Skill UI

Guides building reliable autonomous agents by covering agent loops, goal decomposition, reflection, and tooling patterns while stressing guardrails, human review, and auditability to curb compounding failure rates in production.

Audits prose for 21 AI-writing patterns, swaps flagged terms via a 43-entry table, rewrites the passage with human phrasing, and runs a second-pass review so content sounds natural before publishing.

This skill orchestrates end-to-end autonomous AI research projects using a sophisticated two-loop architecture. It manages the entire research lifecycle, from initial literature review and hypothesis formation to running constrained experiments and synthesizing findings into publishable papers. It acts as a project manager, autonomously driving the process while structuring the workspace and presenting progress to human users.

Analyzes accumulated ARIS usage logs to propose optimizations for SKILL.md prompts, reviewer settings, and workflow defaults. A read-only producer that stages patches for human-gated review.

Three-layer verification pipeline that extracts verifiable claims from AI output, searches the web for supporting or contradicting sources, flags hallucinations, and builds structured reports for human review.

This skill structures a highly controlled, bounded development life cycle for AI agents. It mandates a structured three-phase workflow: Planning (Spec), Implementation (Build), and Verification (Review). It is essential for building complex features from scratch, especially when dealing with ambiguous requirements, high risk, or needing explicit human approval gates to ensure the resulting code meets all defined specifications.

This skill guides the architectural design of an Itô Data Atlas agent for advanced quantitative research. It facilitates market discovery, constructs candidate prediction-market baskets, drafts necessary parameter changes, and integrates human-in-the-loop review. It is strictly for workflow and architectural planning, and does not execute live trading orders.

This skill guides authors on positioning their manuscript for the ACM/IEEE International Conference on Human-Robot Interaction (HRI). It helps determine if the work fits the venue, how to re-frame the narrative, and what evidence (user studies, interaction contribution) is expected by HRI reviewers. Ideal for pre-submission strategy and scope calibration in human-robot interaction research.

Audits AI-assisted legal, compliance, governance, and institutional decisions before reliance to determine whether the responsible human or institution has enough access to evidence, reasoning, uncertainty, authority, and review path to genuinely own the decision rather than merely approve, sign, or transmit it.

Transform a legal professional's bounded knowledge, workflow, or judgment patterns into a safe, structured, and reusable AI skill. This tool processes inputs like legal memos, compliance checklists, or negotiation notes to extract core capabilities, risk taxonomies, and review standards. It strictly separates the extracted capability from the individual's personal voice or identity, ensuring full source traceability and mandatory human review points for high-stakes legal work.

This tool automates the cleanup and standardization of complex legal documents written in French (Word format). It distinguishes between deterministic corrections (typography, spacing, obvious errors) applied automatically, and context-sensitive revisions (judgment rewrites) that require intelligent human review. It generates a detailed, reversible registry of all changes, ensuring high accuracy for professional legal writing.

This skill acts as an expert model-routing advisor for reviewing legal agreements (NDAs, MSAs). Instead of reviewing the contract itself, it analyzes the document's nature—such as dominant sub-task (extraction, reasoning, redlining), stakes, and length—to recommend the optimal primary and fallback LLM. It provides comprehensive decision support, mitigating common errors and suggesting necessary human verification points.