Results for “severity-classification”

Severity-tagged code review checklist (CRITICAL/HIGH/MEDIUM/LOW) used by code-critic agent

Audits test code in any language using the academic testsmells.org 19-smell catalog, producing a severity-ranked report with specific locations and actionable fixes.

Analyse text complexity across quantitative, qualitative, and reader-task dimensions with scaffolding recommendations. Use when selecting texts, assessing readability, or planning reading support.

Build a multi-factor asset criticality scoring model to weight vulnerability prioritization based on business impact, data sensitivity, and operational importance.

選択肢(A/B/C)の深掘り比較→淘汰→推奨で判断負担を下げ判断の質を上げるスキル。5段階（L1固定3点/L1.5案拡張Diverge・自動/L2評価軸マトリクス/L3複数LLM弁証論/L4過去判断照合）。 「比較して」「深掘りして」「メリデメ教えて」「お勧めは？」「徹底的に」「過去の判断と照合」「前にどう決めたっけ」「/sentaku」等で発火。teian(浅)の深掘り要求を受け取り、brainstorming(深:設計全体)と棲み分け。

OWASP Top 10 + Supabase-first hardening burndown. Use when "security audit plan", "OWASP audit", "hardening plan", or "security burndown". App-layer auth flows → audit-auth-flows. Table RLS → plan-rls-audit. Key rotation → plan-secrets-audit. App LLM attacks → audit-llm-security.

Analyzes algorithm time and space complexity, classifies problems by complexity classes, proves NP-completeness, and designs approximation algorithms.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Evaluates the robustness and alignment with human judgment of reference-based and reference-free evaluation metrics for machine translation and summarization, particularly under adversarial conditions.

Quantifies how sensitive a language model benchmark's reliability and ranking stability are to specific design choices, such as the selection of scenarios, subscenarios, examples, and few-shot prompts. Use when the user has predictions and gold and needs to compute DIoR.

AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.