← ClaudeAtlas

challengelisted

Challenge a plan, design, or approach in two structured passes — scope/necessity, then correctness/completeness. Use before executing any plan.
dagonet/claude-code-toolkit · ★ 3 · AI & Automation · score 72
Install: claude install-skill dagonet/claude-code-toolkit
# Challenge a Plan or Design Challenge the current plan, approach, or design with two structured passes. Catches over-engineering, missing requirements, YAGNI violations, and implementation flaws early. ## Arguments - `$ARGUMENTS` — (Optional) Description of what to challenge. If omitted, challenge the current plan or approach in the conversation context. ## Workflow 1. **Identify the target** - If `$ARGUMENTS` is provided, use it as the challenge target - If omitted, identify the most recent plan, design, or proposed approach in the conversation - If no clear target exists, ASK the user what to challenge 2. **Attempt architect delegation** - If an architect agent is available (team context with AGENT_TEAM.md), spawn the architect to perform both challenges - If no architect is available (solo session), perform both challenges directly 3. **Challenge 1 — Scope & Necessity** - Is every component/feature actually needed? (YAGNI check) - Are there simpler approaches that were dismissed too quickly? - Are edge cases identified but deferred appropriately? - Does the design solve the stated problem without gold-plating? - Is the tier assignment (if applicable) correct for the scope? - Could any pieces be cut without losing the core value? 4. **Challenge 2 — Correctness & Completeness** - Does the plan match the stated requirements faithfully? - Are there missing steps, untested paths, or incorrect assumptions? - Are error handling a