Skill UI

Translate cybersecurity findings into defensible 0-100 A-F risk scores, FAIR-aligned dollar loss estimates, and board-ready summaries. Passive analysis only, with ownership-aware confidence caps and attack-path amplification. Ideal for scoring risk, quantifying exposure, estimating breach cost, or explaining risk grades.

Hivemind is an advanced orchestration layer designed to manage complex tasks using a parallel swarm of external, low-cost workers. It simulates a structured team workflow (scout, coder, tester) to decompose large problems, execute subtasks in isolated worktrees, synthesize aggregated results, and perform consensus reviews. This dramatically reduces token costs and enhances reliability for large-scale coding, research, and testing tasks.

A vendor-neutral, benchmark-grounded advisor that routes complex legal tasks to the optimal Large Language Model (LLM). It analyzes the specific legal vertical (e.g., contract drafting, legal research, info extraction) and user constraints (cost, speed, accuracy, jurisdiction) to recommend a primary model, a fallback, and crucial human verification steps. This tool provides decision support, not legal advice.

This framework moves beyond simple storage solutions (like vector databases) to treat memory as a complex metabolic system. It provides tools and methodologies to audit, price, and govern an agent's memory, focusing especially on the forgetting policy. Key functions include cost profiling (construction vs. query energy), classifying stored records (fact/skill/log), and ensuring a mandatory forgetting policy to prevent state bloat and maintain performance.

This skill assists in-house legal teams in architecting external counsel panels. It helps define optimal panel structures, establish weighted selection criteria for law firms, and perform right-sourcing analyses (tiering). Users can assess coverage gaps, optimize legal spend, and transform informal vendor relationships into strategic, data-driven frameworks, ensuring cost efficiency and strategic alignment.

This internal gate performs a deterministic, early check on the readiness of source materials for meta-paper writing. It runs after source curation and before expensive section generation, verifying that the curated, verifiable bibliography meets the required numeric citation target and structural criteria. This prevents costly generation attempts if the source coverage is insufficient or invalid.

This skill estimates the download size and sync frequency cost of an offline profile before pushing it to users. It performs read-only diagnostics, verifying the profile, counting rows per table with scope filters, and calculating cache size. Useful for sanity checks before setup or assignment to prevent data cap surprises.

A specialized skill for legal project management, designed to model, review, and optimize legal matter team structures. It identifies resource conflicts, assesses team gearing (ensuring the right grade mix is used), plans for team continuity during absences, and analyzes resource over-allocation across multiple matters. It helps law firms ensure cost efficiency and appropriate staffing levels.

A sophisticated model-routing advisor for generating, redlining, or rewriting contract language. It determines the optimal LLM based on user constraints (stakes, cost, speed, jurisdiction) and grounds its recommendations in legal benchmarking evidence. It provides a primary model, fallback, and critical warnings.

This tool acts as a model-routing advisor for extracting structured data from complex legal documents, such as contracts. It analyzes key parameters—including stakes, cost, required speed, and document type (e.g., scanned vs. clean digital)—to recommend the optimal LLM model combination (Primary, Fallback, Avoid). It provides critical decision support, guiding users on which AI approach to use for extracting clauses, dates, and parties, without performing the actual extraction.

A model-routing advisor for complex legal research and analysis tasks, including issue-spotting, rule application, and case law interpretation. It guides users in selecting the optimal Large Language Model (LLM) by assessing critical factors such as stakes (risk), cost, speed, and data jurisdiction. It provides a structured recommendation (Primary, Fallback, Avoid) to ensure decision support, not legal advice.

This tool serves as a model-routing advisor for high-stakes legal translation tasks, covering contracts, statutes, and case law. It does not perform the translation itself, but instead provides expert decision support by recommending the optimal primary and fallback LLMs based on language pair, required privacy level, cost, and speed. Crucially, it emphasizes that human legal-linguist review is mandatory, as no single LLM can guarantee certified legal accuracy.