Skill UI

This tool performs a deep, recursive, and parallel investigation, building a comprehensive graph-structured dossier around a specified seed entity. It expands outward across diverse sources, including web search, internal memory stores, codebases, and knowledge graphs. It captures all connected entities and the provenance of every claim, making it ideal for mapping the full context or relationship network of a subject.

A specialized audit skill designed to identify and quantify resource leakage, excessive costs, and billing vulnerabilities within complex development tool workflows (e.g., GitHub Apps). It traces webhook events, queue processing, and model calls to pinpoint where token burn or unauthorized resource usage is occurring, ensuring cost efficiency and clean billing practices.

This tool provides comprehensive querying and analysis of structured federation audit logs. It is essential for security and compliance teams, allowing filtering by specific regulatory frameworks (HIPAA, SOC2, GDPR), date ranges, and event severity. Users can summarize key findings including total events, PII detections, threat blocks, and trust changes to ensure adherence to strict industry and governmental standards.

This tool provides a comprehensive overview of the federation's operational status. It allows users to check overall health, list connected peers along with their trust levels and scores, and summarize crucial metrics like active sessions, message exchanges, PII redactions, and detected threats. Use it to inspect cross-installation agent connectivity and ensure the stability of the federated system.

A comprehensive multi-agent feedback loop inspired by Generative Adversarial Networks (GANs), designed to build complex, production-ready applications. It separates generation from evaluation, using a 'ruthlessly strict' evaluator (QA) to drive continuous iteration. This process ensures high design quality, robust functionality, and originality, overcoming the limitations of single-agent self-critique. Ideal for full-stack feature development and complex product specification implementation.

This skill guides the operation, consolidation, and maintenance of complex working systems within Google Workspace (Docs, Sheets, Slides). It emphasizes treating files as integrated systems—such as trackers or planning hubs—requiring careful inspection, precise edits, and structural cleanup rather than simple content rewriting. Use it for consolidating scattered data, cleaning shared spreadsheets, or ensuring the correct canonical version of a document is utilized.

A structured method for transforming experience (especially failures and complex tasks) into actionable, reusable knowledge. Instead of simple diary entries, this skill guides the user to extract root causes, identify underlying patterns, and articulate what they must do differently next time, thereby accelerating professional learning and debugging efficiency.

This tool simplifies the process of detecting structural drift by combining audit listing, fresh auditing, and trend diffing into a single command. It finds the most recent audit record, runs a current audit against the repository, and compares the two using structural similarity metrics. It alerts when the structural distance falls below a specified threshold, helping maintain code consistency over time.

This tool provides deep inspection and auditing capabilities for GEPA (genetic-evolution prompt-adaptation) genomes by utilizing the internal `@metaharness/darwin/gepa` library. It is crucial for advanced AI development pipelines, allowing users to validate the structural integrity of genomes, render the full system prompt derived from a genome, or classify specific failure modes found in an execution transcript. Ideal for CI/CD gating and debugging complex LLM applications.

This skill generates an enterprise-grade threat model report using the `harness threat-model` command. It categorizes threats across the MCP surface, providing a detailed report including the overall worst severity (clean, low, medium, high) and specific findings. Ideal for pre-launch security reviews and periodic audits when sharing findings with an InfoSec team.

Hookify rules enable developers to define custom, event-driven workflows using Markdown files with YAML frontmatter. These rules monitor specific operational events (such as bash commands, file edits, or user prompts) and can trigger warnings or block operations when predefined regex patterns are matched. They are essential for enforcing coding standards, preventing dangerous operations, and guiding development adherence in complex software environments.

This skill helps transform vague product or engineering ideas into structured, verifiable acceptance criteria (AC). It is crucial for high-impact changes involving security, data migration, or external APIs. By inspecting existing context and asking minimal, targeted questions, it produces clear, observable criteria, significantly de-risking the development process and ensuring handoff readiness.