Split Decision
When facing architectural decisions, technology choices, or strategic trade-offs, present options as a structured comparison and require explicit trade-off acknowledgment before proceeding. Triggers on words like "should we", "which approach", "what's the best way", or when Claude is about to recommend one approach over alternatives. Never present a single recommendation without showing viable alternatives first.
Install
npx skills add ElliotJLT/Claude-Skill-Potions --skill split-decisiongit clone --depth 1 https://github.com/ElliotJLT/Claude-Skill-Potions.git /tmp/Claude-Skill-Potions
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skill-Potions/skills/split-decision ~/.claude/skills/split-decisionPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Split Decision
<purpose>
Claude has a tendency to present "the best approach" as if there's only one right
answer. In reality, most significant decisions involve trade-offs. This skill
forces multi-option analysis before committing to any architectural, technology,
or strategic choice. No more single-option recommendations dressed up as
obvious conclusions.
</purpose>
## When To Activate
Trigger when you see:
- User asks "should we X or Y"
- User asks "what's the best approach for..."
- User asks "which is better..."
- Claude is about to recommend an architectural choice
- Claude is about to recommend a technology/library/tool
- Any decision with meaningful trade-offs (not trivial choices)
- Refactoring approaches with multiple valid paths
- Database, framework, or infrastructure decisions
Do NOT trigger for:
- Trivial decisions ("should I use let or const here")
- Bug fixes with clear solutions
- Syntax questions
- When user has already made the decision and just needs implementation
## Instructions
### Step 1: Identify Viable Options
Generate 2-4 genuinely viable options. These must be:
- Actually reasonable choices (not strawmen to make one look better)
- Different enough to have meaningful trade-offs
- Options you'd actually consider recommending
If there's truly only one viable option, state why alternatives don't apply.
### Step 2: Assess Each Option
For each option, evaluate:
| Dimension | What to assess |
|-----------|----------------|Details
- Skill name
split-decision- Repository
- ElliotJLT/Claude-Skill-Potions
- Path
skills/split-decision/SKILL.md- License
- MIT
- Repo updated
- 12 February 2026
FAQ
What does the Split Decision skill do?
When facing architectural decisions, technology choices, or strategic trade-offs, present options as a structured comparison and require explicit trade-off acknowledgment before proceeding. Triggers on words like "should we", "which approach", "what's the best way", or when Claude is about to recommend one approach over alternatives. Never present a single recommendation without showing viable alternatives first.
How do I install the Split Decision skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add ElliotJLT/Claude-Skill-Potions --skill split-decision. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Split Decision popular?
It lives in ElliotJLT/Claude-Skill-Potions, which has 62 GitHub stars and 2 forks.
Related skills
Agent Audit
62ElliotJLT/Claude-Skill-Potions
When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.
Battle Plan
62ElliotJLT/Claude-Skill-Potions
Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.
Breadcrumbs
62ElliotJLT/Claude-Skill-Potions
Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.
Subagent Driven Development
43obra/clank
Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks
Installing Skills System
43obra/clank
Fork, clone to ~/.clank, run installer, edit CLAUDE.md
Survey Experiment Eval
36dariia-m/my_claude_skills
Evaluates survey experiment designs for economics research. Produces a structured diagnostic report covering identification, randomization, power, survey instrument quality, demand effects, ethics, pre-registration, and analysis plan. Use this skill whenever the user describes a survey experiment, shares a pre-analysis plan, uploads a survey instrument or Qualtrics file, asks "does this design work", "review my experiment", "what's wrong with this RCT", "check my survey experiment", "evaluate my experimental design", "audit my design", or discusses any planned or ongoing survey-based randomize
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.