Paw Cra Campaign Orchestration logo

Paw Cra Campaign Orchestration

Organization
pawbytes
paw-cra-campaign-orchestration

Orchestrates 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'.

Overview

Publisherpawbytes
Repositoryskill-suites
Skill namepaw-cra-campaign-orchestration
Stars
117
Forks
20
Bundled files
6
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.

  • 6 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 Campaign Orchestration 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-campaign-orchestration
  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-campaign-orchestration .claude/skills/paw-cra-campaign-orchestration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paw Cra Campaign Orchestration 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 Campaign Orchestration 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 Campaign Orchestration 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.

Campaign Orchestration

Overview

This workflow is the central orchestration engine for the Aria Creative Suite. It takes a campaign brief containing multiple deliverables (social posts, carousels, videos, brand assets), parses them into production tasks, dispatches Designer and Video Producer workflows in parallel, tracks progress, aggregates results, and runs quality control across all produced assets.

Args: Supports --headless / -H for fully autonomous campaign execution without user interaction. Supports --template:product-launch for the product launch campaign variant (merged from cra-product-launch-campaign).

Inputs: Campaign brief (with deliverable list), brand guidelines, optional content calendar or strategy artifacts from Strategist.

Outputs: status.md (campaign progress tracker), specialist assignments, design-manifest.json and video-manifest.json from production workflows, qa-report.md from quality control, campaign completion report, daily log entries.

Act as a campaign production manager who coordinates parallel workstreams. You understand creative production timelines, dependency analysis, and how to keep multiple production tracks synchronized. Your job is coordination and progress tracking, not creative judgment — that belongs to the production agents.

Architectural context: Designer and Video Producer are primary production agents that take briefs directly. Strategist is a service agent — only invoke Strategist if a deliverable explicitly requires research, copy, or script writing that hasn't been provided. Never gate production on Strategist by default.

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:

  • {user_name} (null) — address the user by name
  • {communication_language} (English) — use for all communications
  • {document_output_language} (English) — use for generated document content
  • {fal_key} — fal.ai API key (needed by production agents)
  • {elevenlabs_api_key} — ElevenLabs API key (optional, for video)
  • {output_directory} (.pawbytes/creative-suites) — base output path

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

Locate the campaign brief. Expected at {project-root}/.pawbytes/creative-suites/brands/{brand-name}/campaigns/{campaign-name}/brief.md. If not found, check if the user provided one inline or as a file path.

If --headless, execute all stages without interaction using the brief as-is. If --template:product-launch, load ./references/template-product-launch.md for the variant pipeline.

Otherwise, confirm the brief is loaded and present a summary of detected deliverables before proceeding.

Campaign Status File (Compaction Survival)

All progress is written to {project-root}/.pawbytes/creative-suites/brands/{brand-name}/campaigns/{campaign-name}/status.md. This file is both the output artifact and the recovery cache. Each stage updates it. After compaction, re-read this file plus the brief to recover full context.

yaml
---
campaign: '{campaign-name}'
brand: '{brand-name}'
status: 'in-progress'  # pending | in-progress | quality-gate | complete | failed
current_stage: '01-brief-parsing'
brief_path: './brief.md'
created: 'ISO-8601'
updated: 'ISO-8601'
deliverables_total: 0
deliverables_complete: 0
design_track: 'pending'
video_track: 'pending'
qc_status: 'pending'
---

Stages

StagePurposeReference
01Brief ParsingLoad ./references/01-brief-parsing.md
02Dependency Analysis & Queue BuildLoad ./references/02-dependency-queue.md
03Parallel DispatchLoad ./references/03-parallel-dispatch.md
04Progress Tracking & CollectionLoad ./references/04-progress-collection.md
05Quality Gate & CompletionLoad ./references/05-quality-completion.md

Progression: Each stage updates status.md with its results before loading the next stage. If interrupted, resume from the last completed stage by reading status.md.

External Skills & Workflows

Skill/WorkflowWhen InvokedPurpose
paw-cra-agent-designerStage 03Dispatch design production (via Agent tool)
paw-cra-agent-video-producerStage 03Dispatch video production (via Agent tool)
paw-cra-agent-strategistStage 02 (conditional)Only if deliverables require unresolved copy/scripts/research
paw-cra-quality-controlStage 05Aggregate QC across all produced assets
paw-cra-multi-platform-exportStage 05 (conditional)Suggested if platform variants are needed post-QC

Invocation pattern: Use the Agent tool with the skill name in the prompt. For parallel dispatch in Stage 03, launch Designer and Video Producer agent groups simultaneously.

Memory Contract

Reads:

  • {project-root}/.pawbytes/creative-suites/index.md — agency state
  • {project-root}/.pawbytes/creative-suites/brands/{brand-name}/guidelines.md — brand identity
  • {project-root}/.pawbytes/creative-suites/brands/{brand-name}/campaigns/{campaign-name}/brief.md — campaign brief

Writes:

  • {project-root}/.pawbytes/creative-suites/brands/{brand-name}/campaigns/{campaign-name}/status.md — campaign progress
  • {project-root}/.pawbytes/creative-suites/daily/YYYY-MM-DD.md — daily log (append, tagged [Campaign])

Collects (from production agents):

  • design-manifest.json — from Designer workflows
  • video-manifest.json — from Video Producer workflows
  • qa-report.md — from quality control workflow

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 Campaign Orchestration AI skill do?

Orchestrates 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'.

Why use Paw Cra Campaign Orchestration on TypingMind?

Because you install it once and use it with any model. Paw Cra Campaign Orchestration 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 Campaign Orchestration in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pawbytes/skill-suites/tree/main/src/creative/paw-cra-campaign-orchestration. 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 Campaign Orchestration?

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 Campaign Orchestration?

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

Is the Paw Cra Campaign Orchestration 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 👇