Security

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows…

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

App Store Optimization (ASO) — store-side discoverability for the iOS App Store and Google Play: metadata, visual assets, localization, ratings and reviews…

Permission management implementation pattern: RBAC model, permission checking with company-security-sdk, PermissionCheckMixin, and integration with FastAPI/DRF.

This skill should be used when the user asks to "analyze a Dockerfile", "optimize Docker layers", "validate docker-compose", "check container best practices"…

Turns REST API documentation into a runnable curl, fetch, or code example with required headers, request body, and placeholders for secrets.

Configure a minimum release age (cooldown) on package managers so freshly published versions are not installed for N days — a cheap, high-leverage defense…

Use BEFORE any GitHub API write (repo create, PATCH, fork, PR, comment, delete) or any burst of API reads.

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows…

AI model safety scanner built on NVIDIA garak for testing LLMs against 179 security probes across 35 vulnerability families

From an OpenAPI spec (URL or local path), produce an API summary (endpoints, methods, auth) and optionally example calls (curl or code snippets).

Offensive security skill for offensive business logic

Implement "Sign In with OpenRouter" using OAuth PKCE — framework-agnostic, no SDK or client registration required.

Use when verifying a frontend UI change in a real browser before reporting done.

为 Hermes 配置 MiniMax 作为模型源。MiniMax 提供两种接入方式：API Key 直连（openai-completions 协议）和 OAuth 门户（anthropic-messages 协议）。包含 provider 注册、模型定义、别名配置、fallback…

Audits any domain's AI-readiness by using curl to directly probe robots.txt, llms.txt, and llms-full.txt, then scores each file against a structured checklist…

Use when installing the redteam-threat-exploits skill into a Hermes profile and wiring it to a local OpenCTI instance with a reusable launcher.

Offensive security skill for offensive anti forensics

Reviews a ClawHub skill's source code for security risks before installation.

Audits any SDK documentation site and produces a fully scored, downloadable HTML report.

Offensive security skill for bug identification

Use a GitHub repo as a zero-infra, anonymous-friendly data store — JSON files as records, GitHub App bot as the write layer, build-time index compilation as…

Offensive security skill for offensive advanced redteam

Offensive security skill for offensive api abuse