Paw Ps Product Package Assembler logo

Paw Ps Product Package Assembler

Organization
pawbytes
paw-ps-product-package-assembler

Bundle product artifacts into a coherent, production-ready package. Use when the user requests 'package product', 'bundle artifacts', 'assemble deliverables', 'create product package', or 'finalize outputs'.

Overview

Publisherpawbytes
Repositoryskill-suites
Skill namepaw-ps-product-package-assembler
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 Ps Product Package Assembler 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/prodig/paw-ps-product-package-assembler
  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/prodig/paw-ps-product-package-assembler .claude/skills/paw-ps-product-package-assembler
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paw Ps Product Package Assembler 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 Ps Product Package Assembler 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 Ps Product Package Assembler 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.

Product Package Assembler

Overview

This workflow bundles product artifacts from the execution phase into a coherent, production-ready package. It ensures outputs feel like one unified product, not scattered drafts, by gathering executor outputs, verifying completeness against product-type requirements, organizing into a structured bundle, and generating a comprehensive manifest.

Args: Accepts --headless / -H for non-interactive execution.

Output: Packaged product bundle with organized directory structure, completeness report, and packaging manifest.

The Non-Negotiable: Must ensure outputs feel like one product, not scattered drafts.

On Activation

Load available config from {project-root}/.pawbytes/config/config.yaml and {project-root}/.pawbytes/config/config.user.yaml (root level and ps section). If config is missing, let the user know paw-ps-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
  • {output_directory} (.pawbytes/prodig-suites) — base output path

Load shared memory from {project-root}/.pawbytes/prodig-suites/index.md. Load output standards from {project-root}/.pawbytes/prodig-suites/output-standards.md.

Product context resolution: Identify the active product from memory or accept a product slug as argument. The product workspace is expected at .pawbytes/prodig-suites/products/{product-slug}/. If no product can be resolved, ask the user.

If --headless or -H is passed, run the full pipeline without interaction: gather artifacts, check completeness, organize bundle, generate manifest.

Otherwise, greet the user, confirm the target product, and proceed through the stages below.

Pipeline

This workflow progresses through four stages. Each stage updates the packaging status file using the document-as-cache pattern for compaction survival.

StagePurposeReference
1. Gather ArtifactsCollect all execution artifacts from executorsLoad ./references/01-gather-artifacts.md
2. Check CompletenessVerify against product-type requirementsLoad ./references/02-check-completeness.md
3. Organize BundleStructure into coherent packageLoad ./references/03-organize-bundle.md
4. Generate ManifestCreate package manifest and notesLoad ./references/04-generate-manifest.md

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

Packaging Status File

All progress is written to {project-root}/.pawbytes/prodig-suites/products/{product-slug}/packaging-status.md. This file is both the output artifact and the recovery cache.

yaml
---
product: '{product-slug}'
status: 'in-progress'  # pending | in-progress | complete | incomplete
current_stage: '01-gather-artifacts'
created: 'ISO-8601'
updated: 'ISO-8601'
artifacts_found: 0
artifacts_packaged: 0
missing_items: []
---

Artifact Sources

Artifacts are collected from executor outputs:

SourceContainsManifest File
Discovery agentsResearch reports, briefs, specsdiscovery-manifest.json
StrategistStrategy documents, plansstrategy-manifest.json
Executor agentsContent, code, designs, mediaexecutor-manifest.json
Synthesis workflowsIntegrated deliverablessynthesis-manifest.json

Product Types & Completeness Criteria

Different product types have different required artifacts:

Product TypeRequired Artifacts
DocumentMain document, outline, research notes
ApplicationCode package, README, documentation
CampaignCreative assets, copy, strategy brief
ReportReport document, data sources, methodology
PresentationSlide deck, speaker notes, handouts

Output Structure

.pawbytes/prodig-suites/products/{product-slug}/package/
├── manifest.json           # Package manifest
├── completeness-report.md  # What's present, what's missing
├── packaging-notes.md      # Special considerations
├── artifacts/              # All gathered artifacts
│   ├── {artifact-1}
│   ├── {artifact-2}
│   └── ...
└── metadata/               # Supporting metadata
    ├── source-manifests/
    └── audit-trail.json

Memory Contract

Reads:

  • {project-root}/.pawbytes/prodig-suites/index.md — module state
  • {project-root}/.pawbytes/prodig-suites/output-standards.md — output standards
  • {project-root}/.pawbytes/prodig-suites/products/{product-slug}/product-context.md — product context
  • Executor manifests from execution phase

Writes:

  • {project-root}/.pawbytes/prodig-suites/products/{product-slug}/packaging-status.md — packaging progress
  • {project-root}/.pawbytes/prodig-suites/products/{product-slug}/package/ — packaged bundle
  • {project-root}/.pawbytes/prodig-suites/daily/{date}.md — daily log (append, tagged [Packaging])

Escalation Routes

SignalRoutes To
Missing executor outputspaw-ps-agent-product-builder (to rerun execution)
Incomplete artifactsAppropriate executor agent
Quality issuespaw-ps-quality-reviewer
Export needspaw-ps-export-handler

Output Contract

Every packaging deliverable includes:

  • Action type: bundling, completeness-check, organizing
  • Files saved: paths to all created files
  • Completeness status: what's present vs. missing
  • Recommendations: next steps (quality review, re-execution, etc.)
  • Package location: resolved path to bundle

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 Ps Product Package Assembler AI skill do?

Bundle product artifacts into a coherent, production-ready package. Use when the user requests 'package product', 'bundle artifacts', 'assemble deliverables', 'create product package', or 'finalize outputs'.

Why use Paw Ps Product Package Assembler on TypingMind?

Because you install it once and use it with any model. Paw Ps Product Package Assembler 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 Ps Product Package Assembler in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pawbytes/skill-suites/tree/main/src/prodig/paw-ps-product-package-assembler. 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 Ps Product Package Assembler?

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 Ps Product Package Assembler?

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

Is the Paw Ps Product Package Assembler 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 👇