the project", "animated walkthrough of the work", "how was this built with Discovery", "project story HTML", "explain the project to leadership", "demo what Discovery did". DO NOT USE FOR: writing the research paper itself (arxiv-paper), PowerPoint decks (pptx), or token-only read-outs (discovery-token-usage).
timothymeyers/discovery-tools · ★ 1 · AI & Automation · score 70

Install: claude install-skill timothymeyers/discovery-tools

# Discovery project story Builds `discovery-work.html`, a single offline file that replays how a Discovery project unfolded. It uses real human words and real records, shown as plain-language scenes with animated tree, flow or metrics diagrams. Presenter notes, the exact exchange, the chronology and the record behind each beat sit one click away. Everything lives in this skill folder. Only the Python standard library is needed; QA needs Node with `playwright-core` and Chromium. Nothing in the target workspace is modified until the user chooses where to save the release. ``` scripts/mine_exhaust.py workspace → evidence.json (read-only mining) scripts/verify_quotes.py re-read every quoted human turn from its source file scripts/propose_outline.py evidence → outline.json + outline-proposal.md (scene count from evidence) scripts/lock_outline.py freeze the approved outline (hash + the user's verbatim approval) scripts/build_story.py scaffold story.json · build + validate → discovery-work.html scripts/qa.cjs browser QA: themes × viewports × every beat, playback, drawers templates/discovery-work.template.html self-contained renderer (own --ps-* theme) references/*.md schema, sources, heuristics, narrative rules, known defects ``` ## Dependencies The mining, outline, lock and build scripts are **Python standard library only**. `scripts/qa.cjs` needs **Node** plus **`playwright-core`** and a **Chromium** build. It resolves them in thi