plugins/qa/skills/qa-video-producer/SKILL.md
Use after QA has already passed to produce founder-facing proof videos with a Browser Use-verified workflow, a Playwright-recorded walkthrough, Remotion intro/outro, and Deepgram narration. Never use for partial, failed, or blocked QA runs.
npx skillsauth add ansarullahanasz360/cc-guide qa-video-producerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Produce the final founder proof video for a completed QA run. This skill is downstream of $qa; it does not decide that work passed, substitute for QA, or create confidence from incomplete evidence.
Before doing substantive video work, read:
../../references/evidence-contract.md../../references/browser-use-proof.md../../references/tool-selection.md../../references/qa-operating-model.mdThen inspect the QA run folder and confirm:
verification-report.md exists.manifest.json exists.PASS or MERGE.PASS or MERGE.If any item is missing, FAIL, BLOCKED, or PARTIAL, stop. Update the report/manifest with a no-video decision if needed, name the blocker, and do not render the founder video.
The proof video must be a real walkthrough artifact:
DEEPGRAM_API_KEY or the QA keychain helper.finalVerdict, verdict, required gates, test gates, runtime gates, merge/pass status, or report outcome.Default to 5-10 minutes for meaningful sprint or feature proof videos. Use a shorter video only for a tiny scoped change, and state in the report why the shorter walkthrough is enough.
PASS or MERGE.create-proof-walkthrough-plan.mjs.record-playwright-proof-walkthrough.mjs unless the run documents an approved fallback.validate-proof-video.mjs.narration.txt from the verified report.generate-deepgram-narration.mjs when Deepgram is available.render-remotion-proof-segment.mjs.assemble-proof-video-segments.mjs.run-proof-video-pipeline.mjs when the project provides the end-to-end wrapper.Return the report path, manifest path, source walkthrough recording path, video path, duration, narration status, validation status, and any reason video was not produced.
development
Decide HOW to run a coding task — interactive, goal mode, or a workflow — then author the launch-ready prompt or goal package for Claude Code, Codex, or Antigravity. Use when the user says "launchpad", "start a goal", "set up a goal/sprint", "should this be a goal or interactive", "plan an autonomous run", "I want to brain-dump a task", "help me write a goal prompt", or is about to kick off a long autonomous run and wants it scoped, delegated, and verifiable first.
development
Use when turning founder requirements, research packets, plans, specs, and system designs into one or more independently executable Claude Code, Cloud Code, or Codex implementation sprints with story writing, review, execution, optional verification, and sprint-level commits.
tools
Interactive Claude Code repository setup and optimization. Configures the complete ecosystem - skills, commands, subagents, hooks, rules, MCPs, and plugins. Invoke with /setup-claude init or /setup-claude audit.
testing
Pre-flight check for Ralph TUI loops. Validates config, templates, prd.json, and environment before starting a loop. Run after /prd to verify everything is ready. Detects global CLAUDE.md conflicts, validates template variables, and provides launch commands.