Evidence group skill. Runs direct end-user interviews to saturation. Gates on access — halts if discovery-context says user_access is none or proxy-only.
Use when summarizing whether the bet clears the bar — explicitly tally how many unique insights it carries across tech, market, and GTM. One isn't enough; name which ones and why.
Use FIRST, before hunting any bug — write down the system's trust model (who can reach what, which callers are already trusted, what the deployment model is).
Use before attacking a build that has any lifecycle, phases, or persisted progress — enumerate the states, transitions, and guards, then probe every transition under crash / kill…
Use to scan everything an outsider can read — README, marketing copy, docs, public config, AND error messages, stack traces, debug pages, response headers, and logs — for leaked…
Use whenever you write or review external copy in someone's voice (the founder/brand), and as a gate on every claim.
Use whenever you reach for a value (color, spacing, radius, type, motion) or build a component — extend tokens and shared components in place, never fork into one-off className…
Use to validate that a design actually works for real people — when a flow is built or prototyped and you need to know if users can do the job.
Use when reviewing a change, a design, or a system's readiness — ask "if this gets attacked or exploited in prod, would we even know?" Review the audit trail, the…
Use before a launch/traffic spike (marketing push, Black Friday, a new large customer) or when asked "can we handle the load / will this scale" — model the expected and worst-case…
Use when advancing a deal toward commitment — build a Mutual Action Plan working backward from go-live (including legal/procurement), drive each step, and ASK for the commitment…
Use when handed a real deck, one-pager, or pitch to assess end to end — the orchestration that turns the seven reads into the ordered deliverable.
Use pre-build, for a new idea, or at n=1 — is there a real market and will anyone pay? Run Mom-Test conversations on real prospects, hunt commitment + advancement, say "no one…
Use when making the actual call — a clear invest / pass with conviction, the single risk you'd underwrite, and the coaching you'd give either way.
Use when the question is "how do we reach buyers at all?" — distribution / go-to-market strategy. Run the Bullseye (brainstorm → cheap-test a few → focus the ONE that works) and…
Use when the system must change safely over time, when an invariant needs protecting, for "should we rewrite this?", or for a behavior-preserving refactor — protect the…
Use when gathering directly from people — talk about their life and specific past behavior, not your idea; get past Q&A into story; embrace silence.
Use when naming a product, feature, category, or pricing tier — or when an existing name confuses, over-promises, or fights the positioning.
Use while writing any diff — make it look like the rest of the codebase wrote it: match conventions, reuse shared components, stay DRY, write for the next human, and never leave a…
Use before or while designing when you need to understand users — their goals, context, mental models, and real behavior.
Use when applying AI to selling — conversation/deal intelligence, AI-assisted research/prioritization, AI SDRs, AI-aware forecasting.
Use first, before any copy — when positioning is unwritten, vague, aspirational, or being re-improvised per artifact.
Use when designing the ergonomics of a terminal / CLI / builder tool — command and flag design, sensible defaults, inferring arguments instead of demanding flags,…
Use before you run anything — statically walk every user journey end-to-end (happy path plus the error, empty, returning-user, and cancel states) by reading flow + spec + code, to…
Use when performance matters, something is slow, or a job is failing/timing out — measure before optimizing, profile to find the real bottleneck, parallelize independent work and…
Use throughout gathering and synthesis — name the biases that distort findings (sampling, leading, sponsor, social-desirability, confirmation, your own priors) and design and…
Use before scaling any message, after a launch underperforms, or whenever positioning is still a hypothesis (pre-users).
Use when generating or accepting AI/LLM-written code — treat the model as a fast junior, not an oracle: give it context, then verify every line; never ship plausible-but-wrong…
Use to land your review as a durable artifact — the attack surface reviewed, findings at file:line (or "none"), the P-grade and minimal fix, and a clear GO / NO-GO — including on…
Use whenever you record a claim — attach its verbatim source (the quote, who, when, what kind) so a finding can always be traced back.
Use when a QUALIFIED deal stalls — "let me think it over," goes quiet, keeps asking for more info, won't commit.
Use when scoping how to land a change — prefer small, short-lived, independently-safe increments over a big-bang merge; keep the codebase deployable; gate risky changes behind…
Use when the build implies quality beyond "it works" — sweep the non-functional surface: performance under load, accessibility, the obvious security holes, and…
Use to keep problems distinct from solutions — map how people actually think about getting their job done (their cognition, reactions, guiding principles), deliberately separated…
Use before recording any new person/entity/insight/belief — search what already exists and converge new signal onto it; coin a new node only when nothing fits.
Use when there's a technical or scientific claim under the pitch — push on the mechanism in proportion to how load-bearing it is.
Use whenever a load-bearing call is made (or asked again) — record problem, options, what was chosen, why, and what was rejected, so settled questions aren't re-litigated and "why…
Use when scoping any user-facing surface — require a whole-surface design up front; ship in slices, but each slice lands in its final place, nothing bolted on to be re-placed…
Use when investigating a build or a suspicious area where a fixed script won't find the unknown — run time-boxed exploratory sessions guided by a charter (a mission), learning,…
Use when consulted EARLY on a design or proposal (before the build) — say plainly what it would take to ship this safely while it's still cheap to change, and escalate…
Use when a verdict rests on a measured quantity rather than a single deterministic assertion — a noisy/probabilistic output, a performance number, an accuracy or conversion rate.
Use when scoping what to test on a non-trivial build — model coverage across the product's real dimensions (Structure, Function, Data, Integrations, Platform, Operations, Time) so…
Use when running a founder meeting or generating the questions you'd ask — the texture of the conversation, not a diligence checklist.
Use on a discovery or first real sales call — diagnose the buyer's problem with SPIN + Gap Selling (current → future → quantify the gap) before pitching anything; problem → impact…
Use when a build is proposed with no path to reach users — force distribution (channel + activation + retention loop) into the product decision.
Use when proposing the approach for an initiative, or when tempted to add structure "for future scale" — design the idiomatic, simplest thing that solves the real problem and…