Search
LLM guardrails
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. | fossasia/ | 1.6k | 12 repos | ~578 | Automated safety check: Pass | Apache-2.0 | today |
| 2 | Query AI Safety HOT news, research papers, incidents, hot topics, and daily/weekly/monthly reports through its public read-only MCP service. | wuyoscar/ | 827 | — | ~1.4k | Automated safety check: Pass | Unknown | today |
| 3 | 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/ | 4.7k | — | ~461 | Automated safety check: Pass | MIT | 2 days ago |
| 4 | 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/ | 177 | 5 repos | ~3.8k | Automated safety check: Pass | MIT | 4 mo ago |
| 5 | Behavioral guardrails for LLM-assisted coding. An agent skill from alirezarezvani/ClaudeForge. | alirezarezvani/ | 429 | — | ~1.2k | Automated safety check: Pass | MIT | 4 mo ago |
| 6 | Systematically reduce the shipped bundle size of a JS/TS library without sacrificing code readability or breaking consumer APIs. | kcsujeet/ | 351 | — | ~2.9k | Automated safety check: Pass | MIT | today |
| 7 | Interactive scaffold generator for Orloj multi-agent systems. | OrlojHQ/ | 123 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | 22 days ago |
| 8 | Installs, tunes and enforces Sponsio contracts that block unsafe tool calls in LLM agents, covering setup, auditing, observe mode and flipping to enforce. | SponsioLabs/ | 454 | — | ~12k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 9 | Turns a natural-language description of routing intent into a valid Lemonade collection.router policy JSON. | amd/ | 408 | — | ~4k | Automated safety check: Pass | MIT | yesterday |
| 10 | 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/ | 140 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 12 days ago |
| 11 | 11.Iso42001 Expert ISO 42001 AI Management System (AIMS) compliance advisor. | Sushegaad/ | 946 | 1 repo | ~3.7k | Automated safety check: Pass | MIT | yesterday |
| 12 | Installs hooks that check each agent action against security policies before it runs, blocking destructive commands and logging every decision. | pegasi-ai/ | 392 | — | ~1.4k | Automated safety check: Warn | Apache-2.0 | yesterday |
| 13 | Guide for writing eval conversation JSONs and running them through policy engines | open-bias/ | 143 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 14 | 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/ | 351 | 3 repos | ~371 | Automated safety check: Pass | GPL-3.0 | 4 days ago |
| 15 | 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/ | 275 | — | ~2.8k | Automated safety check: Pass | MIT-0 | 5 days ago |
| 16 | 16.Celestia Route Celestia requests to the correct repo and apply canonical blob submit/retrieve guidance (Go, Rust, and Node RPC) with docs guardrails. | celestiaorg/ | 183 | — | ~2.8k | Automated safety check: Pass | No licence | yesterday |
| 17 | Pick the right SDAF BOM for a target SAP product / release / DB platform / version / kernel / topology. | Azure/ | 146 | — | ~1.6k | Automated safety check: Pass | MIT | 2 days ago |
| 18 | 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/ | 449 | — | ~420 | Automated safety check: Pass | MIT | yesterday |
| 19 | A skill your agent uses when we want to turn a just-finished Formax workflow (e.g. | yusifeng/ | 194 | — | ~530 | Automated safety check: Pass | MIT | 2 mo ago |
| 20 | Ship and spec AI features, LLM products, agents, copilots, and generative UX — including when to use a model vs. | andreaskelm/ | 234 | — | ~1.8k | Automated safety check: Pass | Unknown | yesterday |
| 21 | 21.Cx AI Center 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/ | 121 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | 4 days ago |
| 22 | Guardrail tester that checks whether the permission rules and PreToolUse hooks already set up in Claude Code, Codex, Gemini CLI, OpenCode, or Cursor stop a battery of dangerous commands, including… | RyanAlberts/ | 1.1k | — | ~2.9k | Automated safety check: Pass | MIT | 2 days ago |
| 23 | Check user-generated text against a written policy before it is published. | mrmps/ | 424 | — | ~1.5k | Automated safety check: Pass | MIT | 3 days ago |
| 24 | Guide for creating a new policy engine under openbias/policy/engines/ | open-bias/ | 143 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 25 | 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/ | 130 | — | ~1.3k | Automated safety check: Pass | MIT | 2 mo ago |
| 26 | 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/ | 139 | — | ~1.5k | Automated safety check: Pass | No licence | 12 days ago |
| 27 | Select and run Guardrails verification for code, dependency, test, tooling, documentation, or repository-workflow changes. | openai/ | 105 | — | ~619 | Automated safety check: Pass | MIT | 3 days ago |
| 28 | 28.Dsh Playbook How to dispatch well — choosing flash vs pro, writing self-contained briefs, parallelism, verifying results, and guardrails | ZSeven-W/ | 158 | — | ~1.1k | Automated safety check: Pass | MIT | 2 days ago |
| 29 | 29.Typescript TypeScript anti-slop guardrails. An agent skill from web-infra-dev/rstest. | web-infra-dev/ | 505 | — | ~1.3k | Automated safety check: Pass | MIT | yesterday |
| 30 | Always-on operational guardrails, model-independent. An agent skill from mrtooher/fable-mode. | mrtooher/ | 873 | — | ~918 | Automated safety check: Pass | No licence | today |
| 31 | 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/ | 208 | — | ~956 | Automated safety check: Pass | MIT | 5 mo ago |
| 32 | Step-by-step guide for adding a new guardrail provider to Agent Kernel. | yaalalabs/ | 192 | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 33 | Evaluate, rank, and communicate work priorities using AI as a structured thinking partner. | ILoveDotNet/ | 155 | — | ~3.5k | Automated safety check: Pass | CC0-1.0 | 4 days ago |
| 34 | 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/ | 13k | 2 repos | ~2k | Automated safety check: Pass | MIT | 3 mo ago |
| 35 | Migrate Python OpenAI Agents SDK applications to Pydantic AI and, when warranted, Pydantic AI Harness. | pydantic/ | 21k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 36 | Prepare independent review of a complete Guardrails change before pushing or updating a PR, using the repository adversarial-review procedure. | openai/ | 105 | — | ~825 | Automated safety check: Pass | MIT | 3 days ago |
| 37 | Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. | coco-research/ | 531 | — | ~3.3k | Automated safety check: Pass | MIT | today |
| 38 | 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/ | 222 | — | ~6.4k | Automated safety check: Pass | MIT | 5 mo ago |
| 39 | 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/ | 251 | — | ~1.2k | Automated safety check: Pass | MIT | 13 days ago |
| 40 | 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/ | 13k | 2 repos | ~2.3k | Automated safety check: Pass | MIT | 3 mo ago |
| 41 | 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/ | 184 | — | ~1.2k | Automated safety check: Pass | Unknown | yesterday |
| 42 | 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/ | 249 | — | ~17k | Automated safety check: Pass | MIT | 2 days ago |
| 43 | 当需要为 AI 系统设计多层安全防线、内容过滤策略和伦理边界时调用此 skill。典型场景包括：设计拒绝策略与升级机制、防御 prompt 注入攻击、实现领域特定安全规则（教育、医疗、金融等）、定义 AI 的价值观锚点。 | kangarooking/ | 208 | — | ~1.2k | Automated safety check: Pass | MIT | 5 mo ago |
| 44 | Design or review specx core scope boundaries in Python services. | maksimzayats/ | 202 | — | ~1.8k | Automated safety check: Pass | MIT | 2 mo ago |
| 45 | OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation | jnMetaCode/ | 140 | — | ~644 | Automated safety check: Warn | Apache-2.0 | 12 days ago |
| 46 | AI governance, EU AI Act compliance, OWASP LLM security, responsible AI practices for GitHub Copilot agents | Hack23/ | 239 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 47 | Run or install repo security leak checks with BetterLeaks and Trivy. | instructa/ | 139 | — | ~557 | Automated safety check: Pass | No licence | 12 days ago |
| 48 | Generate, edit, and compose images using Gemini Nano Banana models via portable Python scripts. | cnemri/ | 127 | — | ~587 | Automated safety check: Pass | MIT | 8 mo ago |
