Best LLM guardrails skills, page 5

Decide which of your recurring rituals to put on autopilot — and which to keep manual.

mohitagw15856/pm-claude-skills

Set up a repo or project so an AI coding agent works well in it — the CLAUDE.md, the context, the guardrails, and the conventions the agent needs to be useful instead of lost.

mohitagw15856/pm-claude-skills

Delegate so the work comes back right the first time — the brief that transfers outcome, context, and constraints (not just the task), the autonomy level stated explicitly, and the check-in design…

mohitagw15856/pm-claude-skills

Protect aging parents from the scams that target them — the conversation that doesn't condescend, the family code word, the top patterns aimed at seniors, and the guardrails that help without taking…

mohitagw15856/pm-claude-skills

Specify the safety and reliability guardrails for an LLM feature before it ships.

mohitagw15856/pm-claude-skills

Plan a paid acquisition / performance marketing program with unit economics that work.

mohitagw15856/pm-claude-skills

Run a rigorous candidate reference check that surfaces real signal.

mohitagw15856/pm-claude-skills

Figure out the best card or payment route for a purchase (or your everyday spending) to maximize cashback/points — without overspending or drowning in complexity.

mohitagw15856/pm-claude-skills

Design a small team of AI agents to tackle a complex task in parallel — who does what, how they hand off, and how to keep them coordinated — instead of one overloaded agent doing everything serially.

mohitagw15856/pm-claude-skills

Build a staff shift schedule that matches coverage to demand while hitting a labor-cost target.

mohitagw15856/pm-claude-skills

Design a usage-based pricing scheme that scales revenue with value without scaring customers away — the metric that tracks value, tiers with included volume, and the guardrails that prevent bill…

mohitagw15856/pm-claude-skills

Build and debug Browser Use tools/actions: custom Tools/Controller actions, default browser/file actions, ActionResult returns, parameter injection, sensitive data, security guardrails, and…

VectorSpaceLab/AREX-Skill

Streamlined fast-path for trivial data-only fixes — no TDD, no branching ceremony.

danielvm-git/bigpowers

Security wrapper over the upstream agent-browser skill, adding URL blocklisting, rate limiting, robots.txt enforcement, and scraping guardrails.

yonatangross/orchestkit

Framework for demonstrating AI capabilities in legal contexts.

lawve-ai/awesome-legal-skills

Select appropriate Ollama models for processing sensitive but legal content.

divinevideo/divine-mobile

A skill your agent uses when deciding whether a responsible-AI project belongs at ACM FAccT or should route to a pure-ML venue (NeurIPS/ICML/ICLR), an HCI venue (CHI/CSCW), a law/policy venue, or an…

brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when planning an ACM FAccT project timeline from venue fit through abstract registration, OpenReview submission, the rebuttal window, the new Accept/Revise/Reject…

brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when building or debugging OpenAI Agents SDK workflows — defining agents with tools and handoffs, wiring typed context, streaming responses, adding guardrails, or integrating…

kid-sid/claude-spellbook

A skill your agent uses when a team must decide what to measure before building anything — picking one north-star metric, separating leading input drivers from lagging outputs, adding guardrails so…

ericrisco/rsc-harness

Creates behavioral rules in markdown to block dangerous commands or restrict AI behavior.

athola/claude-night-market

Sequence pre-event readiness (listing assets, review count, inbound inventory) against a promotion timeline, then lay out automatic, manual, product-targeting, brand, and display ad structures…

xjli360/sealeap-amazon-skills

Set up a beginner Sponsored Products structure on the US marketplace in five gated steps—auto campaigns bid by targeting group, search-phrase research, manual keyword campaigns, product (ASIN)…

xjli360/sealeap-amazon-skills

A skill your agent uses when you need evidence-bounded safety policy, abuse categories, refusal/redirect behavior, privacy, escalation, and Human risk decisions; triggers include AI 安全 and AI safety.

majiayu000/claude-skill-registry

You are an expert in the OpenAI Agents SDK (formerly Swarm), the official framework for building multi-agent systems.

majiayu000/claude-skill-registry

Define deterministic guardrails for agent tool calls — protected paths, test-file locks during bug fixes, post-edit formatters, production approval gates, secret deny rules.

HoangNguyen0403/agent-skills-standard

Interacts with Google Cloud services using the gcloud CLI safely and efficiently.

Kilo-Org/kilo-marketplace

5-layer agent output validation, I/O contract specification, vertical slice development, and test doubles policy with per-layer examples

nWave-ai/nWave

Tool safety protocols, adversarial output validation, error recovery patterns, and I/O contracts for research operations

nWave-ai/nWave