creative-qa
Record human-in-the-loop quality judgments for generated images, voice takes, and videos in short-form production. Use this when a person has reviewed an asset and you need structured verdicts, reasons, issue categories, and rerun guidance without turning subjective approval into untracked chat history.
- Installs
- 998
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/postplusai/postplus-skills --skill creative-qa- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads creative-qa automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Creative QA
Use When
- Record human-in-the-loop quality judgments for generated images, voice takes, video renders, and final exports.
- Use after a person has reviewed an asset and you need structured verdicts, reasons, issue categories, blame stage, proposed action, and rerun guidance.
Do Not Use When
- No human verdict exists yet.
- The user wants autonomous AI approval.
- The task is prompt critique before generation; use preflight or prompt QA instead.
Required Input
- Human reviewer verdict and reasons.
- Target object type, id, and version.
- Reviewer and review timestamp.
- Proposed action.
Human Rule
Humans decide quality. AI may summarize notes, normalize categories, and suggest likely blame stages, but only human-confirmed feedback becomes the durable QA record.
Do not invent approval, rejection, or reviewer intent.
Default Workflow
- Confirm the reviewed asset: type, id, version, and optional campaign/persona/concept linkage.
- Confirm the human reviewer, timestamp, verdict, and reasons.
- Normalize reasons into
goodReasons,badReasons, issue categories, and blame stage. - Decide proposed action: approve, rerun a specific stage, revise source input, or reject.
- If rerun guidance exists, build a feedback handoff with a concrete
rerunTarget. - Store or return the structured QA record next to the reviewed object or in the work folder's QA area.
Supported Objects
imagevoice_takevideo_renderfinal_export
Verdicts
Valid verdicts are approved, revise, and reject.
For revise or reject, require non-empty badReasons and issueCategories. For approved, these may be empty arrays.
Categories
Common issue categories:
lip_sync,persona_drift,audio_style,audio_pacing,hook_weak,ad_like,ugc_native_feel,visual_realism,subtitle_accuracy,mixed
Common blame stages:
image,script,voice,render,subtitle,mixed
Use blame stage as diagnostic guidance, not as a substitute for human verdict.
Stop Conditions
- Stop when required user intent, source evidence, or owned input artifacts are missing and guessing would change the result.
- If an owned CLI or script command still fails after any bounded recovery allowed by the executing PostPlus skill, report the exact error and stop. Do not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools.
Output Shape
qaReport:
qaReportId,targetObjectType,targetObjectId,targetVersion,campaignId,personaId,conceptId,reviewer,reviewedAt,verdict,goodReasons,badReasons,issueCategories,blameStage,scores,proposedAction,status
Optional feedbackHandoff:
feedbackId,qaReportId,targetObjectType,targetObjectId,feedbackCategory,feedbackText,dependencyImpact,rerunTarget
Anti-Patterns
- silently approving an asset
- replacing a human verdict with an AI guess
- using vague stage labels as rerun targets
- losing linkage to the reviewed object version
- preserving subjective chat notes without structured reasons
Handoff
- Return the structured QA record structured output or an explicit blocker. If feedback is present, hand off to the named rerun target with the QA record attached.
Public Command Boundary
- Choose the smallest matching command or workflow from the user input and run it directly.
- If an owned CLI or script command still fails after any bounded recovery allowed by the executing PostPlus skill, report the exact error and stop. Do not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools.
FAQ
What does the creative-qa skill do?
Record human-in-the-loop quality judgments for generated images, voice takes, and videos in short-form production. Use this when a person has reviewed an asset and you need structured verdicts, reasons, issue categories, and rerun guidance without turning subjective approval into untracked chat history.
How do I install creative-qa?
Run npx skills add https://github.com/postplusai/postplus-skills --skill creative-qa in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/creative-qa/ (personal) or .claude/skills/creative-qa/ (project).
Which AI agents can use creative-qa?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is creative-qa safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains creative-qa?
It is published by postplusai in postplusai/postplus-skills. It has 998 recorded installs.
More from postplusai/postplus-skills
audio-transcription
postplusai/postplus-skills
Transcribe local or remote audio into text and timestamps. Convert an existing timed transcript locally into SRT or ASS without another transcription job.
video-transcription
postplusai/postplus-skills
Transcribe speech in local or remote videos with timestamps. Convert existing timed transcripts locally into SRT or ASS; use media-analysis for visual understanding.
google-trends-research
postplusai/postplus-skills
Research Google Trends keyword momentum, regional interest, and related queries. Use search-interest evidence without treating it as sales or total demand.
facebook-research
postplusai/postplus-skills
Research public Facebook pages, groups, posts, reels, comments, ads, events, marketplace listings, and profiles for audience or competitor evidence.
youtube-research
postplusai/postplus-skills
Research public YouTube channels, video metrics, and comment samples; obtain downloadable video records when requested. Use for content and audience evidence.
video-analysis
postplusai/postplus-skills
Analyze local or remote social videos through PostPlus, especially for TikTok/Reels shot beats, timelines, voiceover or on-screen text capture, creative strategy, and natural Markdown outputs. Use this when you need video-level analysis beyond metadata and want results linked back to source metadata.
Popular media & creative skills
hyperframes
heygen-com/hyperframes
Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.
media-use
heygen-com/hyperframes
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
hyperframes-registry
heygen-com/hyperframes
About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.
hyperframes-creative
heygen-com/hyperframes
Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.
ai-video-generation
101-skills/superpowers
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
ai-image-generation
101-skills/superpowers
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image