Skill UI

This meta-skill automates the complex process of modernizing legacy PDF documents (e.g., historical contracts, scanned manuals, legal documents). It follows a structured four-step pipeline: structural extraction, natural-language rewriting of problem pages, generating an audit summary, and finally re-merging the content into a single, refined PDF. This ensures content is modernized while maintaining fidelity to the original meaning, providing a human review summary before finalization.

This utility reads the raw content of a UTF-8 text file and emits it verbatim to stdout. It is specifically designed for meta-skills that require round-tripping an artifact through disk, allowing users to manually edit structured files (like scripts or YAML) during review pauses. Unlike standard built-in readers that add line numbering, this method preserves the original bytes, making it suitable for downstream parsers.

A human-in-the-loop studio for iteratively tuning AI outputs or reviewing complex media/prose. It allows users to directly manipulate visual parameters (color, typography, layout) or annotate documents in real-time, moving beyond static comparison grids or vague prompts. Perfect for designers and content creators who need hands-on, visual feedback.

Generates complete, highly structured, and sequenced multi-email campaigns for various purposes, including user onboarding, product launches, lead nurturing, and re-engagement. The skill creates detailed content for each email, including attention-grabbing subject lines, preview text, full body copy, primary CTA button text, and a strategic note explaining the psychological intent. It ensures the entire sequence maintains a consistent narrative arc while allowing each email to stand alone.

This skill generates comprehensive, academic-style survey papers as a single, self-contained HTML file. By reading an anchor resource and curating research data, it structures the content and utilizes advanced LLMs (like Kimi K2.6 via Fireworks) to generate all prose, figures, and bibliographies, suitable for rapid academic literature review.

The Santa Method is a multi-agent adversarial verification framework designed to improve output quality by requiring two independent reviewers (Agent B and Agent C) to pass the content before publication. It eliminates single-agent bias and systematically improves outputs through iterative refinement loops until convergence or manual escalation.

This comprehensive skill provides best practices for secure coding across multiple domains. It guides developers on managing secrets, validating user input, preventing SQL injection, implementing robust authentication and authorization (including RLS), and mitigating XSS attacks. Use this when handling sensitive data, APIs, or user-generated content to ensure the highest level of security.

This comprehensive dashboard aggregates critical health metrics across all client brands in an agency portfolio. It provides a single-view snapshot of campaign status, budget pacing, KPI attainment, content pipeline, and team utilization, essential for leadership standups and weekly agency reviews.

Tool to embed C2PA (Content Provenance) manifests into AI-generated multimedia assets (image, video, audio, PDF). This mechanism adds a machine-readable provenance trail detailing the generator, prompt, and review history. Essential for complying with global regulations like the EU AI Act Article 50, ensuring verifiable digital authenticity, and building brand trust.

This comprehensive tool runs content through six critical scoring dimensions: content quality, brand voice, hallucination risk, claim verification, output structure, and readability. It generates a composite score, flags specific issues with actionable fix suggestions, and ensures compliance against defined brand guidelines. Essential for pre-publication reviews, client sign-offs, and continuous quality tracking.

This tool provides a holistic, portfolio-level quality assessment by evaluating multiple content pieces (assets, libraries, or deliverables) simultaneously. Instead of reviewing content one by one, it processes the entire set to generate comprehensive rankings, dimension breakdowns (e.g., brand voice, claim verification), systemic issue reports, and a prioritized revision list. Ideal for content audits, pre-launch checks, and large campaign reviews.

This skill allows users to manage and switch between different active brand profiles within a multi-client or agency environment. It is essential for maintaining context accuracy across diverse workflows. Users can list all available brands, switch the active profile using a unique brand slug, and review key brand attributes. It ensures that all subsequent generated content adheres to the correct brand's voice, compliance rules, and business context.