Agent skill
design
Design a feature or change into a reviewed ADR. Outputs an accepted decision record ready for /scope.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/design-lightforgelabsstudio-aide
SKILL.md
Design
Produce an Architecture Decision Record (ADR) for a feature or change. Read AGENTS.md if not in context.
Inputs
Design question or topic. Timebox if relevant.
Review-aware
Before starting: check if <artifact>.findings.md exists for this topic. If it does, read it and incorporate findings before proceeding.
Workflow
-
GitHub state check — Run
gh issue listandgh pr listto avoid proposing already-built or conflicting work. -
Shape options — Produce 1 recommended option (+ 1 alternative max). Include: pros/cons, risks, dependencies, success validation.
-
Draft ADR — Write to
.aide/docs/decisions/YYYY-MM-DD-<slug>.md(AIDE framework decisions) ordocs/decisions/YYYY-MM-DD-<slug>.md(game/project decisions). Status:Draft. -
Cross-review — Use
/findingsto exchange findings before accepting. Do not accept unreviewed ADRs. -
Accept — Set status to
Accepted. Hand off to/scopeto decompose into GitHub issues.
ADR format
# Title
Status: Draft | Accepted | Superseded
## Context
## Decision
## Rationale
## Consequences
Reference
- Design pillars:
design/directory - Quick reference:
docs/DESIGN_QUICK_REFERENCE.md
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?