ce-riffrec-feedback-analysis

everyinc/compound-engineering-plugin

Analyze Riffrec feedback captures—screen, voice, and events—into structured evidence for product teams.

What is ce-riffrec-feedback-analysis?

Converts Riffrec recordings (zip bundles, video, or audio) into actionable bug reports or requirements kickoff material. Use this when you have a product feedback capture and need to extract issues, workflows, or design insights for downstream analysis.

Routes input (video, audio, zip bundle) to quick bug report or extensive analysis path based on recording length and complexity
Extracts synchronized screen, voice, and event data from Riffrec bundles or standalone media files
Generates structured bug reports with evidence links and reproduction steps for short recordings
Produces requirements kickoff material, problem analyses, and brainstorm handoff for longer or multi-issue sessions
Keeps raw recordings and sensitive data local-only; commits only text artifacts and repo-relative screenshot paths

How to install ce-riffrec-feedback-analysis

npx skills add https://github.com/everyinc/compound-engineering-plugin --skill ce-riffrec-feedback-analysis

Prerequisites

Riffrec installed and configured (or user asks for setup guidance via the skill)
Input: a `riffrec-*.zip` bundle, `.mp4`/`.mov`/`.webm` video, `.m4a`/`.mp3`/`.wav` audio file, or meeting notes `.md`
Python available in the environment (skill runs `analyze_riffrec_zip.py`)

Claude Code

Cursor

Windsurf

Cline

How to use ce-riffrec-feedback-analysis

1.Provide a Riffrec recording (zip bundle, video, or audio file) or describe a setup/capture request
2.Skill inspects the input and routes to Quick Bug Report (short, single issue) or Extensive Analysis (longer, multi-issue)
3.For Quick Bug Report: review the concise bug report with transcription and evidence links
4.For Extensive Analysis: review the requirements kickoff, problem analysis, and brainstorm handoff; continue into `ce-brainstorm` skill if needed
5.Commit text artifacts (bug reports, requirements) to the repo; keep raw recordings and frames local-only unless privacy is cleared

Use cases

Good for

User submits a 30-second screen+voice recording of a UI bug; skill emits a concise bug report with transcription and screenshot evidence
Product team shares a 10-minute Riffrec bundle showing a broken workflow; skill extracts requirements, identifies pain points, and hands off to brainstorm
Designer captures a feature walkthrough; skill produces a structured requirements document with event timeline and visual evidence
QA records a crash scenario; skill generates a detailed reproduction guide with synchronized screen and audio context

Who it's for

Product managers and designers analyzing user feedback or feature walkthroughs
QA and bug reporters documenting issues with synchronized screen and voice evidence
Engineering teams consuming structured feedback for sprint planning or root-cause analysis
Teams using Riffrec capture tool who need to turn raw recordings into actionable artifacts

ce-riffrec-feedback-analysis FAQ

What file formats does this skill accept?

Riffrec `.zip` bundles, `.mp4`/`.mov`/`.webm` video files, `.m4a`/`.mp3`/`.wav` audio files, and meeting-notes `.md` files.

How do I capture a Riffrec recording in the first place?

Ask the skill for setup guidance or read the `references/install-riffrec.md` reference. The skill will route you to installation and capture instructions.

What's the difference between Quick Bug Report and Extensive Analysis?

Quick Bug Report handles short recordings (under ~60 seconds) with a single specific issue; it emits one concise report. Extensive Analysis handles longer recordings, multiple issues, or workflows; it produces requirements kickoff material and hands off to brainstorm.

Where do output artifacts get saved?

By default, `docs/brainstorms/riffrec-feedback/` in repos with that directory. Use `--output-dir` to override. Quick Bug Report uses a temp location to avoid repo pollution.

Should I commit raw recordings and screenshots to the repo?

No—keep raw recordings, audio chunks, and extracted frames local-only by default. Commit only text artifacts (bug reports, requirements, analysis summaries) and use repo-relative screenshot paths so other agents can access evidence.

Full instructions (SKILL.md)

Source of truth, from everyinc/compound-engineering-plugin.

name: ce-riffrec-feedback-analysis description: Analyze Riffrec feedback captures from bundles or standalone recordings. Always load for `riffrec-*.zip`, `session.json` + `events.json` + `recording.webm` + `voice.webm` bundles, `.mp4`/`.mov`/`.webm` videos, `.m4a`/`.mp3`/`.wav` audio, or capture/share requests.

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.

Choose the path

Route to the matching reference based on the input. Read only that reference; do not load the others.

Setup — user has no recording yet and asks how to install Riffrec, capture a session, or share feedback. Read references/install-riffrec.md.
Quick bug report — input is a short recording (under ~60 seconds), the user describes a single specific issue, or asks for "quick", "small", or "just transcribe". Read references/quick-bug-report.md. Emit one concise bug report; skip the full artifact set and brainstorm handoff.
Extensive analysis — input is a longer recording, contains multiple issues / requirements / workflow walkthroughs, or the user wants requirements or brainstorm material. Read references/extensive-analysis.md. Always continue into the ce-brainstorm skill.

When the input is ambiguous (e.g., a zip arrived without context), inspect the recording length and event count before choosing. If still unclear, ask the user which path applies before running anything heavy.

Common rules

Keep raw recordings, audio chunks, zip contents, session dumps, and extracted screenshots local-only by default. Do not commit raw/ or frames/ directories unless the user explicitly asks and privacy is acceptable.
Text/metadata artifacts (requirements kickoff material, analysis summaries, problem analyses, source manifests) may be committed when they are needed for traceability and contain no sensitive data.
Use repo-relative screenshot paths in any committed doc so later agents can open the evidence without absolute local paths.

Analyzer entrypoint

All non-setup paths share the same analyzer, which ships in this skill's scripts/ directory. The Bash tool's working directory is the user's project, not the skill directory, so a bare scripts/<name> path will not resolve. Invoke it by the skill's own absolute path: set SKILL_DIR to the directory you loaded this ce-riffrec-feedback-analysis SKILL.md from, in the same command (shell state does not persist between Bash calls):

SKILL_DIR="<absolute path of the directory containing this SKILL.md>"
python "$SKILL_DIR/scripts/analyze_riffrec_zip.py" /path/to/input

Accepted inputs: a Riffrec .zip, an .mp4 / .mov / .webm video, an .m4a / .mp3 / .wav audio file, or a meeting-notes .md. Use --output-dir <dir> to control where artifacts land. In repos with docs/brainstorms/, the default remains docs/brainstorms/riffrec-feedback/ as a documented evidence/kickoff-artifact exception; it is not the durable ce-brainstorm output convention. The quick path overrides the output dir to a temp location so nothing pollutes the repo.