Evaluates Agent Skills (Cursor / Claude / OpenClaw compatible) and produces a quantitative, rubric-based score with actionable improvement suggestions. Use when the user asks to review, rate, audit, grade, lint, or improve a SKILL.md file, a skill folder, or a skill archive, or says things like "给这个 skill 打分", "评估一下 skill 质量", "audit this skill", "rate my agent skill".
Use when bank operations, relationship managers, or credit middle-office teams need to pre-check onboarding, credit, KYB, due diligence, or post-loan documents, route exceptions, track SLA risk, and preserve audit-ready compliance reasoning.
Use when a finance-related Agent Skill does not clearly fit one sub-scenario and needs intake classification, decision-impact assessment, risk boundary review, and recommendations for whether to evaluate it as fundraising, quant trading, stock trading, securities research, banking workflow, financial education, or financial data analysis.
Use when analysts, finance teams, or operators need to clean financial datasets, check data quality, analyze revenue, margin, cash flow, customer value, anomalies, or trends, and produce traceable management-ready insights with confidence caveats.
Use when learners, educators, or financial literacy teams need beginner-friendly explanations, analogies, quizzes, misconception tracking, and safety boundaries for topics such as funds, stocks, bonds, insurance, asset allocation, risk, and return.
Use when the parent pipeline routes a a11y-related PR review request. Reads the diff and emits structured a11yFindings using the a11y specialist heuristics.
Use when the parent pipeline routes a api-related PR review request. Reads the diff and emits structured apiFindings using the api specialist heuristics.
Use when the parent pipeline routes a async-related PR review request. Reads the diff and emits structured asyncFindings using the async specialist heuristics.