ReddRadar
Agent skill
vibe-coding-yaml
AI outputs YAML descriptors instead of code, CLI executes deterministically for 100% auditable behavior with zero slop. Use when auditability is critical, generated code review needed, or deterministic execution required. YAML serves as intermediate representation. Triggers on "auditable generation", "YAML output", "deterministic execution", "code review", "vibe coding".
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/vibe-coding-yaml
SKILL.md
Vibe Coding YAML
Purpose
AI generates YAML descriptors instead of code, CLI executes deterministically for 100% auditable behavior with zero slop.
When to Use
- Auditable code generation
- Deterministic outputs required
- Generated code review needed
- UI component generation
- Infrastructure as code
- Compliance requirements
Core Instructions
Pattern
AI outputs YAML:
component:
type: Button
props:
text: "Submit"
variant: "primary"
onClick: "handleSubmit"
styles:
padding: "12px 24px"
borderRadius: "8px"
backgroundColor: "#007bff"
CLI executes deterministically:
generate-component component.yaml > Button.tsx
Benefits
- 100% auditable: Review YAML, not generated code
- Zero slop: Deterministic execution
- Versionable: YAML in Git
- Reproducible: Same YAML = same output
- Reviewable: Easier to review descriptors than code
Example Workflow
# 1. AI generates descriptor
descriptor = {
'type': 'api_endpoint',
'method': 'POST',
'path': '/users',
'handler': 'createUser',
'validation': {
'email': 'required|email',
'name': 'required|string'
}
}
# 2. Save as YAML
with open('endpoint.yaml', 'w') as f:
yaml.dump(descriptor, f)
# 3. Execute deterministically
$ generate-endpoint endpoint.yaml > routes/users.ts
# 4. Review YAML (not generated code)
$ git diff endpoint.yaml
Performance
- 100% auditable
- 0% slop rate
- Deterministic behavior
- Easy review process
Version
v1.0.0 (2025-10-23)
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
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?