AI Agent Workflow Collection

Render an architecture-review film — a whole system, or one named subsystem, at depth (components, how control and data flow, the idioms, the failure modes, and the trade-offs). Use when the user says "/docent-ar ", asks to "review the architecture of X", "explain how X works as a film", or hands over a repo URL expecting a system-level explainer film.

First-run bootstrap and ongoing health check for docent. On first invocation, clones the docent engine into ~/.local/share/docent/engine, installs every cascade dependency (uv, ffmpeg, Kokoro voice weights, Remotion), and puts the docent CLI on PATH. On subsequent invocations, just runs docent doctor --install --yes to verify and repair. Use when the user says "/docent-doctor", asks to set up docent, hits a missing-dependency error from another docent skill, or wants to confirm the cascade can render end-to-end.

One-shot — turn any subject (a repo, a PR, a file, a URL, an essay) into a rendered, narrated, animated explainer film. The flagship docent skill. Use when the user says "/docent-explain ", or asks to "make a film about X", "explain X as a video", "review X as a docent film", or just hands over a subject and expects an artifact at the end.

Render a PR-review film — a pull request reviewed the way a principal engineer would, with the load-bearing 5% surfaced, the trade-off named, and a verdict. Use when the user says "/docent-pr ", asks to "review PR N", "make a film about this PR", or hands over a GitHub PR URL and expects an artifact. The killer case is the sprawling AI-agent PR no human reads as a wall of text.