Skill UI

A 98-rule design specification for building AI-native CLI tools across three certification levels. Covers structured JSON output, error handling, input contracts, exit codes, safety guardrails, self-description, and agent feedback loops.

This skill helps secure Large Language Model (LLM) and AI deployments against various threats including prompt injection, data exfiltration, model theft, and supply chain attacks. It covers implementing guardrails, output filtering, PII scrubbing, and API security measures to ensure compliance with standards like SOC2 or ISO 27001.

This skill rewrites user prompts to reduce false-positive safety triggers in AI models without bypassing policies or altering intent. It specifically targets cyber, bio/chem, and reasoning classifiers by abstracting sensitive domains and reframing offensive language into defensive equivalents. Useful for developers and researchers needing to test or discuss sensitive topics within safety guardrails.

This skill enables security professionals to conduct authorized assessments on Linux systems, identifying misconfigurations and vulnerabilities that allow privilege escalation from standard users to root. It covers techniques like SUID exploitation, sudo misconfigurations, and cron job hijacking, strictly requiring written authorization and defensive guardrails.

Secure OpenClaw deployments with preflight hardening checks, CI/CD guardrails, container runtime restrictions, and post-deploy verification. This skill provides a repeatable security workflow for build pipelines, container runtime lockdown, production promotion gates, data protection, and incident-ready rollback patterns.

This skill helps design honest scarcity and urgency messaging based on verified inventory, capacity, or deadlines. It creates genuine psychological motivation without manipulation, ensuring trust is preserved. It involves audience research, ethical guardrails, and matching tone to cynicism levels to drive timely decisions effectively.

This skill generates a concise and enforceable security policy document for applications handling sensitive data. It creates a single coherent Blue Book using MUST, SHOULD, and CAN language, defining explicit assumptions, scope, and security gates. The workflow includes gathering context, drafting the policy, enforcing guardrails against secrets, and performing quality checks on threat models and data handling rules.

This skill enables developers to deploy frontend and full-stack applications on Vercel efficiently. It covers setting up preview environments for pull requests, configuring edge functions, managing environment variables across different stages, and implementing production guardrails. Includes integration with GitHub Actions for automated CI/CD pipelines and security best practices like custom domains and headers.

A comprehensive skill for conducting client-side injection vulnerability assessments on web applications. It identifies XSS and HTML injection flaws, demonstrates exploitation techniques for session hijacking and credential theft, and validates input sanitization and output encoding mechanisms. Includes practical examples and strict safety guardrails.

Policy and workflow for reviewing AI-generated code before merge or execution. Covers AST-based static checks, dependency advisories, isolated behavior tests, and evidence collection with language-specific coverage limits.

Prepare an AI outbound phone call end-to-end: research the callee, define the objective and fallback, draft a natural branching script with guardrails, and generate a post-call summary template.