Skill UI

This skill helps legal teams evaluate and classify legal risks using a severity and likelihood matrix. It calculates risk scores to determine appropriate actions, from monitoring low risks to escalating critical issues to senior counsel. Useful for contract review, deal exposure analysis, and compliance management.

Scores a manuscript against a specific venue's documented desk-reject triggers and returns a ranked, fixable risk report. Use before submission after mechanical readiness is confirmed.

This skill routes goals through the acc's scored-memory loop using acc_act with runtime="solve". It enables deliberation on returned brain_frames and submission via continue. Users must reason over frames and end proposals with a prediction score. It ensures honest commitment closure and prevents solo-derivation outside the loop.

Design LLM-as-judge rubrics, direct scores and pairwise comparisons. Use for judge models, evals, position bias and calibration against human labels.

Evaluate AI agent behavior using versioned cases and explicit verifiers. This skill helps compare agent or prompt changes, reproduce failures, and run regression tests. It ensures reliability on declared task distributions without inferring product readiness from generic scores. Includes methods for uncertainty reporting and safety verification.

Audit local AI coding-agent sessions with agenttrace to inspect token and cost spikes, tool failures, retry loops, latency, anomalies, health scores, diffs, and CI gates. Use for debugging slow, expensive, or unreliable runs and comparing attempts.

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.

Spectral vector search using graph Laplacian eigenstructure. Augments nearest-neighbour search with lambda-tau scores, capturing both semantic similarity and structural role in embeddings. Ideal for RAG pipelines and graph-based retrieval where cosine/L2 similarity misses latent structure.

Design, test, and deploy an automated triage agent for Monte Carlo alerts. Fetch, score, and troubleshoot alerts using MCP tools, then classify and take actions. Build a reusable workflow that matches your team's response process.

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.

This skill enables you to act as an elite AI-powered customer support specialist. It covers conversational AI, automated ticketing, sentiment analysis, and omnichannel support experiences. You will master best practices for customer experience optimization, knowledge management, and analytics. Ideal for improving satisfaction scores, reducing resolution times, and driving loyalty through intelligent automation and personalized service across various channels.

A skill for detecting and removing AI-sounding patterns in Chinese writing. It scores drafts for AI-smell using a deterministic formula, rewrites against 35 known patterns (e.g., 赋能, 闭环, 首先-其次-最后), and optionally clones reference styles or produces variants. Ideal for editing marketing copy, WeChat articles, and social posts to sound human-authored.