📊 AI Training Dataset Quality Audit | Production-grade Codex skill for pre-training dataset auditing (balance, bias, leakage, ethical fitness). Binds scores to named frameworks (NIST, Gebru's Datasheets) and uses a crawl4ai pipeline.
npx skills add dungnotnull/ai-dataset-quality-audit-agent-skill📊 AI Training Dataset Quality Audit | Production-grade Codex skill for pre-training dataset auditing (balance, bias, leakage, ethical fitness). Binds scores to named frameworks (NIST, Gebru's Datasheets) and uses a crawl4ai pipeline.
Evidence-first current-state research workflow for ECC. Use when the user wants fresh facts, comparisons, enrichment, or a recommendation built from current public evidence and any supplied local context.
Codex skill for citation-backed PhD professor dossier research
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.
Organize real academic research workflows with Claude Code skills for literature tracing, source verification, and bilingual paper search
This skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design". Use for architecture decision records (ADRs), tech stack evaluation, system design reviews, dependency analysis, and generating architecture diagrams in Mermaid, PlantUML, or ASCII format.
Permission Set analysis, hierarchy viewer, and access auditing. TRIGGER when: user asks "who has access to X?", analyzes permission sets/groups, or touches .permissionset-meta.xml / .permissionsetgroup-meta.xml files. DO NOT TRIGGER when: creating new metadata (use sf-metadata), deploying permission sets (use sf-deploy), or Apex sharing logic (use sf-apex).