Expert startup business analyst specializing in market sizing,

Performs comprehensive code reviews of GitLab merge requests, analyzing code quality, security, performance, and best practices. Use when the user says "review" or "code review" or asks to review...

Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and...

Functional error handling and nullable value management using fp-ts Option and Either types

Build knowledge graphs for support systems, connecting concepts, articles, and solutions

Master the Effect AI LanguageModel service for text generation, structured output, streaming, and tool calling. Use when working with LLM interactions, schema-validated responses, or building...

Analyzes legacy JCL (Job Control Language) scripts to assist with migration to modern workflow orchestration and batch processing systems. Extracts job flows, step sequences, data dependencies,...

Perform comprehensive code reviews using Google Gemini CLI to identify bugs, security vulnerabilities, performance issues, and code quality problems. Use after code changes, before commits, during...

CloudBase platform knowledge and best practices. Use this skill for general CloudBase platform understanding, including storage, hosting, authentication, cloud functions, database permissions, and...

Code review expert for security, quality, and performance analysis. Use when reviewing code, PRs, conducting security audits, or identifying performance issues.

|

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for...

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for...

Generate creative logo concepts and design directions

|

Use to stress-test predictions by assuming they failed and working backward to identify why. Invoke when confidence is high (>80% or <20%), need to identify tail risks and unknown unknowns, or...

Write scientific manuscripts. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), abstracts, for research papers and journal submissions.

Write scientific manuscripts. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), abstracts, for research papers and journal submissions.

Creating algorithmic art using p5.js with seeded randomness and interactive

Pytest test development for Python microservices. Use when writing unit tests, integration tests, fixtures, mocking external services, or setting up test infrastructure. Triggers on requests to...