Best LLM guardrails skills for Claude Code, Codex and other agents.

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.

fossasia/eventyay-interpretation

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails…

RedWoodOG/Hermes-Desktop

设置 Claude Code hooks，在危险 git commands（push、reset --hard、clean、branch -D 等）执行前阻止它们。适用于用户想防止破坏性 git 操作、添加 git safety hooks，或在 Claude Code 中阻止 git push/reset 时。

vinvcn/mattpocock-skills-zh-CN

Behavioral guardrails for LLM-assisted coding. An agent skill from alirezarezvani/ClaudeForge.

alirezarezvani/ClaudeForge

Systematically reduce the shipped bundle size of a JS/TS library without sacrificing code readability or breaking consumer APIs.

kcsujeet/ilamy-calendar

Interactive scaffold generator for Orloj multi-agent systems.

OrlojHQ/orloj

Read AI Safety HOT daily digests, search recent AI safety research and incidents, and follow current hot topics.

wuyoscar/AISafetyHot-Hub

Installs, tunes and enforces Sponsio contracts that block unsafe tool calls in LLM agents, covering setup, auditing, observe mode and flipping to enforce.

SponsioLabs/Sponsio

Checks each shell command for destructive patterns such as recursive deletes, force pushes and dropped tables, and asks before letting them run.

garrytan/gstack

Turns a natural-language description of routing intent into a valid Lemonade collection.router policy JSON.

amd/skills

当需要为 AI 产品定义核心身份、角色声明和能力边界时调用此 skill。典型场景包括：设计新 AI 产品的 system prompt 首段、为不同场景创建差异化角色（如教学助手 vs 编程代理）、重新定义 AI 与用户的关系框架。

kangarooking/system-prompt-skills

按中国法规（网安法 / PIPL / 等保2.0 / 数据出境 / AI生成内容标识）审计一个 AI 项目的代码仓库，产出每条都带 文件:行 取证、经独立复核、经脚本校验的合规报告。当用户问「这个项目上线合不合规」「调用了 OpenAI/Claude 算不算数据出境」「要不要做 AI 标识」「帮我做合规自查/等保/PIPL 检查」时使用。Audit an AI project's…

jnMetaCode/shellward

Expert ISO 42001 AI Management System (AIMS) compliance advisor.

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

Designs, tests and refines LLM prompts: zero-shot, few-shot and chain-of-thought patterns, system prompts, structured output schemas and evaluation test suites.

Jeffallan/claude-skills

Always-on operational guardrails, model-independent. An agent skill from mrtooher/fable-mode.

mrtooher/fable-mode

Installs hooks that check each agent action against security policies before it runs, blocking destructive commands and logging every decision.

pegasi-ai/reins

Guide for writing eval conversation JSONs and running them through policy engines

open-bias/open-bias

A skill your agent uses when you need a deterministic inspection of a WordPress repository (plugin/theme/block theme/WP core/Gutenberg/full site) including tooling/tests/version hints, and a…

gambitph/Stackable

Generate preventive Well-Architected guardrails — AWS Config rules, Service Control Policies, permission boundaries, CloudWatch alarms, and IaC policy checks (CDK Aspects, cfn-guard, OPA/Sentinel) —…

aws-samples/sample-well-architected-skills-and-steering

Route Celestia requests to the correct repo and apply canonical blob submit/retrieve guidance (Go, Rust, and Node RPC) with docs guardrails.

celestiaorg/docs

Pick the right SDAF BOM for a target SAP product / release / DB platform / version / kernel / topology.

Azure/sap-automation

A skill your agent uses when we want to turn a just-finished Formax workflow (e.g.

yusifeng/formax

设置 Claude Code 钩子，在危险 Git 命令（push、reset --hard、clean、branch -D 等）执行前将其拦截。当用户想要防止破坏性 Git 操作、添加 Git 安全钩子或在 Claude Code 中阻止 git push/reset 时使用。

devcxl/mattpocock-skills-zh

A skill your agent uses for any question or action about the user's AI/GenAI applications or agents — their behavior, prompts/responses, quality, hallucinations, guardrails, security, cost/tokens…

coralogix/cx-cli

Check user-generated text against a written policy before it is published.

mrmps/classifier-dev

Enforces staged execution discipline on large tasks: a written stage plan, delegation to named fable agents where the runtime supports it, a failable verification check at each stage, and a…

mrtooher/fable-mode

Guide for creating a new policy engine under openbias/policy/engines/

open-bias/open-bias

A skill your agent uses when designing or reviewing a backend MVP with tight budget, evolving schema, and reliance on third-party backends where idempotency, replay, and responsibility attribution…

victorGPT/vibeusage

A skill your agent uses when the user wants to turn an application, product, startup idea, SaaS, mobile app, web app, API, AI product, or internal tool into a production-ready Markdown specification…

instructa/agent-skills

Select and run Guardrails verification for code, dependency, test, tooling, documentation, or repository-workflow changes.

openai/openai-guardrails-js

How to dispatch well — choosing flash vs pro, writing self-contained briefs, parallelism, verifying results, and guardrails

ZSeven-W/dsh-crew

Explains how to train a model to be harmless with self-critique, revision and AI-generated preference feedback, with Hugging Face and TRL code for each stage.

Orchestra-Research/AI-Research-SKILLs

TypeScript anti-slop guardrails. An agent skill from web-infra-dev/rstest.

web-infra-dev/rstest

Step-by-step guide for adding a new guardrail provider to Agent Kernel.

yaalalabs/agent-kernel

Evaluate, rank, and communicate work priorities using AI as a structured thinking partner.

ILoveDotNet/ilovedotnet

Migrate Python OpenAI Agents SDK applications to Pydantic AI and, when warranted, Pydantic AI Harness.

pydantic/pydantic-ai

Uses Meta's LlamaGuard moderation model to screen prompts and model replies against six safety categories, with vLLM, FastAPI and NeMo Guardrails setups.

Orchestra-Research/AI-Research-SKILLs

Prepare independent review of a complete Guardrails change before pushing or updating a PR, using the repository adversarial-review procedure.

openai/openai-guardrails-js

A skill your agent uses when an instructor wants to create, interview for, configure, install, update, or review a course AI-use policy for MATLAB AI tutoring.

matlab/agent-skills-playground

A skill your agent uses when authoring or repairing Kilroy Attractor DOT graphs from requirements, with template-first topology, routing guardrails, and validator-clean output.

danshapiro/kilroy

Diagnose and draft Amazon Canada apparel advertising plans with lifecycle and seasonal timing, English/French search coverage, account evidence, profitability guardrails, and approval-ready…

xjli360/sealeap-amazon-skills

Report/investigate RUNTIME ACTIVITY of AI agents (Agent 365 / Copilot Studio / M365 Copilot / Work IQ) — agents used, tools/connectors, channels, tokens, prompt/reply content, and Prompt Shield…

SCStelz/security-investigator

Design or review specx core scope boundaries in Python services.

maksimzayats/specx

OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation

jnMetaCode/shellward

AI governance, EU AI Act compliance, OWASP LLM security, responsible AI practices for GitHub Copilot agents

Hack23/cia

Run or install repo security leak checks with BetterLeaks and Trivy.

instructa/agent-skills

Generate, edit, and compose images using Gemini Nano Banana models via portable Python scripts.

cnemri/google-genai-skills

Start or resume a requested Guardrails implementation or PR takeover in the selected linked worktree with bounded scope and verification.

openai/openai-guardrails-js