Agent skill
design-challenger
Evaluate high-level protocol or system designs for overcomplication, then propose simpler, more structured alternatives with explicit trade-offs. Use when the user wants to challenge a system design, simplify an architecture, reduce protocol complexity, or compare design alternatives.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/design-challenger
SKILL.md
Design Challenger
- Identify overcomplicated designs (too many moving parts, cross-file flow complexity, fragile invariants).
- Propose cleaner alternatives that reduce invariants, shorten flows, and consolidate responsibilities.
- Stay objective by grounding suggestions in project context, requirements, and assumptions.
- Allow bold redesigns (some recall is acceptable) while keeping trade-offs explicit.
- Avoid code-level refactors; focus on protocol/system-level design changes only.
TRIGGER: User provides a high-level protocol or system design for evaluation.
- Clarify the context briefly when needed: intended users, runtime constraints, compatibility needs, and failure modes.
- If domain context is missing, consult references before proposing alternatives.
- Map the current design at a high level: components, handoffs, invariants, and cross-file flow.
- Identify the overcomplication drivers: unnecessary indirections, redundant layers, excessive configurability, or fragile sequencing.
- Propose one or more simpler designs that meet the same requirements with fewer moving parts.
- If major simplification requires removing a feature, make the case and note impact; consider modular or optional variants when removal is too costly.
- Explicitly enumerate trade-offs for each alternative.
Load only the minimum needed for the task.
references/context-questions.md: use when the prompt lacks constraints.references/complexity-smells.md: use to spot overcomplication drivers.references/simplification-tactics.md: use to structure alternatives.references/decision-matrix.md: use when multiple options must be compared.references/tradeoff-catalog.md: use to enumerate trade-offs.references/domain-context.md: use only when domain context is missing.
<output_format>
Output Format
Use the following format and keep it concrete and concise. Do not include code.
- What is overcomplicated
- ...
- Simpler alternative
- ...
- Trade-offs
- ... </output_format>
- Do not suggest code edits or function-level tweaks (e.g., no line-level or snippet changes).
- Avoid subjective preferences; justify improvements by reducing complexity, invariants, or moving parts.
- Do not propose changes that reduce security posture; simplifications should be neutral or positive for security.
- Feature removal is allowed only with clear justification (usage, risk, maintenance cost, compatibility impact).
- If requirements force complexity, say so and focus on the minimal simplifications that preserve constraints.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?