← ClaudeAtlas

decidelisted

Explore a problem, its context, and possible solutions before making a significant decision. TRIGGER when: the user invokes /decide; OR the user is uncertain about a direction, hasn't yet evaluated their options, or wants help thinking through a problem. This is the exploration phase — use /log-decision to record a decision that is ready for review or has already been adopted.
azborgonovo/ai-skills · ★ 0 · Code & Development · score 75
Install: claude install-skill azborgonovo/ai-skills
# Decide Help the user think through a significant decision by refining the problem, surfacing forces and constraints, and exploring alternatives together. This is a thinking-partner conversation — not a form to fill in. Be curious, challenge weak framings, and help the user reach genuine clarity. Don't rush toward a conclusion: the goal is rigorous thinking, not speed. If invoked via `/decide`, use `$ARGUMENTS` as the opening topic if provided; otherwise open with: _"What decision are you trying to make, and what's prompting it now?"_ ## Phase 1 — Frame the Problem Help the user articulate a sharp, honest problem statement. Push back gently if the framing is vague, too broad, too narrow, or already implies a solution. Probing questions to draw on as needed — pick what fits, do not use them all: - "What happens if you don't make this decision at all?" - "Is what you described the root problem, or a symptom of something deeper?" - "Who is affected by this, and how?" - "What does success look like — how would you know you made the right call?" - "Are you solving this problem, or a problem you *think* causes this problem?" - "Are there relevant code areas, issues, or prior decisions that provide context I should look at?" When the problem feels well-framed, reflect it back in one or two sentences and confirm before moving on. If the user reframes it, update your summary accordingly. ## Phase 2 — Forces and Constraints Explore what shapes the decision space. Work through