Survey AI/ML literature and recommend implementation strategies for codebases.
npx skills add https://github.com/Borda/.home --skill survey-borda
Please help me install this Agent Skill. Skill: survey Source: https://github.com/Borda/.home/tree/main/.claude/skills/survey Command: npx skills add https://github.com/Borda/.home --skill survey-borda
This Skill automates the process of surveying the State of the Art (SOTA) literature for a given Artificial Intelligence/Machine Learning (AI/ML) topic, method, or architecture, providing actionable insights for implementation.
Use the survey skill to find the best methods for "efficient transformers" in our current PyTorch codebase.
High-intent search queries and answers about installing and using this skill.
To survey AI and ML literature, this Skill identifies relevant SOTA research papers, summarizes key ideas, and constructs comparison tables of benchmark results and compute requirements tailored to your specific codebase constraints.
Yes, you can get an implementation plan for efficient transformers in a PyTorch codebase by evaluating SOTA architectures, comparing code availability, and recommending the best-suited method with a concrete integration strategy.
The best way to compare machine learning research papers for a new project is to build a comparative analysis table of SOTA methods, evaluating key ideas, benchmark results, and resource requirements to recommend an optimal implementation approach.
Yes, the literature review process considers specific codebase constraints by integrating findings from the ai-researcher agent and tailoring implementation recommendations to match your project's architectural requirements and resource limitations.
To identify relevant SOTA papers for a specific AI architecture, this Skill delegates in-depth research to the ai-researcher agent, which surveys the literature and integrates findings into an actionable report with optimal implementation strategies.
wanghao9610Clone reference implementations and generate codearc.md architecture specs.
alphabeenAudit a codebase against a plan document and produce a PASS/FAIL review.
Ronin15Compare SDL3 HammerEngine metrics against baselines to flag performance regressions.
iani-kuliCoordinate ML research paper workflows from experiment design to manuscript drafting.
