decision-board

# Decision Board Render a single-file HTML board from a JSON spec, wait for the user to pick, read the result. Then apply the picks — write the doc, file the PRs, update configs, whatever the choices imply. This skill only handles the picking step. Extracting decisions and judging trade-offs happens before; applying choices happens after. ## When to use this skill The trigger is **structural fit, not domain and not count**. In order of importance: 1. **Same option shape across items.** Every item is `one-of-N` over options that share fields (label, optional cost / preview). If each item needs a custom shape, prose is better. 2. **Preview is worth seeing.** The user benefits from looking at each option's preview side-by-side rather than reading prose. If a single sentence captures the choice, inline Q&A is faster. 3. **One person, one sitting.** Solo decision-making, not async review. Item count is the weakest signal — roughly 5–30 is the typical sweet spot, but a well-structured 4-item case can still earn the board while a 10-item bag of unrelated questions doesn't. **Fit beats count.** If the structural fit doesn't hold, push back and suggest a different format. ## Workflow The skill processes a session in five steps. Each step has a clear handoff — the agent owns 1, 2, 4, 5; the user owns 3. ### 1. Extract decisions from the user's material The user usually arrives with unstructured material — a meeting recap, an audit document with conflicting paragraphs, a chat...