Wedge · 2/5
Strategy
Six-pagers and metric trees that survive a smart skeptic.
knowledge engine: coming · standalone skills shipped
The problem
Strategy work fails in two predictable ways. One: the narrative reads cleanly to its author and collapses the first time a sharp exec reads it cold, because the argument has gaps the author filled in from memory. Two: the team chases a 'North Star' that nobody decomposed into the input metrics that actually move it. Both failures are recoverable with a couple of hours of structured self-review — which is exactly what the standalone skills here do.
The level-up path
Strategy is a standalone-skills wedge — there is no corpus-backed engine here, by design. Most strategy work is one-off: you have a memo, a metric goal, or a contested call. The right tool is a sharp single-shot skill, not a deep system that pretends to be smarter than you are.
Three skills:
narrative-review— reads your strategy doc the way a skeptical exec reads it cold. Surfaces logic gaps, claims-as-facts, and the steel-manned counterargument. Reviews; never rewrites.metrics-tree— turns a fuzzy goal (“increase activation”) into the top metric, its input metrics, the leading indicators, and the single metric most worth moving first. Never invents benchmark numbers.tradeoff-frame— exposes the real axes of disagreement on a contested decision and classifies the call as a one-way or two-way door. Frames; never picks.
A note on the knowledge engine
The deep, corpus-backed system is Discovery-only in v1. That is a deliberate choice — see the principles — and the reason is that strategy work, unlike discovery, doesn’t have a single versioned artifact (your research corpus) that benefits from a stateful graph in the same way. If a need for a strategy-side engine emerges from real use, it will land in a later version of mogkit. Until then, sharp standalone skills are the right tool.
Visual setup walkthrough
npx mogkit init my-strategy-workspace(one-time per workspace).- Open the workspace in Claude Code.
- Paste your strategy memo, metric goal, or contested decision into the relevant skill. Each returns a reasoning scaffold, not a rewrite.
- You write the next version. The skill made it sharper.
Skills to install
narrative-review
advanced standalone strategy
Reviews a strategy doc, six-pager, or memo the way a skeptical executive reads it — surfacing logic gaps, hand-waves, claims-as-facts, the strongest counterargument, and what a smart skeptic attacks first. The author keeps authorship.
metrics-tree
intermediate standalone strategy
Turns a fuzzy goal into a structured metrics tree — the top metric, its defining equation, the input metrics that compose it, the leading indicators, and the single metric most worth moving first — without inventing a number the PM hasn't measured.
tradeoff-frame
intermediate standalone conflict
Frames a contested decision honestly — names the real axes of disagreement, what each option optimizes versus sacrifices, whether the decision is a one-way or two-way door, and the evidence that would actually move a reasonable person. Frames; does not pick.
All of these install automatically when you run
npx mogkit init.
Material
A curated path. Not a link dump.
INSPIRED book
by Marty Cagan
The clearest articulation of what strong product orgs actually do — and what weak ones substitute in.
EMPOWERED book
by Marty Cagan
How product leaders create the conditions where strong product work is even possible. Read it after INSPIRED.
Lenny's Newsletter newsletter
by Lenny Rachitsky
The single most consistent stream of operator interviews and applied PM content on the internet.
Working Backwards book
by Colin Bryar & Bill Carr
The actual mechanism behind Amazon's six-pager and press-release-driven planning. Source material for narrative-led product work.