Skills, prompts, agents, automations, and files from people who use them in real work. Every listing is reviewed before it goes live.
5 listings for “safety”
A Claude Code subagent that turns on TypeScript strict checks one flag at a time and fixes the resulting errors directory by directory with real types, without falling back to `any` or blanket `@ts-ignore`.
ALAISkillHub Library
A drop-in .claude/settings.json with two PreToolUse hooks: one denies dangerous Bash commands (recursive deletes of root or home, force pushes to main, disk wipes, piping curl to a shell), the other blocks edits to .env files, keys and lockfiles.
ALAISkillHub Library
A Claude Code skill that reviews new schema migrations (Postgres and MySQL; Rails, Django, Laravel, Prisma, Alembic, Knex and raw SQL) for table locks, rewrites, unsafe renames, missing rollbacks and backfills that should run separately.
ALAISkillHub Library
A launch readiness checklist for LLM features covering scope, data and privacy, prompt and model config, evals, injection and tool safety, cost limits, observability, user disclosure, kill switch and post-launch review, with blockers marked.
ALAISkillHub Library
Labeler guidelines for comparing two model responses side by side: a priority order for deciding (safety, correctness, instructions, helpfulness, clarity), label definitions, per-response flags, rationale examples and edge cases.
ALAISkillHub Library
New features as they ship, AI live chat improvements, and the best new listings in the catalog.