Agent skill · Audited from source

Tool Foundation Sprint Differentiation

skill · product-on-purpose/pm-skillsApache-2.0 licenceAudited 19 Oct 2026 · source 2abfbb961d31

★ 741pushed 1 day agoversion 1.0.0
✓SAFEGrade B · 89/100 · 19 Oct 2026 · 2abfbb9
741repo stars · whole product-on-purpose/pm-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 2abfbb961d31 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Day 1 afternoon move of a Foundation Sprint. Converts the morning's Basics frame into a defensible strategic position by scoring differentiator candidates against customer-perceived value, choosing two committed…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Tool Foundation Sprint Differentiation (product-on-purpose/pm-skills)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/product-on-purpose/tool-foundation-sprint-differentiation

Trust audit

Audit 0.4.1 · source read 19 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 2abfbb961d31 · 19 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherproduct-on-purpose GitHub organizationOwner of the repository this skill is read from
  • Source folderproduct-on-purpose/pm-skills/skills/tool-foundation-sprint-differentiationThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdict2abfbb961d31A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Day 1 afternoon move of a Foundation Sprint. Converts the morning's Basics frame into a defensible strategic position by scoring differentiator candidates against customer-perceived value, choosing two committed…

---
name: tool-foundation-sprint-differentiation
description: Day 1 afternoon move of a Foundation Sprint. Converts the morning's Basics frame into a defensible strategic position by scoring differentiator candidates against customer-perceived value, choosing two committed differentiators, plotting alternatives on a 2x2 chart, writing decision principles, and producing a one-page Mini Manifesto. Use after Basics is signed; before Approach Options the next morning.
license: Apache-2.0
metadata:
  classification: tool
  version: "1.0.0"
  updated: 2026-07-04
  tool: foundation-sprint
  move: differentiation
  category: problem-framing
  frameworks:
    - foundation-sprint
    - click
    - character-note-and-vote
  timebox_minutes: 150
  roles:
    - facilitator
    - decider
    - pm
    - design
  prerequisites:
    - tool-foundation-sprint-basics
  inputs:
    - basics bundled artifact
    - differentiation candidates
  outputs:
    - scored differentiator candidates
    - 2 chosen differentiators
    - 2x2 differentiation chart with competitors plotted
    - decision principles list
    - one-page Mini Manifesto
  author: product-on-purpose
---

<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->

# Foundation Sprint Differentiation

Day 1 afternoon of a Foundation Sprint. The team converts the morning's Basics frame (customer, problem, advantage, competitors) into a defensible strategic position. The output is a one-page Mini Manifesto that the team and Decider sign as the Day 1 strategic summary.

Family contract: [`docs/reference/skill-families/foundation-sprint-skills-contract.md`](../../docs/reference/skill-families/foundation-sprint-skills-contract.md). This skill is a member of `foundation-sprint-skills`.

## When to Use

- Day 1 afternoon of a Foundation Sprint, immediately after lunch.
- The Basics bundled artifact is signed by the Decider; the customer, problem, advantage, and competitor map are committed.
- The team is ready to commit to a strategic position the product will occupy.

## When NOT to Use

- Basics is unresolved or under negotiation. Differentiation depends on a stable input frame.
- The team has already pre-chosen differentiators and just wants ratification. The skill is built for genuine decision-making; ratification theater wastes the afternoon.
- The team has lost the room: low energy, no Decider, time pressure. Postpone or split into shorter blocks rather than rush.
- This is a follow-up sprint and the existing differentiation still holds. Use Magic Lenses directly with the existing position.

## What This Skill Produces

A single bundled artifact with five sections:

1. **Scored differentiator candidates**: a table of 8-15 candidate differentiators scored on three customer-perceived dimensions (customer pull, team can deliver, hard to copy). The top scorers advance to the 2x2 chart.
2. **Two chosen differentiators**: the two the team commits to as the strategic position.
3. **2x2 differentiation chart**: a customer-perceived chart plotting the chosen differentiators against the competitor set from Basics. The team's product position is named.
4. **Decision principles**: 3-5 principles operationalizing the differentiation. Each principle is a future-product rule ("we will always prefer X over Y").
5. **Mini Manifesto**: a one-page strategic summary written in the team's voice, naming the customer, problem, position, and what the product is NOT.

See `references/TEMPLATE.md` for the canonical structure and `references/EXAMPLE.md` for the Brainshelf example.

## Sequence (150 minutes)

### Step 1: Generate differentiator candidates (15-25 min)

Each team member produces 3-5 candidate differentiators silently. Cluster duplicates, then surface the full set (8-15 candidates is typical). The candidates can be classic (speed, price, simplicity, breadth, depth, trust) or custom (specific to this product or market).

### Step 2: Score candidates (25-40 min)

Score each candidate on three dimensions, 1-5 scale:

- **Customer pull**: would this customer-perceived dimension actually drive a switch?
- **Team can deliver**: can this team build and operate at this dimension competitively?
- **Hard to copy**: how durable is the advantage if a competitor pivots?

Sum the three for a rough score. Top 5-7 candidates advance.

### Step 3: Choose two differentiators (30-45 min via note-and-vote)

The team narrows to two differentiators through `tool-note-and-vote`. The two MUST be observable to the customer (not internal-team values) and deliverable by the team (not aspirational). The Decider supervotes if scoring produces a tie or the team is split.

### Step 4: Plot the 2x2 chart (15-25 min)

Place the two differentiators as the chart axes. Plot the competitor set from Basics (including "do nothing"). Position the product where it can occupy unoccupied space. If the unoccupied position is too far from where competitors cluster, the team may be drifting into a niche that customers don't recognize; if the position overlaps with a strong competitor, the differentiation is not strong enough.

### Step 5: Write decision principles (20-30 min)

Convert the two differentiators into 3-5 operational principles. Examples:

- "Capture is the first-class action. Every other feature waits behind a fast capture path."
- "Private by default. Sharing is opt-in."
- "Surface what's relevant when it matters. Not on a notification schedule."

Principles are NOT marketing copy. They are decision-making rules for future product calls.

### Step 6: Mini Manifesto (15-25 min)

The Decider drafts a one-page Mini Manifesto in the team's voice. Tone is plain, declarative, and direct about what the product is NOT (this is the part teams skip and shouldn't).

## Inference Inputs

| Input | What the skill does with it |
|---|---|
| Basics bundled artifact | Reads target customer (for "customer-perceived" check), problem (for "would this differentiator solve the problem"), ad

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 2abfbb9

Download folder ↗
git clone https://github.com/product-on-purpose/pm-skills
git -C pm-skills checkout 2abfbb961d31

The author documents no install command, so this uses the repository directly. Our verdict covers commit 2abfbb961d31 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 2abfbb961d31

Similar skills

Define Prioritization Framework✓SAFE

product-on-purpose/pm-skills

Run applicable prioritization frameworks (RICE, ICE, MoSCoW, Weighted Scoring, Kano) against a list of features or initiatives. Produces a comparison table showing where rankings agree and diverge across frameworks, and…

★ 741Grade B
Deliver Acceptance Criteria✓SAFE

product-on-purpose/pm-skills

Generates structured Given/When/Then acceptance criteria for a user story or feature slice, covering the happy path, key failure scenarios, and non-functional expectations in testable form. Use when turning requirements…

★ 741Grade B
Discover Journey Map✓SAFE

product-on-purpose/pm-skills

Maps a customer journey across stages, touchpoints, emotional curve, pain points, and moments of truth into a markdown artifact with an optional mermaid timeline or flowchart. Use when synthesizing existing research…

★ 741Grade B
Discover Market Sizing✓SAFE

product-on-purpose/pm-skills

Estimate market opportunity (TAM, SAM, SOM) using multiple sizing frameworks (top-down, bottom-up, comparable company, analogous market). Triangulates across frameworks, highlights where they converge and diverge as…

★ 741Grade B
Efforts✓SAFE

product-on-purpose/pm-skills

68 plug-and-play, best-practice product management skills for AI agents: 30 Triple Diamond phase + 11 foundation + 12 utility + 15 tool (Foundation Sprint + Design Sprint). Plus 6 sub-agents, workflows, 200+ output…

★ 741Grade B
Foundation Lean Canvas✓SAFE

product-on-purpose/pm-skills

Produces a one-page lean canvas across nine interlocking blocks (problem, customer, UVP, solution, channels, revenue, cost, metrics, unfair advantage) with optional inline HTML and SVG visual rendering. Use when framing…

★ 741Grade B

Questions about Tool Foundation Sprint Differentiation

What does the Tool Foundation Sprint Differentiation skill do?
68 plug-and-play, best-practice product management skills for AI agents: 30 Triple Diamond phase + 11 foundation + 12 utility + 15 tool (Foundation Sprint + Design Sprint). Plus 6 sub-agents, workflows, 200+ output samples, guides, and CI-enforced contracts. Apache 2.0.
Is Tool Foundation Sprint Differentiation safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Tool Foundation Sprint Differentiation access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (2abfbb961d31), read on 2026-10-19. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.