Loading...
Loading...
Found 1,018 Skills
Guidance for implementing PyTorch pipeline parallelism for distributed model training. This skill should be used when tasks involve implementing pipeline parallelism, distributed training with model partitioning across GPUs/ranks, AFAB (All-Forward-All-Backward) scheduling, or inter-rank tensor communication using torch.distributed.
Analyze a codebase and generate comprehensive documentation including architecture, components, interfaces, workflows, and dependencies. Creates an AI-optimized knowledge base (index.md) and can consolidate into AGENTS.md, README.md, or CONTRIBUTING.md. Use when the user wants to document a codebase, create AGENTS.md, understand system architecture, generate developer documentation, or asks to "summarize the codebase".
Extract and summarize risk factors from SEC filings using Octagon MCP. Use when analyzing Item 1A risk disclosures, categorizing business risks, identifying new or material risks, and comparing risk profiles across companies or time periods.
Review corporate governance practices and board composition from SEC filings using Octagon MCP. Use when researching board structure, director qualifications, committee composition, governance policies, shareholder rights, and related party transactions from proxy statements.
Simplify and refactor code for clarity, consistency, and maintainability while preserving exact behavior. Use when code was just added or modified and needs readability-focused cleanup without changing outputs, side effects, or external interfaces.
Outbound sales methodology based on Aaron Ross' "Predictable Revenue". Use when you need to: (1) build a scalable outbound sales process, (2) implement Cold Calling 2.0, (3) structure sales team roles (SDR/AE/CSM), (4) design lead generation and qualification frameworks, (5) scale B2B SaaS sales predictably, (6) create prospecting email sequences, (7) build sales development pipeline, (8) separate prospecting from closing.
Rust best practices and code quality guidelines for writing idiomatic, safe, and performant Rust code. This skill should be used when writing, reviewing, or refactoring Rust code. Triggers on tasks involving Rust programming, code review, error handling, type safety, or performance optimization.
Guidance for building and fixing Cython extensions, particularly for numpy compatibility issues. This skill should be used when tasks involve compiling Cython code, fixing deprecated numpy type errors, or resolving compatibility issues between Cython extensions and modern numpy versions (2.0+).
Motivation science framework based on Daniel Pink's "Drive". Use when you need to: (1) design features that leverage intrinsic motivation, (2) create progress systems that support mastery, (3) craft purpose-driven messaging and missions, (4) audit if product mechanics undermine autonomy, (5) design team structures and incentives with AMP principles (Autonomy, Mastery, Purpose), (6) understand why gamification fails, (7) replace carrot-and-stick approaches with intrinsic motivation.
Run Checkov to scan Infrastructure as Code for misconfigurations. Supports Terraform, CloudFormation, Kubernetes, Helm, ARM, Ansible, and Dockerfiles.
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", or "technical debt". Covers smell-driven refactoring, safe transformation sequences, and testing guards. For code quality foundations, see clean-code. For managing complexity, see software-design-philosophy.
Write readable, maintainable code through disciplined naming, small functions, and clean error handling. Use when the user mentions "code review", "naming conventions", "function too long", "code smells", or "readable code". Covers SRP, comment discipline, formatting, and unit testing. For refactoring techniques, see refactoring-patterns. For architecture, see clean-architecture.