LLM guardrails

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

openai/openai-guardrails-js

Guides designing a layered permission pipeline for agent tools that decides which calls are allowed, need confirmation or are denied, with scopes and hooks.

simbajigege/book2skills

Diagnose and strengthen a repository's harness layer: AGENTS.md rules, knowledge layout, architecture boundaries, lint and type gates, API and generated-client contracts, test scaffolding…

PacificStudio/openase

Medium-native long-form research, author-assistance, writing, editing, review, topic discovery, publication matching, and packaging workflow.

flaqai/backlink_skills

Screen LLM input and output with TypeSafe Jev Noul hazard batteries plus a harm Score; policy in code returns pass, review, or block.

cobusgreyling/Jev

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

WandB-specific PerforatedAI integration guardrail skill. An agent skill from PerforatedAI/PerforatedAI.

PerforatedAI/PerforatedAI

A skill your agent uses when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent orchestration, optimizing cost, or adding AI safety…

kid-sid/claude-spellbook

Choose bounded implementation scope and existing owning modules before Guardrails runtime, configuration, client, resource, streaming, Agents, or SDK compatibility changes and feedback fixes.

openai/openai-guardrails-js

Build content moderation applications with Azure AI Content Safety SDK for Java.

microsoft/skills

Azure AI Content Safety SDK for Python. An agent skill from microsoft/skills.

microsoft/skills

Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers.

openai/openai-guardrails-js

A skill your agent uses when reviewing, auditing, scoring, or improving a real or synthetic MATLAB AI tutor transcript, tutoring prompt, generated lesson, exercise, feedback sequence, or skill…

matlab/agent-skills-playground

NVIDIA's runtime safety framework for LLM applications. An agent skill from Orchestra-Research/AI-Research-SKILLs.

Orchestra-Research/AI-Research-SKILLs

Applies the reasoning style of Geoffrey Hinton, deep learning pioneer and 2018 Turing Award winner.

K-Dense-AI/mimeo

Add strict Python project tooling for a specx service. An agent skill from maksimzayats/specx.

maksimzayats/specx

A skill your agent uses when the user wants to tailor a workflow for a specific industry, domain, or vertical with specialized expertise, terminology, and guardrails.

sharpdeveye/maestro

A skill your agent uses for all frontend and web UI tasks by default to apply a business-agnostic desktop web visual style system with medium-strength guardrails; if an existing design system is…

yusifeng/formax

Configure the shared guard against catastrophic shell commands in local AI agents.

davidondrej/skills

Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.

sickn33/agentic-awesome-skills

A skill your agent uses when reasoning about generative AI, adversarial machine learning, neural network security, algorithmic fairness, or deep learning fundamentals.

K-Dense-AI/mimeo

LLM-powered quality verification using prompt hooks. An agent skill from rohitg00/pro-workflow.

rohitg00/pro-workflow

Meta's 86M prompt injection and jailbreak detector. An agent skill from Orchestra-Research/AI-Research-SKILLs.

Orchestra-Research/AI-Research-SKILLs

Creates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards).

lyndonkl/claude

Generate documents with writefile when retrieval tools fail, with explicit guardrails against task context drift

HKUDS/OpenSpace

Apex code quality guardrails for Salesforce development. An agent skill from github/awesome-copilot.

github/awesome-copilot

AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt…

telagod/code-abyss

Design spec with 98 rules for building CLI tools that AI agents can safely use.

sickn33/agentic-awesome-skills

Builds your north star metric, a metric tree with owned input metrics and guardrails, and a review cadence, as a one-page metrics spec you can paste into a doc.

menkesu/awesome-pm-skills

Find, compare, adapt, and design bounded AI-agent feedback loops with explicit checks, stop rules, guardrails, and handoffs.

sickn33/agentic-awesome-skills

Authorized Android/iOS application reverse engineering and security testing: APK/IPA analysis, runtime instrumentation (Frida/Objection), SSL-pinning and jailbreak/root-detection bypass, per OWASP…

sickn33/agentic-awesome-skills

Wires Promptfoo and DeepTeam into CI/CD for automated, repeatable red-teaming of LLM apps against OWASP LLM Top 10, OWASP Agentic, and MITRE ATLAS presets, failing the build when jailbreak or…

mukul975/Anthropic-Cybersecurity-Skills

Implements input/output validation guardrails for LLM applications using NVIDIA NeMo Guardrails (Colang), custom Python validators for PII detection, and the Guardrails AI framework, intercepting…

mukul975/Anthropic-Cybersecurity-Skills

Senior engineer CLI expertise for AI agents — workflows, safety guardrails, gotchas, and anti-patterns across cloud, IaC, containers, databases, dev tools, and platforms

SylphAI-Inc/skills

Add or refine tests for specx Python services. An agent skill from maksimzayats/specx.

maksimzayats/specx

Autonomous AI code generation safety guardrail register: static AST analysis, forbidden import filters, and zero-day vulnerability checks.

sickn33/agentic-awesome-skills

Deploy frontend and full-stack apps on Vercel with previews, edge functions, environment promotion, and production guardrails.

sickn33/agentic-awesome-skills

Deploys a baseline landing zone foundation for a Google Cloud Organization, establishing security guardrails using Organization Policies, resource hierarchy folders and projects, billing…

google/skills

A skill your agent uses when managing Alibaba Cloud Content Moderation (Green) via OpenAPI/SDK, including the user needs content moderation resource and policy operations, including…

cinience/alicloud-skills

A skill your agent uses when writing, reviewing, or refactoring Manor code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

manor-os/manor-ai

Use before creating a worktree, script, or ad hoc orchestration, handling generated Bazel artifacts, changing native add-ons, or adding serviceradarcore tests.

carverauto/serviceradar

Application security defense knowledge for builders. An agent skill from telagod/code-abyss.

telagod/code-abyss

Control bkit automation level (L0-L4), view trust score, and manage guardrails.

ww-w-ai/bkit-claude-code

Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety.

NVIDIA/skills

AI text humanization and 윤문 (post-editing) specialist that detects and removes AI tells while preserving meaning, facts, and figures.

modu-ai/moai-adk

Run an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem from production data, makes one bounded…

PostHog/posthog

Creates a reusable use case specification file that defines the business problem, stakeholders, and measurable success criteria for model customization, as recommended by the AWS Responsible AI Lens.

awslabs/agent-plugins

Safety guardrails — blocks destructive commands (rm -rf, DROP TABLE, force-push, git reset --hard) and optionally restricts file edits to a specific directory.

Houseofmvps/ultraship