Results for “llm-guardrails”

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode". (gstack)

Safety guardrails for destructive commands. (gstack)

Create minimal framed grid layouts with thin visible boundary lines, L-shaped corner brackets, subtle diagonal line texture, and strict section alignment. Use when asked for clean, neutral, precise, structured, editorial, technical, or guide-border web layouts.

Use when adding a fixed full-screen WebGL laser background with a thin white-hot vertical core, restrained brand-colored halo, and soft smoky fog. Prefer this over mengto-corner-lasers when the beam is a full-viewport WebGL background, not corner ornaments; not for full page layout, copy, or unrelated particle systems.

Use when composing corner-anchored laser accents with thin beams, a bright emitter node, bloom, and atmospheric glow or fog. Prefer this over mengto-webgl-laser when lasers are layout corner ornaments, not a fixed full-screen WebGL beam.

Use when adding a perspective WebGL background grid with fading lines, subtle particle haze, slow forward drift, and gentle camera parallax. Prefer this over mengto-atmosphere-background when the grid/mesh motion is the hero, not soft light folds.

Reads related records across multiple sObjects in one GraphQL request, paginates related lists with cursors, and replaces overlapping @wire(getRecord) calls with a single cache-shared query.

AI safety and responsible AI practices

Design product experiments around hypotheses, audience, metrics, guardrails, and decisions.

Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.