Ce Riffrec Feedback Analysis

Turns Riffrec screen and voice recordings into structured bug reports or requirements docs. When someone drops a riffrec-*.zip bundle, this routes between three paths: setup instructions if they haven't captured anything yet, a quick transcription for sub-60-second clips, or extensive analysis that extracts frames, transcribes audio, and builds a full artifact set in the Compound Engineering format. The extensive path automatically hands off to ce-brainstorm so you go straight from raw feedback to actionable tasks. Keeps recordings local by default but commits the text artifacts when you need traceability. Honest take: this is narrow but solves the "I recorded feedback, now what" problem cleanly if you're already using Riffrec.

skills.sh installs: 2.9K
GitHub stars: 26K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add everyinc/compound-engineering-plugin --skill ce-riffrec-feedback-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

Riffrec Feedback Analysis

Turn raw product feedback into structured evidence for downstream agents. This skill is the consumption side of Riffrec, a capture tool that records synchronized screen + voice + event sessions and emits a riffrec-*.zip bundle.

Done:

Setup ends with a current capture/share path.
Quick analysis ends with one evidence-backed bug report and no durable artifact unless requested.
Extensive analysis ends with the complete evidence set and a ce-brainstorm handoff unless the user asked for extraction only.
A missing input, analyzer failure, or unresolved route ends with an actionable blocker rather than a partial success claim.