Paw Cra Quality Control logo

Paw Cra Quality Control

Organization
pawbytes
paw-cra-quality-control

Aggregate cross-asset quality control for campaigns. Use when the user requests 'run QC', 'quality check campaign', 'review all assets', or 'generate QA report'.

Overview

Publisherpawbytes
Repositoryskill-suites
Skill namepaw-cra-quality-control
Stars
117
Forks
20
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by pawbytes on GitHub. Read the source before you install it.

Installation

Install the Paw Cra Quality Control AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pawbytes/skill-suites/tree/main/src/creative/paw-cra-quality-control
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pawbytes/skill-suites.git /tmp/skill-suites
mkdir -p .claude/skills
cp -r /tmp/skill-suites/src/creative/paw-cra-quality-control .claude/skills/paw-cra-quality-control
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paw Cra Quality Control in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Paw Cra Quality Control on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Paw Cra Quality Control is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Quality Control

Overview

This workflow aggregates quality control across all produced visual and video assets in a campaign, then generates a pass/fail report with revision tickets for anything that needs rework. Act as a meticulous QA lead who understands both brand standards and platform technical requirements.

Args: Accepts --headless / -H for autonomous execution against a campaign folder.

Output: qa-report.md with per-asset pass/fail verdicts, severity-rated issues, and revision tickets routed back to owning production workflows.

Key distinction: This is campaign-level cross-asset QC. Individual production workflows (Designer, Video Producer) already have embedded per-asset review gates. This workflow aggregates those results and adds cross-asset consistency checking that no single production workflow can do alone --- verifying that all campaign assets feel like a cohesive set.

On Activation

Load available config from {project-root}/.pawbytes/config/config.yaml and {project-root}/.pawbytes/config/config.user.yaml (root level and cra section). If config is missing, let the user know paw-cra-setup can configure the module at any time. Resolve and apply throughout the session (defaults in parens):

  • {user_name} (null) --- address the user by name
  • {communication_language} (English) --- use for all communications
  • {document_output_language} (English) --- use for generated document content
  • {output_directory} (.pawbytes/creative-suites) --- base output path

Load shared agency memory from {project-root}/.pawbytes/creative-suites/index.md. Identify the active brand and campaign. Load brand guidelines from .pawbytes/creative-suites/brands/{brand-name}/guidelines.md.

Campaign folder resolution: Accept a campaign folder path as argument, or infer from the active campaign in memory. The campaign folder is expected at .pawbytes/creative-suites/brands/{brand-name}/campaigns/{campaign-name}/ or .pawbytes/creative-suites/campaigns/{campaign-name}/. If no campaign can be resolved, ask the user.

If --headless or -H is passed, run the full pipeline without interaction: collect assets, run all QC checks, generate report, route results.

Otherwise, greet the user, confirm the target campaign, and proceed through the stages below. Offer a summary of what will be checked before starting.

Stages

This workflow progresses through four stages. Each stage writes findings to the in-progress qa-report.md using the document-as-cache pattern for compaction survival.

StagePurposeReference
1. Asset CollectionScan campaign folder, discover all manifests and assetsLoad ./references/01-asset-collection.md
2. Per-Asset QCVisual checks, video checks, brand compliance per assetLoad ./references/02-per-asset-qc.md
3. Cross-Asset ConsistencyVerify cohesion across the full campaign asset setLoad ./references/03-cross-asset-consistency.md
4. Report & RouteGenerate final report, create revision tickets, update statusLoad ./references/04-report-and-route.md

Severity Model

All issues use a three-tier severity:

SeverityMeaningEffect
CriticalAsset is unusable or off-brand --- wrong dimensions, broken file, wrong logo, unreadable textAsset fails. Revision ticket created.
WarningAsset is usable but suboptimal --- slight color drift, audio slightly hot, missing optional metadataAsset passes with note. Revision recommended.
InfoObservation or suggestion --- could improve but not a quality gate issueLogged for reference. No revision ticket.

An asset passes if it has zero critical issues. A campaign is QC-approved only when all assets pass.

Manifest Types

Production workflows emit these manifest files. This workflow reads all of them:

ManifestProducerContains
design-manifest.jsonDesigner workflowsImage assets, dimensions, format, brand colors used
video-manifest.jsonVideo Producer workflowsVideo assets, codec, resolution, duration, subtitle status
clip-manifest.jsonpaw-cra-video-clipsExtracted clips with reframing and platform targets
batch-manifest.jsonpaw-cra-design-batchBatch-produced visual assets with content calendar mapping

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Paw Cra Quality Control AI skill do?

Aggregate cross-asset quality control for campaigns. Use when the user requests 'run QC', 'quality check campaign', 'review all assets', or 'generate QA report'.

Why use Paw Cra Quality Control on TypingMind?

Because you install it once and use it with any model. Paw Cra Quality Control is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Paw Cra Quality Control in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pawbytes/skill-suites/tree/main/src/creative/paw-cra-quality-control. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Paw Cra Quality Control?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Paw Cra Quality Control?

As many as you like. As long as a model supports skills, you can use Paw Cra Quality Control with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Paw Cra Quality Control AI skill free?

Yes. It is published on GitHub by pawbytes under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇