Review generated candidate takes with structured script-faithfulness, identity, background, spatial, action, motion, physics, artifact, dialogue-sync, and subtitle-sync checks before creative take selection.
Scanned 9/9/2026
Install to Claude Code
npx -y skills add badgids/Story-Film-Skills --skill media-qc --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Media Qc?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/badgids-media-qc)More formats (shields.io, HTML) on the badges page.
---
name: media-qc
description: Review generated candidate takes with structured script-faithfulness, identity, background, spatial, action, motion, physics, artifact, dialogue-sync, and subtitle-sync checks before creative take selection.
disable-model-invocation: true
author: Alan Guice (Badgids)
license: Apache-2.0
---
# Media QC
## Workflow
1. Read core contract, `MEDIA_QC.md`, source shot brief, take record, approved references, and adjacent approved material when continuity matters.
2. Inspect the actual generated media. Do not score from the prompt alone.
3. Append or update the take's record in `04_generation/take_qc.jsonl`.
4. Use pass, warn, fail, not-applicable, or not-checked for each relevant dimension and provide concise evidence.
5. Optional automated metrics may be recorded with evaluator/version metadata, but do not convert them into taste judgments automatically.
6. Set `overall` to fail for hard script, identity, continuity, physics, corruption, or sync failures that make the take unusable as planned. For visible dialogue with approved-audio authority, treat wrong speaker ownership, unexpected mouth movement on a non-speaker, or generation/review audio hash drift as a hard sync failure.
7. Pass the QC record to `take-selection`.
## Done
The take has an evidence-backed production-quality record that separates objective/observable defects from later creative preference.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling