Tool Foundation Sprint Brief logo

Tool Foundation Sprint Brief

Organization
product-on-purpose
tool-foundation-sprint-brief

Pre-sprint brief that locks scope, the decision the sprint must unlock, team and role assignments, logistics, inputs to bring, and success criteria before Day 1 of a Foundation Sprint. Use after the readiness verdict is Go and before the sprint begins. Produces a one-page artifact the team and Decider sign off on as the contract for the next two days.

Overview

Publisherproduct-on-purpose
Repositorypm-skills
Skill nametool-foundation-sprint-brief
Stars
717
Forks
92
Bundled files
3
LicenseApache-2.0
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.

  • 3 bundled files

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

  • Open source

    Published by product-on-purpose on GitHub. Read the source before you install it.

Installation

Install the Tool Foundation Sprint Brief 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/product-on-purpose/pm-skills/tree/main/skills/tool-foundation-sprint-brief
  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/product-on-purpose/pm-skills.git /tmp/pm-skills
mkdir -p .claude/skills
cp -r /tmp/pm-skills/skills/tool-foundation-sprint-brief .claude/skills/tool-foundation-sprint-brief
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tool Foundation Sprint Brief 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 Tool Foundation Sprint Brief 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 Tool Foundation Sprint Brief 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.

Foundation Sprint Brief

Produce the one-page brief that aligns the team on scope, decision target, participants, logistics, and success criteria before Day 1 begins. A well-built brief prevents Day 1 from opening with re-litigation of why-are-we-here; a missing or vague brief almost guarantees it.

Family contract: docs/reference/skill-families/foundation-sprint-skills-contract.md. This skill is a member of foundation-sprint-skills.

When to Use

  • The readiness verdict from tool-foundation-sprint-readiness is Go (or Conditional Go with preconditions cleared).
  • The sprint has dates blocked on calendars and you need the artifact that names what the sprint is for.
  • The team has prep activities scheduled and you need a written reference for what to bring.
  • A skeptical exec wants to know "what is the team doing for two days?" and you need an answer that fits on one page.

When NOT to Use

  • The sprint has already started. The brief is a prep artifact, not an in-sprint deliverable. If Day 1 is happening, run tool-foundation-sprint-basics instead.
  • The readiness verdict is Wait. The brief cannot fix an unready team; close the preconditions first, then re-run readiness, then invoke this skill.
  • The team wants a strategy document. The brief is internal prep, not a stakeholder deliverable. If a stakeholder document is needed, that is a downstream artifact.
  • The brief threatens to become a multi-page strategic document. Stop and reframe: the canonical brief is one page.

What This Skill Produces

A single bundled artifact with six sections:

  1. Initiative statement and stakes: one paragraph naming what the team is sprinting on and why a wrong direction would be costly.
  2. Decision the sprint must unlock: the open strategic question the sprint resolves. Single sentence.
  3. Team roster with role assignments: who is in the room and what role each person plays per section of the sprint.
  4. Logistics plan: dates, hours, location, format (in-person, remote, hybrid), tools, daily rhythm.
  5. Existing inputs to bring: the research, customer examples, competitor notes, metrics, and constraints the team should reference during the sprint.
  6. Readiness reaffirmation: a final check that the Go verdict from tool-foundation-sprint-readiness still holds.

See references/TEMPLATE.md for the canonical structure and references/EXAMPLE.md for the Brainshelf book-catalog brief.

Inference Inputs

InputWhat the skill does with it
Readiness verdict and recommendations (from tool-foundation-sprint-readiness)Pulls the recommended attendees, preconditions, and pre-sprint activities into the brief; flags any precondition that has not been closed
Initiative descriptionCompresses into one paragraph for the Initiative Statement section
Team rosterMaps people to the required Foundation Sprint roles (Decider, Facilitator, PM, Design, Engineering, Customer Expert)
Logistics constraintsProduces the dates/hours/location/format/tools matrix; flags any constraint that would force the sprint to extend beyond two days
(Optional) Skeptical-exec talking pointsTightens the Stakes paragraph to address why-now and why-this concerns

Brief Length Discipline

The brief MUST fit on one page (or one screen). The skill enforces this through structural choices, not raw character counts:

  • Initiative Statement: one paragraph, four sentences maximum.
  • Decision the sprint must unlock: one sentence.
  • Team Roster: table with one row per person.
  • Logistics: table.
  • Inputs to Bring: bulleted list, five items maximum.
  • Readiness Reaffirmation: checklist.

If the brief expands beyond this scope, the sprint is being over-engineered before it starts. The fix is not a longer brief; the fix is a clearer decision target.

Common Pitfalls

  • Over-engineering the brief. The brief is a prep artifact, not a strategy doc. If it has an executive summary, an appendix, or a "background" section longer than one paragraph, it has drifted.
  • Treating the brief as a deliverable to stakeholders. Stakeholders do not read the brief; they read the Founding Hypothesis at the end. The brief is for the team. Sharing it publicly invites pre-sprint debate, which the sprint is supposed to resolve.
  • Vague decision target. "We will figure out our strategy" is not a decision. "We will commit to a top bet between [option A] and [option B]" is.
  • Logistics drift. "We'll figure out dates" or "we'll meet hybrid sometimes" telegraphs that the team has not actually committed to the sprint. Either dates and format are locked, or the readiness verdict was wrong.
  • Skipping readiness reaffirmation. The readiness verdict was a snapshot. If a precondition has slipped or the Decider's availability has changed since readiness, the brief needs to surface that, not paper over it.

Canonical Sources

  • Character Capital. "Foundation Sprint guide." Section on pre-sprint preparation and team scoping.
  • Knapp, J., and Zeratsky, J. Click: How to Make What People Want. Pre-sprint prep recommendations.
  • pm-skills foundation-meeting-brief precedent: brief-structure pattern adapted for the strategic context of a Foundation Sprint rather than a meeting.

Cross-Skill Usage

Prerequisites: tool-foundation-sprint-readiness. The brief expects the readiness output as its primary input. When prerequisites is honored, the brief inherits the readiness verdict, attendee recommendations, and pre-sprint activities; the skill then refines and commits them.

If the team has done equivalent prep without running the readiness skill explicitly (e.g., experienced sprint facilitator who knows the readiness criteria), the brief skill can be invoked directly. In that case, the skill body prompts the team to confirm the readiness criteria are met before generating the brief.

Next invocation in the sprint: tool-foundation-sprint-basics on Day 1 morning.

Decider Checkpoint

This skill ends with a Decider Checkpoint in references/TEMPLATE.md. The Decider signs off on scope (the decision target), team (the roster and role assignments), success criteria (what makes the sprint successful or not), and the explicit tradeoff that the sprint will force a top bet rather than preserve all directions. Without sign-off, the brief is advisory; with sign-off, it is the contract for the next two days.

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 Tool Foundation Sprint Brief AI skill do?

Pre-sprint brief that locks scope, the decision the sprint must unlock, team and role assignments, logistics, inputs to bring, and success criteria before Day 1 of a Foundation Sprint. Use after the readiness verdict is Go and before the sprint begins. Produces a one-page artifact the team and Decider sign off on as the contract for the next two days.

Why use Tool Foundation Sprint Brief on TypingMind?

Because you install it once and use it with any model. Tool Foundation Sprint Brief 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 Tool Foundation Sprint Brief in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/product-on-purpose/pm-skills/tree/main/skills/tool-foundation-sprint-brief. 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 Tool Foundation Sprint Brief?

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 Tool Foundation Sprint Brief?

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

Is the Tool Foundation Sprint Brief AI skill free?

Yes. It is published on GitHub by product-on-purpose under the Apache-2.0 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 👇