Skill UI

Design and evaluate LLM product features, retrieval, validated outputs, latency, and cost controls. Covers LLM integration patterns, RAG architecture, scalable prompt engineering, trustworthy AI UX, and cost optimization strategies for sustainable AI implementation in production environments.

AKF is an AI-native file format that embeds trust scores, source provenance, and compliance metadata into various file types like DOCX, PDF, and code. It supports auditing for regulations such as the EU AI Act, SOX, and HIPAA, ensuring transparency and accountability in AI-generated content workflows.

This skill enables independent auditing of AI agent, gateway, or automation workflow runs. It reconstructs events from traces, checkpoints, and tool calls to verify success claims without trusting self-reports. Users establish contracts, build claim ledgers, normalize evidence, rank witnesses, and assign verdicts like proven or contradicted. It ensures integrity in multi-step automation and separates autonomous success from human-assisted outcomes.

This skill audits visual, verbal, and behavioral brand signals to diagnose gaps between market perception and intended brand position. It prescribes alignment changes to close perception gaps, ensuring consistency across touchpoints. Useful for repositioning brands, shifting trust, and aligning identity signals.

Score any MCP server, API, or CLI for agent-readiness using Clarvia AEO (Agent Experience Optimization). Evaluate tools across four dimensions: API accessibility, data structuring, agent compatibility, and trust signals. Supports scoring, searching, comparing, and leaderboard queries.

Learn how to secure internal applications and services using Cloudflare Zero Trust platform. This skill covers setting up Cloudflare Tunnels to replace VPNs, configuring Access policies for identity-aware authentication, and managing device posture checks. It includes instructions for installing cloudflared, creating tunnel configurations, routing DNS, and implementing Access applications via API. Suitable for DevOps engineers and security professionals managing hybrid cloud infrastructure.

This skill builds a deep psychological profile of target customers based on motivations, fears, identity, and trust barriers. It goes beyond demographics to understand emotional drivers and worldview. Use this before positioning, copywriting, or funnel design to create evidence-grounded profiles that downstream skills can consume. It applies frameworks like self-determination theory and identity mapping to infer the psychological structure underlying consumer behavior.

Helps create and maintain a foundational document capturing target developer personas, pain points, channels, alternatives, and trust signals for developer marketing.

Verify an AI agent's 'done, shipped, or fixed' claims against git ground truth using the DOS kernel's dos verify and dos commit-audit commands, instead of trusting the agent's own narration or self-report.

A portable discipline for type safety at the network edge of React apps. It establishes a single typed API client as the fetch boundary, enforcing parse-don't-validate rules to transform wire JSON into trusted domain types. This approach normalizes errors and uses branded identifiers to prevent silent bugs, ensuring untyped data never escapes the boundary.

Evaluate content quality and E-E-A-T signals for AI citability. Assess experience, expertise, authoritativeness, trustworthiness, and content structure to optimize for AI search platforms.

This skill detects when AI agents exploit human trust through social engineering, deceptive guidance, or false assurances. It identifies prompts that induce unsafe actions, request sensitive credentials, or impersonate authority figures. Use this when evaluating agent safety, security advice, or decision-influencing workflows. Skip for static information.