Audit and update npm/Bun dependencies with supply chain integrity checks — verifies maintainers, publish age, tarball diffs, and provenance before bumping. Defers risky packages to ~/.supply-chain/notes/.

Testing patterns and principles. Unit, integration, mocking strategies.

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup

Content quality and E-E-A-T assessment for AI citability — evaluate experience, expertise, authoritativeness, trustworthiness, and content structure

Pre-commit/ship code review: Codex default; optional Claude or Pi.

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Write, edit, and maintain documentation. Use for collaborative drafting, autonomous writing, or improving existing docs. Defaults to collaborative mode where the human makes final decisions. Built by Mintlify.

AI Berkshire skill: 投资论文追踪：买入后的纪律系统. Source: skills/thesis-tracker.md.

AI Berkshire skill: 组合管理：从"研究公司"到"管理组合". Source: skills/portfolio-review.md.

AI Berkshire skill: 投研团队：四角色并行分析框架. Source: skills/investment-team.md.

AI Berkshire skill: 行业投资研究：产业链全景扫描 + 四大师个股分析框架. Source: skills/industry-research.md.

AI Berkshire skill: 财报精读团队：四大师并行解读 + 公众号发布. Source: skills/earnings-team.md.

AI Berkshire skill: 财报精读：一手资料深度解读. Source: skills/earnings-review.md.

Gathers comprehensive documentation and best practices for frameworks, libraries, or dependencies. Use when you need official docs, version-specific constraints, or implementation patterns.

Final review pass to ensure code is as simple and minimal as possible. Use after implementation is complete to identify YAGNI violations and simplification opportunities.