survey
Survey State of the Art (SOTA) literature for an Artificial Intelligence / Machine Learning (AI/ML) topic, method, or architecture. Finds relevant papers, builds a comparison table, and recommends the best implementation strategy for the current codebase. Delegates deep analysis to the ai-researcher agent.
npx skills add majiayu000/claude-skill-registry --skill survey --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
<objective> Survey the literature on an AI/ML topic and return actionable findings: what SOTA methods exist, which fits best for the current use case, and a concrete implementation plan. This skill is an orchestrator — it gathers codebase context, delegates literature search and analysis to the ai-researcher agent, and packages results into a structured report. This skill is NOT for doing research or designing experiments — use the `ai-researcher` agent directly for hypothesis generation, ablation design, and experiment validation. </objective> <inputs> - **$ARGUMENTS**: topic, method name, or problem description (e.g. "object detection for small objects", "efficient transformers", "self-supervised pretraining for medical images"). </inputs> <workflow> ## Step 1: Understand the codebase context Before searching, read the current project to extract constraints: - Framework in use (PyTorch, JAX, TensorFlow, scikit-learn)? - Task being solved (classification, detection, generation, regression)? - Constraints (latency, memory, dataset size, compute budget)? ## Step 2: Research & codebase check (run in parallel) ### 2a: Spawn ai-researcher agent (issue with 2b simultaneously in one resp
- Step 1: Understand the codebase context
- Step 2: Research & codebase check (run in parallel)
- 2a: Spawn ai-researcher agent (issue with 2b simultaneously in one response)
- 2b: Check for existing implementations (main context)
- Step 3: Report
- Team Mode
What does the survey skill do?
Survey State of the Art (SOTA) literature for an Artificial Intelligence / Machine Learning (AI/ML) topic, method, or architecture. Finds relevant papers, builds a comparison table, and recommends the best implementation strategy for the current codebase. Delegates deep analysis to the ai-researcher agent.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill survey --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.