Agent skill
justify-decision
Provide evidence-based justification for architectural and design decisions
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/justify-decision
SKILL.md
Skill: justify-decision
What I do
I provide clear, structured rationale for technical choices. I focus on evidence, context, and consequences, ensuring that decisions are documented and defensible rather than based on mere opinion or habit.
When to use me
- When proposing a significant change to the architecture
- When choosing between multiple competing libraries or frameworks
- During the creation of Architectural Decision Records (ADRs)
- When explaining a complex design choice to stakeholders
Core principles
- Evidence over opinion — Use benchmarks, documentation, or historical data to support claims.
- Context is king — Explain the specific constraints and requirements that led to the decision.
- Consequence awareness — Explicitly state what we are gaining AND what we are giving up (technical debt, complexity, etc.).
- Distinguish reversibility — Identify if a decision is a "one-way door" (hard to undo) or a "two-way door" (easy to pivot).
Patterns & examples
ADR-Style Justification:
- Context: We need to handle 10k concurrent WebSocket connections on a single node.
- Decision: Use Elixir/Phoenix instead of Node.js.
- Evidence: BEAM VM's lightweight process model and built-in distribution primitives.
- Consequences: Team needs to learn a new language; better fault tolerance; lower operational overhead.
Decision Confidence Matrix:
- High Confidence: Backed by production data or extensive spike results.
- Medium Confidence: Backed by industry standard practices and documentation.
- Low Confidence: Based on theoretical advantages; requires early validation.
Anti-patterns to avoid
- ❌ Post-hoc rationalisation — Making a choice based on preference then looking for evidence to support it.
- ❌ Ignoring alternatives — Presenting a decision as the only option without acknowledging valid competitors.
- ❌ Vague justifications — Using terms like "industry standard" or "best practice" without explaining why they apply here.
KB Reference
~/vaults/baphled/3. Resources/Knowledge Base/AI Development System/Skills/Thinking-Analysis/Justify Decision.md
Related skills
trade-off-analysis— Weighing options before justifyingdocumentation-writing— Recording the justification clearlycritical-thinking— Validating the logic of the justificationarchitecture— Applying justifications to system design
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?