AI Agent Skills

awesome grounding: A curated list of research papers in visual grounding

Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.

Quant-focused research ideation pipeline: scope selection (3 stages) → anchor-first literature grounding → single-core idea generation → iterative refinement → ELO tourn…

Use when the user wants to generate and literature-vet a pool of novel, testable research hypotheses for a question or domain. A multi-agent loop: a Generator proposes c…

Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside…

Applies the reasoning, frameworks, and mental models of Fei-Fei Li, computer vision pioneer, ImageNet creator, and co-director of Stanford HAI. Use this skill whenever C…

Plan and synthesize evidence-grounded product research. Use when deciding what evidence is needed, designing actor walkthroughs, grounding claims in a repository or live…

Write or rebuild one unsettled KB artifact through source-first reconstruction, consolidated authorship, independent review, and guarded promotion. Use when claims need…

Human-guided Research Agent Skill for Master and PhD students in CS, AI, math, and engineering: literature grounding, novelty gates, math formalization, experiment plann…