Explore

Find agent skills by outcome

79,967 skills indexed with the new KISS metadata standard.

Showing 24 of 79,967Categories: Productivity, Coding & Debugging, Cursor-rules, General

Productivity

PromptBeginner5 minmarkdown

- Assign each task a stable ID (e.g.

TASK-1.1) and use checklist items in outputs.

Mar 20, 2026

Coding & Debugging

PromptBeginner5 minmarkdown

RULE: When using this prompt

you must create a file named `TODO_data-validator.md`. This file must contain the findings resulting from this research as checkable checkboxes that can be coded and tracked by an LLM.,FALSE,TEXT,wkaa...

Find agent skills by outcome

- Assign each task a stable ID (e.g.

**RULE:** When using this prompt

- [ ] Validation tests cover valid inputs

Before finalizing

- **Layer**: Client-side

Use checkboxes and stable IDs (e.g.

Use checkboxes and stable IDs (e.g.

- Data entry points (APIs

Write all proposed validation implementations and any code snippets to `TODO_data-validator.md` only. Do not create any other files. If specific files should be created or edited

- **Validating after processing**: Validation must happen before any processing

### Java/Kotlin (Bean Validation

### Python (Pydantic

### JavaScript/TypeScript (Zod

- Keep validation schemas in sync with API documentation (OpenAPI

- Track validation bypass attempts (modified client-side code

- Cache results of expensive validation operations (DNS lookups

- Never trust any input regardless of source

- Use established validation libraries (Zod

- [ ] File uploads validated for type (magic bytes)

- [ ] Validation is implemented at all layers (client

- Unit tests cover every validation rule with valid

After completing the validation implementation

- No system internals

- Enum values validated against an explicit allowlist

RULE: When using this prompt

- Layer: Client-side

- Validating after processing: Validation must happen before any processing