From emba-hwz
Help executives make high-quality decisions under uncertainty by exposing the cognitive biases and heuristics that are likely distorting the call, and by applying decision architecture techniques to debias the process. Use whenever the user faces a consequential business decision — investment, M&A, market entry, restructuring, key hire, crisis response, plant closure, pivot, go/no-go — especially when information is incomplete, stakes are asymmetric, or strong opinions are forming fast. Also trigger when the user asks about biases (confirmation bias, anchoring, availability, overconfidence, sunk cost, groupthink), pre-mortems, red-teaming, decision quality, "I need to think through this carefully," forecasting, or the Kahneman / Beshears / Gino body of work. Even when the user does not explicitly mention biases, if the situation is a non-trivial decision under uncertainty, use this skill.
How this skill is triggered — by the user, by Claude, or both
Slash command
/emba-hwz:entscheiden-unter-unsicherheitThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill operationalizes EMBA Block 1 Tag 3 (Julian Fieres, HWZ). The discipline at its center: executives do not make decisions in the conditions textbooks describe. They make them under time pressure, with partial information, while their own brains apply shortcuts that were optimized for ancestral environments, not for capital allocation in volatile markets.
This skill operationalizes EMBA Block 1 Tag 3 (Julian Fieres, HWZ). The discipline at its center: executives do not make decisions in the conditions textbooks describe. They make them under time pressure, with partial information, while their own brains apply shortcuts that were optimized for ancestral environments, not for capital allocation in volatile markets.
The good news from forty years of behavioral decision research: biases are not random. They are predictable. Once predictable, they are debiasable. The job of executive decision-making is therefore not to eliminate System-1 thinking (Kahneman) — that is impossible — but to design the decision process so the predictable distortions are caught and corrected before the decision is made.
Use it when the user is facing a non-trivial decision: capital allocation, M&A, market entry/exit, plant or product line closure, senior hire or fire, crisis triage, pivot vs. persevere, restructuring, big bet on a technology trend. Also use when the user is leading a team through a decision and wants the process to be high quality, not just the outcome.
Do not use it for routine operational choices (low stakes, reversible, repeatable) — those are better handled by SOPs and judgment, not by heavy decision architecture.
A high-quality decision can produce a bad outcome (the world is uncertain). A low-quality decision can produce a good outcome (luck). Hindsight collapses both into the same judgment. The single most useful executive habit: judge decisions by the process and information available when the call was made, not by what happened afterward.
Build this distinction into every output of this skill. The user should leave with a defensible decision process, not just a guess at the right answer.
Run the framing checks before any analysis. The frame is the hidden lever — a badly framed decision cannot be rescued by good analysis.
Use templates/decision-frame-canvas.md to capture.
Read references/biases-heuristics-catalog.md for the catalog. Then identify which biases are most likely active in this specific decision. Patterns:
Make the biases explicit in the deliverable — not as accusation, but as predictable distortions to design around.
Beshears & Gino's (2015) "Leaders as Decision Architects" reframes executive work: leaders should not just make decisions, they should shape the contexts in which decisions get made. Reference: references/decision-architecture.md.
Pick from this toolkit, sized to the decision:
The output of a serious decision process should be a single document with the structure in templates/decision-document-template.md. The discipline: if you cannot articulate the decision in a 2-page document, you have not made it yet.
Core sections:
Decisions die in the communication step more often than in the deliberation step. Use templates/decision-communication-template.md. The principles:
For consequential decisions, schedule the review now. Without this step, organizations cannot tell good decisions from lucky outcomes (or bad decisions from unlucky outcomes), and so they cannot get better.
Use scripts/decision_journal.py to scaffold a journal entry from a YAML spec.
The decisions this skill is invoked for are weighty. The output should feel like the work of a careful adult, not a deck. Plain language. Honest about uncertainty. Specific about what is being claimed and on what evidence.
Avoid:
Embrace:
The reference files inside this skill apply these sources to executive practice.
npx claudepluginhub sansan88/hwz-emba-claude-plugin --plugin emba-hwzProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.