Foundation Sprint Approach Options

Try it: /pm-skills:tool-foundation-sprint-approach-options "Your context here"

Day 2 morning of a Foundation Sprint. The team forces itself to generate multiple plausible approaches before committing to one. The skill enforces a minimum of 3 approaches; anchoring on a single approach is the most common Day 2 failure mode.

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

When to Use

Day 2 morning of a Foundation Sprint.
Day 1 is signed; the Mini Manifesto, decision principles, and differentiation chart are committed.
The team is ready to generate candidate approaches before evaluating them through Magic Lenses in the afternoon.

When NOT to Use

Day 1 is unresolved. Approach Options without differentiation context produces approaches that miss the strategic position.
The team has only one approach in mind and is unwilling to generate alternatives. The skill forces minimum 3; if the team refuses, the issue is sprint discipline, not tooling.
More than 7 approaches are emerging organically. The skill caps generation at 7; beyond that the team is generating features, not strategic approaches.

How to Use

Invoke the skill by name (/pm-skills:tool-foundation-sprint-approach-options on Claude Code, $tool-foundation-sprint-approach-options on Codex):

/pm-skills:tool-foundation-sprint-approach-options "Your context here"

Or reference the skill file directly: skills/tool-foundation-sprint-approach-options/SKILL.md

What This Skill Produces

A single bundled artifact containing:

3 to 7 one-page approach summaries, each with:
- Name and label (color, letter, ID)
- One-sentence “what it is”
- “Why it’s a good idea” rationale (1 short paragraph)
- Simple doodle or textual visual description
- How the approach serves the two chosen differentiators
Approach set summary table comparing all approaches at a glance (label, name, capture mechanism, recall mechanism, primary trade-off).

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

Sequence (75 minutes)

Step 1: Frame the approach space (5 min)

The facilitator restates the differentiation: “We are committing to [differentiator 1] and [differentiator 2]. Approaches that fail either of these are out of scope.” This sets the boundary; the team generates inside it, not outside it.

Step 2: Silent ideation (15-20 min)

Each team member generates 2-4 candidate approaches silently. Cluster duplicates. Surface 8-12 candidates.

Step 3: Cluster and select 3-7 (15-25 min via Decider call)

The team clusters similar approaches and the Decider narrows to 3-7 candidates that will be one-page-summarized. The 3-minimum is enforced; if the team produces 2 candidates after clustering, push the team back to ideation to generate at least one more.

Step 4: One-page summarize each approach (25-40 min)

Each team member takes 1-2 approaches and writes the one-page summary. Each summary names:

Label: a color, letter, or short identifier (Yellow, Blue, Approach A, etc.)
What it is: one sentence the customer would understand
Why it’s a good idea: short paragraph naming the customer value and the team’s ability to deliver
Visual: a simple doodle or textual description of what the customer sees or does
How it serves the differentiators: one or two lines per chosen differentiator

Step 5: Cross-summary review (5-10 min)

The team reviews the full set, flagging summaries that don’t fit the differentiators or that overlap so heavily with another approach that they’re duplicates. The Decider approves the set advancing to Magic Lenses.

Approach Generation Discipline

The skill enforces five rules at decision-point:

Minimum 3, maximum 7. Fewer than 3 means the team is anchored on one idea; more than 7 means the team is generating features.
Each approach must be a strategic path, not a feature. “Add a settings screen” is a feature; “make capture the home screen” is a strategic path.
Each approach must serve both chosen differentiators (not just one). An approach that wins on differentiator 1 but fails differentiator 2 should be either revised or dropped.
Each approach must be visually describable. If the team can’t draw it on a card, the approach is too abstract for the sprint.
No first-idea bias. The first approach the team thought of should be included only if it survives the differentiation check; many teams find their initial idea is not the strongest after generating alternatives.

Inference Inputs

Input	What the skill does with it
Basics bundled artifact	Reads target customer to ensure approaches are designed for them, not for an adjacent customer
Differentiation bundled artifact	Reads the 2 chosen differentiators and the 2x2 position; flags approaches that miss either differentiator
Approach candidates (optional)	If pre-supplied, pre-populates the silent ideation board; team adds and refines rather than starting cold

Common Pitfalls

Generating features instead of approaches. “Add notifications” is not an approach; it’s a feature. The skill enforces strategic-path framing.
Too few options. Stopping at 2 approaches because “those are obviously the choices” anchors the team. Force a third even if it’s intentionally weaker; it surfaces the trade-offs.
Approaches that fail one differentiator. An approach that beats differentiator 1 but loses differentiator 2 has rejected the Day 1 strategic commitment. Either drop it or revise it.
Skipping the visual. “I can describe it in prose” defeats the purpose. The visual forces concreteness.
Overlap masquerading as distinct approaches. Two summaries that differ only in implementation detail are one approach. Cluster them.

Decider Role

The Decider’s job during Approach Options:

Restate the differentiation boundary at the start.
Narrow the clustered candidates to 3-7 for one-page summary.
Approve the final set advancing to Magic Lenses; reject summaries that drift from the differentiation.

The Decider does NOT pick a top approach in this skill. Magic Lenses produces the top bet; Approach Options produces the candidates Magic Lenses will evaluate.

Canonical Sources

Character Capital. “Foundation Sprint guide.” Approach generation agenda.
Knapp, J., and Zeratsky, J. Click. Day 2 morning sequence.

Cross-Skill Usage

Prerequisites: tool-foundation-sprint-differentiation. The Day 1 strategic position is the load-bearing input.

Next invocation: tool-foundation-sprint-magic-lenses in the afternoon. The approach set produced here is the input to Magic Lenses scoring.

Decider Checkpoint

This skill ends with a Decider Checkpoint in references/TEMPLATE.md. The Decider signs off on the set of approaches advancing to Magic Lenses, confirming none are out-of-scope and none are duplicates. Without sign-off, Magic Lenses begins with an unstable candidate set.

Output Template

Foundation Sprint Approach Options: [Initiative name] (Day 2 Morning)

Approach [N]: [Approach name]

Label: [Color / letter / ID, e.g., Yellow / A / “Camera-First”]

What it is: [One sentence the customer would understand.]

Why it’s a good idea:

[One short paragraph naming customer value and team capability. Cite specific evidence from Basics (customer pain) and Differentiation (team advantage).]

Sketch:

[Simple ASCII or textual description of what the customer sees or does. Doesn't need to be polished; needs to be concrete enough that someone reading the page can imagine using it.]

How it serves the differentiators:

[Differentiator 1]: [How this approach delivers on it.]
[Differentiator 2]: [How this approach delivers on it.]

Approach Set Summary

Label	Approach	Primary capture / interaction	Primary value	Top trade-off
[Label 1]	[Name 1]	[How the customer interacts]	[Differentiator served strongest]	[What it sacrifices]
[Label 2]	[Name 2]	[…]	[…]	[…]
[Label 3]	[Name 3]	[…]	[…]	[…]

[Add rows for each approach in the set.]

Decider Checkpoint

Decider sign-off required before Day 2 afternoon (Magic Lenses) begins.

Decider confirms the set of [3-7] approaches advancing to Magic Lenses.
Decider confirms all approaches honor the [2] decision principles from Day 1.
Decider confirms each approach serves both committed differentiators (not just one).
Decider acknowledges that Magic Lenses will narrow to 1 top bet plus 1 backup; not all approaches will survive.
Decider has not pre-committed to any specific approach; entering Magic Lenses with genuine uncertainty.

Signed: [Decider name, role], [ISO date and local time]

Example Output

Foundation Sprint Approach Options: Brainshelf (Day 2 Morning)

Five candidate approaches generated by the Brainshelf team, advancing to Magic Lenses in the afternoon. The team generated 9 candidates in silent ideation, clustered them, and the Decider narrowed to 5 for one-page evaluation. (Per the ratified spec decision: minimum 3, warn at 4-7, reject at 8 or more.)

Approach A: Camera-First Capture

Label: Yellow / Camera

What it is: The home screen is a camera. Point it at a book spine, dust jacket, or shelf and the app captures it via OCR plus cover-recognition into a private library.

Why it’s a good idea:

Eliminates typing entirely. Sub-3-second capture is achievable. Naturally private (no feed). Matches how people physically encounter books they want to remember. The 22 customer interviews repeatedly named typing-friction as the #1 reason for abandoning Goodreads; this approach attacks that pain directly.

Sketch:

+----------------+
|                |
|   [CAMERA]     |
|     viewfinder |
|                |
|   "Snap a book"|
|                |
|  [recents]     |
+----------------+

How it serves the differentiators:

Capture speed: maximum (single action, no typing).
Personal recall: requires complementary recall view (separate screen reachable from library badge).

Approach B: Library Browser

Label: Blue / Library

What it is: The home screen is the user’s personal library (visual grid of book covers). A persistent capture button floats above. Recall is by browsing.

Why it’s a good idea:

Beautiful default state. Matches mental model of a physical shelf. Recall is one tap. Customers who use Apple Books or Kindle’s library view recognize the pattern immediately.

Sketch:

+----------------+
| [+] My Library |
|  [b][b][b][b]  |
|  [b][b][b][b]  |
|  [b][b][b][b]  |
|                |
+----------------+

How it serves the differentiators:

Capture speed: high but requires extra tap (Floating Action Button).
Personal recall: very high (the home screen IS recall).

Approach C: Voice-First Capture

Label: Green / Voice

What it is: User speaks: “Just finished Project Hail Mary, loved the alien biology.” App resolves the book, captures the note, files it. Recall is also voice (“did I read anything by Andy Weir?”).

Why it’s a good idea:

Hands-free. Captures opinions, not just titles. Especially fast from physical contexts (walking out of bookstore, finishing on a treadmill).

Sketch:

+----------------+
|                |
|  "Speak"  [mic]|
|                |
|  Listening...  |
|                |
|  Just heard:   |
|  "Project Hail |
|   Mary"        |
+----------------+

How it serves the differentiators:

Capture speed: very high (no UI manipulation).
Personal recall: medium (voice recall is less reliable for “did I read X?”).

Approach D: Bookstore Mode

Label: Red / Store

What it is: A specialized mode triggered by geofence at bookstores and libraries that switches the app into “have I read this?” lookup. Browse with phone in hand; titles flash up read/unread status.

Why it’s a good idea:

Surfaces personal recall at the highest-friction moment. Solves the “did I already read this?” pain directly. Differentiated against every competitor (none does this today).

Sketch:

+----------------+
|  Powell's      |
|  Books         |
|                |
|  Project Hail  |
|  Mary  [READ]  |
|                |
|  Tomorrow      |
|  [NEW]         |
+----------------+

How it serves the differentiators:

Capture speed: lower than A/B/C (mode-specific entry).
Personal recall: extremely high (context-aware recall).

Approach E: Read-Later Capture Triage

Label: Purple / Triage

What it is: Brainshelf is a strict capture-and-recall tool for “want to read” intent. Recommendations from any source (article, friend text, podcast) flow into a single triage queue; user processes weekly.

Why it’s a good idea:

Solves the “I get recommendations and lose them” pain directly. Models the product on Pocket / Instapaper, which is a familiar mental model.

Sketch:

+----------------+
| Inbox (8 new)  |
|                |
| Snow Crash     |
|   from Sarah   |
|   [archive]    |
|                |
| Pachinko       |
|   from Vox     |
|   [archive]    |
+----------------+

How it serves the differentiators:

Capture speed: high via share extension.
Personal recall: medium (recall is about queue, not memory).

Approach Set Summary

Label	Approach	Primary capture / interaction	Primary value	Top trade-off
Yellow	Camera-First	Visual scan + OCR	Maximum capture speed	Recall is secondary screen
Blue	Library Browser	Tap-add (FAB)	Recall-as-home-screen	Capture takes extra tap
Green	Voice-First	Voice	Hands-free	Voice recall less reliable
Red	Bookstore Mode	Geofenced lookup	Context-aware recall	Niche; requires location data
Purple	Triage Inbox	Share extension	Captures recommendations from anywhere	No personal recall mechanism

Decider Checkpoint

Decider sign-off required before Day 2 afternoon (Magic Lenses) begins.

Jamie confirms 5 approaches advance to Magic Lenses evaluation.
Jamie confirms all 5 honor the 5 decision principles from yesterday.
Jamie confirms each approach serves both committed differentiators (Yellow and Red strongest on opposite poles; Blue, Green, Purple balanced).
Jamie acknowledges that Magic Lenses will narrow to 1 top bet plus 1 backup; not all 5 will survive.
Jamie has not pre-committed to any approach; entering Magic Lenses with genuine uncertainty.

Signed: Jamie (founder, PM), 2026-05-14 11:50 PT