platform-database
Principles
- Prefer UNION ALL over UNION unless you specifically need deduplication
Rules
See rules index for detailed patterns.
Examples
Positive Trigger
User: "Review this schema and migration plan for zero-downtime rollout."
Expected behavior: Use platform-database guidance, follow its workflow, and return actionable output.
Non-Trigger
User: "Implement ARIA labels and focus rings on this modal."
Expected behavior: Do not prioritize platform-database; choose a more relevant skill or proceed without it.
Troubleshooting
Skill Does Not Trigger
- Error: The skill is not selected when expected.
- Cause: Request wording does not clearly match the description trigger conditions.
- Solution: Rephrase with explicit domain/task keywords from the description and retry.
Guidance Conflicts With Another Skill
- Error: Instructions from multiple skills conflict in one task.
- Cause: Overlapping scope across loaded skills.
- Solution: State which skill is authoritative for the current step and apply that workflow first.
Output Is Too Generic
- Error: Result lacks concrete, actionable detail.
- Cause: Task input omitted context, constraints, or target format.
- Solution: Add specific constraints (environment, scope, format, success criteria) and rerun.
Workflow
- Identify whether the request clearly matches
platform-databasescope and triggers. - Apply the skill rules and referenced guidance to produce a concrete result.
- Validate output quality against constraints; if gaps remain, refine once with explicit assumptions.
More from ravnhq/ai-toolkit
core-coding-standards
Universal code quality rules — KISS, DRY, clean code, code review. Base
79promptify
Transform user requests into detailed, precise prompts for AI models.
65lang-typescript
TypeScript language patterns and type safety rules — strict mode, no
52tech-react
React 19 patterns for components, hooks, Server Components, and data
51design-frontend
Visual design system patterns for web UIs. Tailwind CSS v4 design tokens
42platform-backend
Server-side architecture and security — API design, error handling, validation,
39