Day 2 afternoon move of a Foundation Sprint. Evaluates the candidate approach set through multiple lenses (4 classic plus at least 1 custom) to surface trade-offs, identify consistent winners and contradictions, and produce a top bet plus a backup plan. Use after Approach Options is signed. Lens scoring is a sense-making tool, not mathematical truth; arbitrary precision is a smell.
SkillScore86Maintained
Automatic
◆Product Management pack
Last verified 8/18/2026
What it changes
Passed 19 of 22 test cases with the skill, and 8 of 22 without it.
Without skill36%
With skill86%
Checks it passed that the model alone missed
Drafts the decision rationale as a single concise paragraph.
Uses the four classic lenses: Customer, Pragmatic, Growth, and Money.
Declines to run the evaluation because fewer than 3 options are provided.
and 17 more in the full report
12 fixed7 passed either way2 still failing1 broke
Pass-rate lift
+50 pp
Tokens
+60%
Agent turns
0%
Response time
-12%
Model gemini-3.6-flashMeasured 8/18/2026v119 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
What is the core focus and question asked by the Growth lens in the Magic Lenses evaluation framework?
What was checked, without and with the skill
Checked
Without skill
With skill
Asks which approach gives a story strong enough to acquire users without paid channels or through word-of-mouth.
Missed
Passed
case-18 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md120 lines3 files
Foundation Sprint Magic Lenses
Day 2 afternoon of a Foundation Sprint. The team evaluates each candidate approach from multiple perspectives, surfaces contradictions, and produces a top bet plus a backup plan. The Decider names both; without an explicit backup, invalidation of the top bet sends the team back to ambiguous debate.
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 afternoon of a Foundation Sprint.
Approach Options is signed; the team has 3-7 candidate approaches advancing.
The team has at least 1 team-specific custom lens prepared (per ratified spec decision; classic lenses alone are insufficient).
When NOT to Use
Approach Options is unresolved or under-numbered (fewer than 3). Force a third option through the approach-options skill first.
The team has pre-committed to a top bet. Magic Lenses is a sense-making exercise; if the decision is already made, the time is better spent on Founding Hypothesis.
The team is exhausted and cannot evaluate clearly. Postpone to Day 2 morning of a follow-up sprint rather than rush.
What This Skill Produces
A single bundled artifact with six sections:
Classic lens charts: customer, pragmatic, growth, money lenses each as a 2x2 plot or qualitative position of every approach.
Custom lens charts: at least 1 team-specific lens (defensibility, mission fit, founder excitement, learning rate, etc.).
Pattern review: consistent winners across lenses, contradictions, biggest trade-off the team is making.
Top bet: the Decider's chosen approach with rationale.
Backup plan: the runner-up approach the team falls back to if the top bet invalidates.
Decision rationale: one paragraph explaining why the top bet over the backup.
See references/TEMPLATE.md for the canonical structure and references/EXAMPLE.md for the Brainshelf example.
The Five Canonical Lenses
Lens
What it asks
Why it matters
Customer
Which approach do target customers immediately understand and want?
If customers don't get it, nothing else matters
Pragmatic
Which approach can the team ship at quality in [build window]?
Beautiful approaches the team can't ship are not real options
Growth
Which approach gives the team a story strong enough to acquire users without paid channels?
Friction at the door tells you about word-of-mouth potential
Teaches PMs to create syntactically valid mermaid diagrams by selecting the right diagram type for their communication need, following syntax validity rules, and validating before shipping. Covers all 15 mermaid diagram types with PM-relevant examples and a dual-lens navigation system.