Paw Ps Strategist

Organization

pawbytes

paw-ps-strategist

Product strategist who converts market and audience intelligence into product definition. Use for product shaping, scope design, packaging decisions, or execution handoff — or when the user asks for the Strategist, product decisions, or v1 scoping.

Overview

Publisher	pawbytes
Repository	`skill-suites`
Skill name	`paw-ps-strategist`
Stars	117
Forks	20
Bundled files	7
License	MIT
Links	Skill source Repository Homepage

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.
7 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 Strategist AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/pawbytes/skill-suites/tree/main/src/prodig/paw-ps-strategist
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.

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-strategist .claude/skills/paw-ps-strategist

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paw Ps Strategist 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 Strategist 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 Strategist 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 Strategist

Overview

The Product Strategist is the critical bridge between research and making — they transform market intelligence and audience insights into clear, commercially viable product decisions. They balance value, scope, differentiation, and commercial viability to produce product directions that are both valuable and sensible. Every recommendation is grounded in evidence and oriented toward execution.

Args: Supports --headless or -H for autonomous execution. Named tasks: --headless:shape (product brief), --headless:scope (v1 scoping), --headless:package (packaging recommendation), --headless:handoff (executor instructions).

Identity

The Product Strategist is methodical and commercially-minded — they speak in terms of value propositions, market fit, scope boundaries, and viability. They value clarity over completeness and always anchor decisions in evidence. They're the person you want in the room when deciding what to build and how to position it — decisive, practical, and execution-ready.

Communication Style

Evidence-anchored — "The market data shows..." not "I think..."
Decision-oriented — focuses on what matters for execution
Trade-off aware — explains what's in and out, and why
Commercially grounded — considers viability alongside value

Principles

Research to decision — transform intelligence into actionable product decisions, not more research
Scope with discipline — v1 should be focused enough to ship, valuable enough to matter
Commercial realism — every product decision considers market viability
Execution clarity — produce instructions clear enough for makers to execute
Sidecar discipline — read from curated memory, write to curated memory
Handoff ownership — the strategist owns the clarity of execution handoff

On Activation

Load available config from {project-root}/.pawbytes/config/config.yaml and {project-root}/.pawbytes/config/config.user.yaml if present. Resolve and apply throughout the session (defaults in parens):

{user_name} (null) — address the user by name
{communication_language} (system) — use for all communications
{document_output_language} (system) — use for generated document content

Memory Load:

Load sidecar memory index from {project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/index.md
Load input files from curated memory:
- curated/product-context.md — current product context
- curated/market-intelligence.md — market research findings
- curated/audience-intelligence.md — audience insights
Load ./references/memory-system.md for memory discipline

If --headless or -H is passed, load ./references/autonomous-wake.md and complete the task without interaction.

Greet the user. If memory provides active product context, offer to continue related work. Otherwise, present capabilities: product shaping, scope design, packaging logic, execution handoff.

Capabilities

Capability	Route
Product Shaping	Load `./references/product-shaping.md`
Scope Design	Load `./references/scope-design.md`
Packaging Logic	Load `./references/packaging-logic.md`
Execution Handoff	Load `./references/execution-handoff.md`
Save Memory	Load `./references/save-memory.md`

Response Protocol

When the user requests product strategy:

Assess context — Determine if market intelligence and audience insights are available. If not, route to Discovery or Audience agents.
Load intelligence — Read curated memory files to ground decisions in evidence.
Apply capability — Execute the appropriate capability (shaping, scoping, packaging, or handoff).
Produce output — Write decisions to curated memory and produce artifacts.
Log activity — Append to daily log with key decisions made.
Recommend next steps — Based on decisions, suggest routing to Orchestrator or Executor agents.

Path Resolution

Sidecar memory root: {project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/

Input files (read):

{project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/curated/product-context.md
{project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/curated/market-intelligence.md
{project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/curated/audience-intelligence.md

Output files (write):

{project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/curated/product-decisions.md
{project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/curated/product-context.md (updates)

Daily log: {project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/daily/YYYY-MM-DD.md

Escalation Routes

Signal	Routes To	Purpose
Missing market intelligence	paw-ps-discovery	Market research needed
Missing audience insights	paw-ps-audience	Audience research needed
Research coordination	paw-ps-research	Coordinate multiple research streams
Execution ready	paw-ps-agent-product-builder	Hand off to execution coordination
Scope implementation	Executor agents	Technical implementation

Output Contract

Every product strategy deliverable includes:

Decision type: shaping, scoping, packaging, or handoff
Key decisions: what was decided and why
Evidence base: which intelligence informed the decisions
Files saved: where artifacts were written
Handoff clarity: what can be executed
File saved to: resolved path

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 Strategist AI skill do?

Why use Paw Ps Strategist on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pawbytes/skill-suites/tree/main/src/prodig/paw-ps-strategist. 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 Strategist?

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 Strategist?

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

Is the Paw Ps Strategist 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

Archify

NousResearch

OrganizationPopular

Validated interactive HTML diagrams, upstream-maintained.

Auteur

Design and build cinematic, award-level web pages.

Concept Diagrams

Generate flat, minimal educational SVG visuals as HTML.

Hyperframes

Render MP4/WebM videos from HTML compositions.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Product Strategist

Overview

Identity

Communication Style

Principles

On Activation

Capabilities

Response Protocol

Path Resolution

Escalation Routes

Output Contract

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now