Asset Quality Reviewer

Quality Control

by pawbytes · MIT license · ★ 114 on GitHub

Quality Control cover

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

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

# 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

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.

Manual install (npx, ZIP)
Claude Codenpx skills add pawbytes/skill-suites --skill paw-cra-quality-control -g -a claude-code
Claude Code (degit)npx degit pawbytes/skill-suites/src/creative/paw-cra-quality-control#main ~/.claude/skills/paw-cra-quality-control
Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md4.5 KB
Read SKILL.md here
pawbytes/main1 file shown
SKILL.md
Show the full text68 lines
paw-cra-quality-control/SKILL.md68 lines · 4.5 KB

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.

Stage Purpose Reference
1. Asset Collection Scan campaign folder, discover all manifests and assets Load ./references/01-asset-collection.md
2. Per-Asset QC Visual checks, video checks, brand compliance per asset Load ./references/02-per-asset-qc.md
3. Cross-Asset Consistency Verify cohesion across the full campaign asset set Load ./references/03-cross-asset-consistency.md
4. Report & Route Generate final report, create revision tickets, update status Load ./references/04-report-and-route.md

Severity Model

All issues use a three-tier severity:

Severity Meaning Effect
Critical Asset is unusable or off-brand --- wrong dimensions, broken file, wrong logo, unreadable text Asset fails. Revision ticket created.
Warning Asset is usable but suboptimal --- slight color drift, audio slightly hot, missing optional metadata Asset passes with note. Revision recommended.
Info Observation or suggestion --- could improve but not a quality gate issue Logged 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:

Manifest Producer Contains
design-manifest.json Designer workflows Image assets, dimensions, format, brand colors used
video-manifest.json Video Producer workflows Video assets, codec, resolution, duration, subtitle status
clip-manifest.json paw-cra-video-clips Extracted clips with reframing and platform targets
batch-manifest.json paw-cra-design-batch Batch-produced visual assets with content calendar mapping
1---
2name: paw-cra-quality-control
3description: Aggregate cross-asset quality control for campaigns. Use when the user requests 'run QC', 'quality check campaign', 'review all assets', or 'generate QA report'.
4---
5 
6# Quality Control
7 
8## Overview
9 
10This 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.
11 
12**Args:** Accepts `--headless` / `-H` for autonomous execution against a campaign folder.
13 
14**Output:** `qa-report.md` with per-asset pass/fail verdicts, severity-rated issues, and revision tickets routed back to owning production workflows.
15 
16**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.
17 
18## On Activation
19 
20Load 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):
21 
22- `{user_name}` (null) --- address the user by name
23- `{communication_language}` (English) --- use for all communications
24- `{document_output_language}` (English) --- use for generated document content
25- `{output_directory}` (`.pawbytes/creative-suites`) --- base output path
26 
27Load 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`.
28 
29**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.
30 
31If `--headless` or `-H` is passed, run the full pipeline without interaction: collect assets, run all QC checks, generate report, route results.
32 
33Otherwise, greet the user, confirm the target campaign, and proceed through the stages below. Offer a summary of what will be checked before starting.
34 
35## Stages
36 
37This 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.
38 
39| Stage | Purpose | Reference |
40|-------|---------|-----------|
41| 1. Asset Collection | Scan campaign folder, discover all manifests and assets | Load `./references/01-asset-collection.md` |
42| 2. Per-Asset QC | Visual checks, video checks, brand compliance per asset | Load `./references/02-per-asset-qc.md` |
43| 3. Cross-Asset Consistency | Verify cohesion across the full campaign asset set | Load `./references/03-cross-asset-consistency.md` |
44| 4. Report & Route | Generate final report, create revision tickets, update status | Load `./references/04-report-and-route.md` |
45 
46## Severity Model
47 
48All issues use a three-tier severity:
49 
50| Severity | Meaning | Effect |
51|----------|---------|--------|
52| **Critical** | Asset is unusable or off-brand --- wrong dimensions, broken file, wrong logo, unreadable text | Asset fails. Revision ticket created. |
53| **Warning** | Asset is usable but suboptimal --- slight color drift, audio slightly hot, missing optional metadata | Asset passes with note. Revision recommended. |
54| **Info** | Observation or suggestion --- could improve but not a quality gate issue | Logged for reference. No revision ticket. |
55 
56An asset **passes** if it has zero critical issues. A campaign is **QC-approved** only when all assets pass.
57 
58## Manifest Types
59 
60Production workflows emit these manifest files. This workflow reads all of them:
61 
62| Manifest | Producer | Contains |
63|----------|----------|----------|
64| `design-manifest.json` | Designer workflows | Image assets, dimensions, format, brand colors used |
65| `video-manifest.json` | Video Producer workflows | Video assets, codec, resolution, duration, subtitle status |
66| `clip-manifest.json` | `paw-cra-video-clips` | Extracted clips with reframing and platform targets |
67| `batch-manifest.json` | `paw-cra-design-batch` | Batch-produced visual assets with content calendar mapping |
68 
View all files on GitHub →

Details

License
MIT
Stars on the repo
★ 114
Checked
Source
pawbytes/skill-suites ↗
Creator
pawbytes · 60 listings
View creator

Similar skills

See all →

More from pawbytes

SkillCreative Campaign Directorpawbytes/skill-suites · by pawbytesCreative director and orchestrator for Pawbytes Creative Suites. Use when the user needs creative direction, campaign planning, brand setup, or help choosing the right creative specialist or workflow. Triggers: 'Aria', 'creative direction', 'campaign planning', 'brand setup', 'which creative agent should I use', 'creative suite'.★ 114 GitHub starsSkillCustomer Insights Analyzerpawbytes/skill-suites · by pawbytesCustomer insight specialist for audience understanding. Use when defining target audience, buyer personas, customer pains, value mapping, problem discovery, audience language. Triggers: 'who would buy this', 'target audience', 'buyer persona', 'customer pain points', 'ideal customer', 'user problems', 'value proposition', 'audience research'.★ 114 GitHub starsSkillBatch Design Producerpawbytes/skill-suites · by pawbytesBatch visual production workflow for campaigns. Accepts a content calendar or campaign brief, produces multiple platform-ready assets with organized bundle output and machine-readable manifest. Trigger for 'batch design', 'content calendar to assets', 'campaign batch', 'produce all campaign visuals', or 'bulk asset generation'.★ 114 GitHub starsSkillBrand Asset Designerpawbytes/skill-suites · by pawbytesBrand asset and flyer production pipeline. Use when user requests 'create logo', 'design brand asset', 'make flyer', 'generate icon', or 'create banner'.★ 114 GitHub starsSkillCampaign Orchestration Enginepawbytes/skill-suites · by pawbytesOrchestrates multi-deliverable campaigns by dispatching Designer and Video Producer workflows in parallel. Use when the user requests 'run campaign', 'execute campaign', 'launch campaign production', or 'orchestrate deliverables'.★ 114 GitHub starsSkillCommunity Platform Builderpawbytes/skill-suites · by pawbytesBuilds and manages owned community platforms. Use when the user requests 'Discord community', 'Slack community', 'community platform', 'community-led growth', 'forum', 'champions program', 'ambassador program', or 'community engagement strategy'.★ 114 GitHub stars